Hugging Face's logo

Xenova
/
nomic-embed-text-v1-ablated

Feature Extraction
Transformers.js
ONNX
nomic_bert
custom_code
Model card Files
xet
Community
1

Add/update the quantized ONNX model files and README.md for Transformers.js v3

#1
by whitphx HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+16
-0
whitphx

Applied Quantizations

❌ Based on model.onnx with slimming

0%|          | 0/1 [00:00<?, ?it/s]
Processing /tmp/tmpnbc83gzs/model.onnx:   0%|          | 0/1 [00:00<?, ?it/s]

  0%|          | 0/5 [00:00<?, ?it/s]

 - Quantizing to int8:   0%|          | 0/5 [00:00<?, ?it/s]2025-07-22 08:09:26,928 root [INFO] - Quantization parameters for tensor:"/emb_ln/Add_1_output_0" not specified
2025-07-22 08:09:26,934 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.0/attn/MatMul]
2025-07-22 08:09:26,934 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.0/attn/MatMul_1]
2025-07-22 08:09:26,935 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:26,938 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/norm1/Add_1_output_0" not specified
2025-07-22 08:09:26,954 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:26,962 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/norm2/Add_1_output_0" not specified
2025-07-22 08:09:26,968 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.1/attn/MatMul]
2025-07-22 08:09:26,968 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.1/attn/MatMul_1]
2025-07-22 08:09:26,969 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:26,972 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/norm1/Add_1_output_0" not specified
2025-07-22 08:09:26,989 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:26,996 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/norm2/Add_1_output_0" not specified
2025-07-22 08:09:27,003 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.2/attn/MatMul]
2025-07-22 08:09:27,003 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.2/attn/MatMul_1]
2025-07-22 08:09:27,004 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:27,007 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/norm1/Add_1_output_0" not specified
2025-07-22 08:09:27,023 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:27,031 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/norm2/Add_1_output_0" not specified
2025-07-22 08:09:27,037 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.3/attn/MatMul]
2025-07-22 08:09:27,037 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.3/attn/MatMul_1]
2025-07-22 08:09:27,038 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:27,041 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/norm1/Add_1_output_0" not specified
2025-07-22 08:09:27,056 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:27,065 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/norm2/Add_1_output_0" not specified
2025-07-22 08:09:27,072 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.4/attn/MatMul]
2025-07-22 08:09:27,072 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.4/attn/MatMul_1]
2025-07-22 08:09:27,073 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:27,076 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/norm1/Add_1_output_0" not specified
2025-07-22 08:09:27,093 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:27,102 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/norm2/Add_1_output_0" not specified
2025-07-22 08:09:27,109 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.5/attn/MatMul]
2025-07-22 08:09:27,109 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.5/attn/MatMul_1]
2025-07-22 08:09:27,110 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:27,113 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/norm1/Add_1_output_0" not specified
2025-07-22 08:09:27,131 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:27,139 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/norm2/Add_1_output_0" not specified
2025-07-22 08:09:27,146 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.6/attn/MatMul]
2025-07-22 08:09:27,146 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.6/attn/MatMul_1]
2025-07-22 08:09:27,147 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:27,150 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/norm1/Add_1_output_0" not specified
2025-07-22 08:09:27,167 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:27,177 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/norm2/Add_1_output_0" not specified
2025-07-22 08:09:27,184 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.7/attn/MatMul]
2025-07-22 08:09:27,184 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.7/attn/MatMul_1]
2025-07-22 08:09:27,185 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:27,188 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/norm1/Add_1_output_0" not specified
2025-07-22 08:09:27,205 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:27,214 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/norm2/Add_1_output_0" not specified
2025-07-22 08:09:27,221 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.8/attn/MatMul]
2025-07-22 08:09:27,221 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.8/attn/MatMul_1]
2025-07-22 08:09:27,222 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:27,225 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/norm1/Add_1_output_0" not specified
2025-07-22 08:09:27,244 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:27,253 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/norm2/Add_1_output_0" not specified
2025-07-22 08:09:27,260 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.9/attn/MatMul]
2025-07-22 08:09:27,260 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.9/attn/MatMul_1]
2025-07-22 08:09:27,261 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:27,264 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/norm1/Add_1_output_0" not specified
2025-07-22 08:09:27,282 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:27,290 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/norm2/Add_1_output_0" not specified
2025-07-22 08:09:27,298 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.10/attn/MatMul]
2025-07-22 08:09:27,298 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.10/attn/MatMul_1]
2025-07-22 08:09:27,299 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:27,302 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/norm1/Add_1_output_0" not specified
2025-07-22 08:09:27,321 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:27,330 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/norm2/Add_1_output_0" not specified
2025-07-22 08:09:27,337 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.11/attn/MatMul]
2025-07-22 08:09:27,338 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.11/attn/MatMul_1]
2025-07-22 08:09:27,339 root [INFO] - Quantization parameters for tensor:"/encoder/layers.11/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:27,342 root [INFO] - Quantization parameters for tensor:"/encoder/layers.11/norm1/Add_1_output_0" not specified
2025-07-22 08:09:27,360 root [INFO] - Quantization parameters for tensor:"/encoder/layers.11/mlp/Mul_1_output_0" not specified


 - Quantizing to int8:  20%|██        | 1/5 [00:05<00:20,  5.18s/it]

 - Quantizing to uint8:  20%|██        | 1/5 [00:05<00:20,  5.18s/it]2025-07-22 08:09:31,532 root [INFO] - Quantization parameters for tensor:"/emb_ln/Add_1_output_0" not specified
2025-07-22 08:09:31,537 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.0/attn/MatMul]
2025-07-22 08:09:31,538 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.0/attn/MatMul_1]
2025-07-22 08:09:31,539 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:31,541 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/norm1/Add_1_output_0" not specified
2025-07-22 08:09:31,558 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:31,565 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/norm2/Add_1_output_0" not specified
2025-07-22 08:09:31,571 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.1/attn/MatMul]
2025-07-22 08:09:31,572 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.1/attn/MatMul_1]
2025-07-22 08:09:31,573 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:31,575 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/norm1/Add_1_output_0" not specified
2025-07-22 08:09:31,591 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:31,599 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/norm2/Add_1_output_0" not specified
2025-07-22 08:09:31,605 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.2/attn/MatMul]
2025-07-22 08:09:31,605 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.2/attn/MatMul_1]
2025-07-22 08:09:31,606 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:31,609 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/norm1/Add_1_output_0" not specified
2025-07-22 08:09:31,626 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:31,633 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/norm2/Add_1_output_0" not specified
2025-07-22 08:09:31,640 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.3/attn/MatMul]
2025-07-22 08:09:31,640 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.3/attn/MatMul_1]
2025-07-22 08:09:31,641 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:31,644 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/norm1/Add_1_output_0" not specified
2025-07-22 08:09:31,659 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:31,668 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/norm2/Add_1_output_0" not specified
2025-07-22 08:09:31,674 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.4/attn/MatMul]
2025-07-22 08:09:31,675 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.4/attn/MatMul_1]
2025-07-22 08:09:31,675 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:31,678 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/norm1/Add_1_output_0" not specified
2025-07-22 08:09:31,696 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:31,704 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/norm2/Add_1_output_0" not specified
2025-07-22 08:09:31,710 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.5/attn/MatMul]
2025-07-22 08:09:31,711 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.5/attn/MatMul_1]
2025-07-22 08:09:31,712 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:31,715 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/norm1/Add_1_output_0" not specified
2025-07-22 08:09:31,732 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:31,741 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/norm2/Add_1_output_0" not specified
2025-07-22 08:09:31,748 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.6/attn/MatMul]
2025-07-22 08:09:31,748 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.6/attn/MatMul_1]
2025-07-22 08:09:31,749 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:31,752 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/norm1/Add_1_output_0" not specified
2025-07-22 08:09:31,770 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:31,779 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/norm2/Add_1_output_0" not specified
2025-07-22 08:09:31,786 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.7/attn/MatMul]
2025-07-22 08:09:31,787 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.7/attn/MatMul_1]
2025-07-22 08:09:31,788 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:31,791 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/norm1/Add_1_output_0" not specified
2025-07-22 08:09:31,808 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:31,817 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/norm2/Add_1_output_0" not specified
2025-07-22 08:09:31,824 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.8/attn/MatMul]
2025-07-22 08:09:31,825 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.8/attn/MatMul_1]
2025-07-22 08:09:31,826 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:31,829 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/norm1/Add_1_output_0" not specified
2025-07-22 08:09:31,847 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:31,855 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/norm2/Add_1_output_0" not specified
2025-07-22 08:09:31,863 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.9/attn/MatMul]
2025-07-22 08:09:31,863 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.9/attn/MatMul_1]
2025-07-22 08:09:31,864 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:31,867 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/norm1/Add_1_output_0" not specified
2025-07-22 08:09:31,885 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:31,893 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/norm2/Add_1_output_0" not specified
2025-07-22 08:09:31,900 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.10/attn/MatMul]
2025-07-22 08:09:31,901 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.10/attn/MatMul_1]
2025-07-22 08:09:31,902 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:31,905 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/norm1/Add_1_output_0" not specified
2025-07-22 08:09:31,923 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:31,932 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/norm2/Add_1_output_0" not specified
2025-07-22 08:09:31,940 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.11/attn/MatMul]
2025-07-22 08:09:31,940 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.11/attn/MatMul_1]
2025-07-22 08:09:31,941 root [INFO] - Quantization parameters for tensor:"/encoder/layers.11/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:31,944 root [INFO] - Quantization parameters for tensor:"/encoder/layers.11/norm1/Add_1_output_0" not specified
2025-07-22 08:09:31,962 root [INFO] - Quantization parameters for tensor:"/encoder/layers.11/mlp/Mul_1_output_0" not specified


 - Quantizing to uint8:  40%|████      | 2/5 [00:09<00:14,  4.84s/it]

 - Quantizing to q4:  40%|████      | 2/5 [00:09<00:14,  4.84s/it]   2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/word_embeddings/Gather ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/token_type_embeddings/Gather ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/Add ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Cast ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/ReduceMean ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Sub ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Sub ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Mul ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Pow ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/ReduceMean_1 ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Add ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Sqrt ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Div ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Mul ...
2025-07-22 08:09:33,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Add_1 ...
2025-07-22 08:09:33,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_1 ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_1 ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Concat ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Reshape ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:33,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Cast ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Range ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Neg ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Einsum ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Cos ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Sin ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape ...
2025-07-22 08:09:33,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_3 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_4 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_5 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose_1 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose_2 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/MatMul ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/MatMul ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Div_1 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Add ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Softmax ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/MatMul_1 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/MatMul_1 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose_3 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_3 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_6 ...
2025-07-22 08:09:33,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_7 ...
2025-07-22 08:09:33,649 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_3 ...
2025-07-22 08:09:33,649 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_4 ...
2025-07-22 08:09:33,649 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Concat_1 ...
2025-07-22 08:09:33,649 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Reshape_1 ...
2025-07-22 08:09:33,649 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/out_proj/MatMul ...
2025-07-22 08:09:33,652 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/out_proj/MatMul ...
2025-07-22 08:09:33,652 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/Add ...
2025-07-22 08:09:33,652 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/ReduceMean ...
2025-07-22 08:09:33,652 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Sub ...
2025-07-22 08:09:33,652 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Pow ...
2025-07-22 08:09:33,652 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/ReduceMean_1 ...
2025-07-22 08:09:33,652 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Add ...
2025-07-22 08:09:33,652 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Sqrt ...
2025-07-22 08:09:33,652 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Div ...
2025-07-22 08:09:33,652 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Mul ...
2025-07-22 08:09:33,652 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Add_1 ...
2025-07-22 08:09:33,652 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/mlp/fc11/MatMul ...
2025-07-22 08:09:33,658 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/mlp/fc11/MatMul ...
2025-07-22 08:09:33,659 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/mlp/fc12/MatMul ...
2025-07-22 08:09:33,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/mlp/fc12/MatMul ...
2025-07-22 08:09:33,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/mlp/Sigmoid ...
2025-07-22 08:09:33,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/mlp/Mul ...
2025-07-22 08:09:33,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/mlp/Mul_1 ...
2025-07-22 08:09:33,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/mlp/fc2/MatMul ...
2025-07-22 08:09:33,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/mlp/fc2/MatMul ...
2025-07-22 08:09:33,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/Add_1 ...
2025-07-22 08:09:33,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/ReduceMean ...
2025-07-22 08:09:33,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Sub ...
2025-07-22 08:09:33,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Pow ...
2025-07-22 08:09:33,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/ReduceMean_1 ...
2025-07-22 08:09:33,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Add ...
2025-07-22 08:09:33,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Sqrt ...
2025-07-22 08:09:33,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Div ...
2025-07-22 08:09:33,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Mul ...
2025-07-22 08:09:33,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Add_1 ...
2025-07-22 08:09:33,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_1 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_1 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Concat ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Reshape ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Cast ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Range ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:33,677 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Neg ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Einsum ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Cos ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Sin ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:33,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_3 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_4 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_5 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose_1 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose_2 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/MatMul ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/MatMul ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Div_1 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Add ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Softmax ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/MatMul_1 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/MatMul_1 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose_3 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_3 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_6 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_7 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_3 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_4 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Concat_1 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Reshape_1 ...
2025-07-22 08:09:33,679 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/out_proj/MatMul ...
2025-07-22 08:09:33,682 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/out_proj/MatMul ...
2025-07-22 08:09:33,682 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/Add ...
2025-07-22 08:09:33,683 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/ReduceMean ...
2025-07-22 08:09:33,683 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Sub ...
2025-07-22 08:09:33,683 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Pow ...
2025-07-22 08:09:33,683 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/ReduceMean_1 ...
2025-07-22 08:09:33,683 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Add ...
2025-07-22 08:09:33,683 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Sqrt ...
2025-07-22 08:09:33,683 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Div ...
2025-07-22 08:09:33,683 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Mul ...
2025-07-22 08:09:33,683 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Add_1 ...
2025-07-22 08:09:33,683 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/mlp/fc11/MatMul ...
2025-07-22 08:09:33,689 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/mlp/fc11/MatMul ...
2025-07-22 08:09:33,689 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/mlp/fc12/MatMul ...
2025-07-22 08:09:33,695 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/mlp/fc12/MatMul ...
2025-07-22 08:09:33,695 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/mlp/Sigmoid ...
2025-07-22 08:09:33,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/mlp/Mul ...
2025-07-22 08:09:33,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/mlp/Mul_1 ...
2025-07-22 08:09:33,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/mlp/fc2/MatMul ...
2025-07-22 08:09:33,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/mlp/fc2/MatMul ...
2025-07-22 08:09:33,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/Add_1 ...
2025-07-22 08:09:33,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/ReduceMean ...
2025-07-22 08:09:33,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Sub ...
2025-07-22 08:09:33,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Pow ...
2025-07-22 08:09:33,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/ReduceMean_1 ...
2025-07-22 08:09:33,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Add ...
2025-07-22 08:09:33,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Sqrt ...
2025-07-22 08:09:33,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Div ...
2025-07-22 08:09:33,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Mul ...
2025-07-22 08:09:33,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Add_1 ...
2025-07-22 08:09:33,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_1 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_1 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Concat ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Reshape ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Cast ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:33,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Range ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Neg ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Einsum ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Cos ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Sin ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:33,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_3 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_4 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_5 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose_1 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose_2 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/MatMul ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/MatMul ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Div_1 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Add ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Softmax ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/MatMul_1 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/MatMul_1 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose_3 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_3 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_6 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_7 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_3 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_4 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Concat_1 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Reshape_1 ...
2025-07-22 08:09:33,710 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/out_proj/MatMul ...
2025-07-22 08:09:33,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/out_proj/MatMul ...
2025-07-22 08:09:33,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/Add ...
2025-07-22 08:09:33,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/ReduceMean ...
2025-07-22 08:09:33,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Sub ...
2025-07-22 08:09:33,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Pow ...
2025-07-22 08:09:33,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/ReduceMean_1 ...
2025-07-22 08:09:33,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Add ...
2025-07-22 08:09:33,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Sqrt ...
2025-07-22 08:09:33,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Div ...
2025-07-22 08:09:33,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Mul ...
2025-07-22 08:09:33,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Add_1 ...
2025-07-22 08:09:33,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/mlp/fc11/MatMul ...
2025-07-22 08:09:33,721 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/mlp/fc11/MatMul ...
2025-07-22 08:09:33,721 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/mlp/fc12/MatMul ...
2025-07-22 08:09:33,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/mlp/fc12/MatMul ...
2025-07-22 08:09:33,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/mlp/Sigmoid ...
2025-07-22 08:09:33,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/mlp/Mul ...
2025-07-22 08:09:33,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/mlp/Mul_1 ...
2025-07-22 08:09:33,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/mlp/fc2/MatMul ...
2025-07-22 08:09:33,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/mlp/fc2/MatMul ...
2025-07-22 08:09:33,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/Add_1 ...
2025-07-22 08:09:33,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/ReduceMean ...
2025-07-22 08:09:33,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Sub ...
2025-07-22 08:09:33,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Pow ...
2025-07-22 08:09:33,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/ReduceMean_1 ...
2025-07-22 08:09:33,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Add ...
2025-07-22 08:09:33,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Sqrt ...
2025-07-22 08:09:33,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Div ...
2025-07-22 08:09:33,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Mul ...
2025-07-22 08:09:33,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Add_1 ...
2025-07-22 08:09:33,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_1 ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_1 ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Concat ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Reshape ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:33,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Cast ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Range ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Neg ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Einsum ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Cos ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Sin ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:33,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_3 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_4 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_5 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose_1 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose_2 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/MatMul ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/MatMul ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Div_1 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Add ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Softmax ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/MatMul_1 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/MatMul_1 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose_3 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_3 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_6 ...
2025-07-22 08:09:33,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_7 ...
2025-07-22 08:09:33,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_3 ...
2025-07-22 08:09:33,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_4 ...
2025-07-22 08:09:33,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Concat_1 ...
2025-07-22 08:09:33,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Reshape_1 ...
2025-07-22 08:09:33,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/out_proj/MatMul ...
2025-07-22 08:09:33,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/out_proj/MatMul ...
2025-07-22 08:09:33,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/Add ...
2025-07-22 08:09:33,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/ReduceMean ...
2025-07-22 08:09:33,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Sub ...
2025-07-22 08:09:33,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Pow ...
2025-07-22 08:09:33,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/ReduceMean_1 ...
2025-07-22 08:09:33,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Add ...
2025-07-22 08:09:33,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Sqrt ...
2025-07-22 08:09:33,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Div ...
2025-07-22 08:09:33,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Mul ...
2025-07-22 08:09:33,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Add_1 ...
2025-07-22 08:09:33,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/mlp/fc11/MatMul ...
2025-07-22 08:09:33,754 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/mlp/fc11/MatMul ...
2025-07-22 08:09:33,755 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/mlp/fc12/MatMul ...
2025-07-22 08:09:33,761 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/mlp/fc12/MatMul ...
2025-07-22 08:09:33,761 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/mlp/Sigmoid ...
2025-07-22 08:09:33,761 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/mlp/Mul ...
2025-07-22 08:09:33,761 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/mlp/Mul_1 ...
2025-07-22 08:09:33,761 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/mlp/fc2/MatMul ...
2025-07-22 08:09:33,767 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/mlp/fc2/MatMul ...
2025-07-22 08:09:33,767 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/Add_1 ...
2025-07-22 08:09:33,767 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/ReduceMean ...
2025-07-22 08:09:33,767 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Sub ...
2025-07-22 08:09:33,768 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Pow ...
2025-07-22 08:09:33,768 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/ReduceMean_1 ...
2025-07-22 08:09:33,768 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Add ...
2025-07-22 08:09:33,768 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Sqrt ...
2025-07-22 08:09:33,768 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Div ...
2025-07-22 08:09:33,768 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Mul ...
2025-07-22 08:09:33,768 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Add_1 ...
2025-07-22 08:09:33,768 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape ...
2025-07-22 08:09:33,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather ...
2025-07-22 08:09:33,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_1 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_1 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Concat ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Reshape ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Cast ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Range ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Neg ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Einsum ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Cos ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Sin ...
2025-07-22 08:09:33,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_3 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_4 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_5 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose_1 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose_2 ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/MatMul ...
2025-07-22 08:09:33,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/MatMul ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Div_1 ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Add ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Softmax ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/MatMul_1 ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/MatMul_1 ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose_3 ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_3 ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_6 ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_7 ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_3 ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_4 ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Concat_1 ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Reshape_1 ...
2025-07-22 08:09:33,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/out_proj/MatMul ...
2025-07-22 08:09:33,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/out_proj/MatMul ...
2025-07-22 08:09:33,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/Add ...
2025-07-22 08:09:33,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/ReduceMean ...
2025-07-22 08:09:33,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Sub ...
2025-07-22 08:09:33,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Pow ...
2025-07-22 08:09:33,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/ReduceMean_1 ...
2025-07-22 08:09:33,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Add ...
2025-07-22 08:09:33,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Sqrt ...
2025-07-22 08:09:33,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Div ...
2025-07-22 08:09:33,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Mul ...
2025-07-22 08:09:33,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Add_1 ...
2025-07-22 08:09:33,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/mlp/fc11/MatMul ...
2025-07-22 08:09:33,786 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/mlp/fc11/MatMul ...
2025-07-22 08:09:33,786 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/mlp/fc12/MatMul ...
2025-07-22 08:09:33,792 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/mlp/fc12/MatMul ...
2025-07-22 08:09:33,792 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/mlp/Sigmoid ...
2025-07-22 08:09:33,792 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/mlp/Mul ...
2025-07-22 08:09:33,792 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/mlp/Mul_1 ...
2025-07-22 08:09:33,792 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/mlp/fc2/MatMul ...
2025-07-22 08:09:33,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/mlp/fc2/MatMul ...
2025-07-22 08:09:33,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/Add_1 ...
2025-07-22 08:09:33,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/ReduceMean ...
2025-07-22 08:09:33,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Sub ...
2025-07-22 08:09:33,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Pow ...
2025-07-22 08:09:33,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/ReduceMean_1 ...
2025-07-22 08:09:33,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Add ...
2025-07-22 08:09:33,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Sqrt ...
2025-07-22 08:09:33,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Div ...
2025-07-22 08:09:33,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Mul ...
2025-07-22 08:09:33,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Add_1 ...
2025-07-22 08:09:33,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,804 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_1 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_1 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Concat ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Reshape ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Cast ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Range ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Neg ...
2025-07-22 08:09:33,805 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Einsum ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Cos ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Sin ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_3 ...
2025-07-22 08:09:33,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_4 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_5 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose_1 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose_2 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/MatMul ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/MatMul ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Div_1 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Add ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Softmax ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/MatMul_1 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/MatMul_1 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose_3 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_3 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_6 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_7 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_3 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_4 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Concat_1 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Reshape_1 ...
2025-07-22 08:09:33,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/out_proj/MatMul ...
2025-07-22 08:09:33,811 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/out_proj/MatMul ...
2025-07-22 08:09:33,811 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/Add ...
2025-07-22 08:09:33,811 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/ReduceMean ...
2025-07-22 08:09:33,811 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Sub ...
2025-07-22 08:09:33,811 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Pow ...
2025-07-22 08:09:33,811 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/ReduceMean_1 ...
2025-07-22 08:09:33,811 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Add ...
2025-07-22 08:09:33,811 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Sqrt ...
2025-07-22 08:09:33,811 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Div ...
2025-07-22 08:09:33,811 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Mul ...
2025-07-22 08:09:33,811 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Add_1 ...
2025-07-22 08:09:33,811 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/mlp/fc11/MatMul ...
2025-07-22 08:09:33,817 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/mlp/fc11/MatMul ...
2025-07-22 08:09:33,817 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/mlp/fc12/MatMul ...
2025-07-22 08:09:33,823 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/mlp/fc12/MatMul ...
2025-07-22 08:09:33,824 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/mlp/Sigmoid ...
2025-07-22 08:09:33,824 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/mlp/Mul ...
2025-07-22 08:09:33,824 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/mlp/Mul_1 ...
2025-07-22 08:09:33,824 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/mlp/fc2/MatMul ...
2025-07-22 08:09:33,829 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/mlp/fc2/MatMul ...
2025-07-22 08:09:33,830 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/Add_1 ...
2025-07-22 08:09:33,830 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/ReduceMean ...
2025-07-22 08:09:33,830 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Sub ...
2025-07-22 08:09:33,830 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Pow ...
2025-07-22 08:09:33,830 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/ReduceMean_1 ...
2025-07-22 08:09:33,830 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Add ...
2025-07-22 08:09:33,830 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Sqrt ...
2025-07-22 08:09:33,830 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Div ...
2025-07-22 08:09:33,830 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Mul ...
2025-07-22 08:09:33,830 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Add_1 ...
2025-07-22 08:09:33,830 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,835 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,835 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape ...
2025-07-22 08:09:33,835 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather ...
2025-07-22 08:09:33,835 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_1 ...
2025-07-22 08:09:33,835 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze ...
2025-07-22 08:09:33,835 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_1 ...
2025-07-22 08:09:33,835 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Concat ...
2025-07-22 08:09:33,835 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Reshape ...
2025-07-22 08:09:33,835 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape ...
2025-07-22 08:09:33,835 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Cast ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Range ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Neg ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Einsum ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Cos ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Sin ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:33,836 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_3 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_4 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_5 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose_1 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose_2 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/MatMul ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/MatMul ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Div_1 ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Add ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Softmax ...
2025-07-22 08:09:33,837 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/MatMul_1 ...
2025-07-22 08:09:33,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/MatMul_1 ...
2025-07-22 08:09:33,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose_3 ...
2025-07-22 08:09:33,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_3 ...
2025-07-22 08:09:33,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_6 ...
2025-07-22 08:09:33,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_7 ...
2025-07-22 08:09:33,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_3 ...
2025-07-22 08:09:33,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_4 ...
2025-07-22 08:09:33,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Concat_1 ...
2025-07-22 08:09:33,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Reshape_1 ...
2025-07-22 08:09:33,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/out_proj/MatMul ...
2025-07-22 08:09:33,841 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/out_proj/MatMul ...
2025-07-22 08:09:33,842 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/Add ...
2025-07-22 08:09:33,842 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/ReduceMean ...
2025-07-22 08:09:33,842 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Sub ...
2025-07-22 08:09:33,842 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Pow ...
2025-07-22 08:09:33,842 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/ReduceMean_1 ...
2025-07-22 08:09:33,842 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Add ...
2025-07-22 08:09:33,842 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Sqrt ...
2025-07-22 08:09:33,842 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Div ...
2025-07-22 08:09:33,842 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Mul ...
2025-07-22 08:09:33,842 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Add_1 ...
2025-07-22 08:09:33,842 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/mlp/fc11/MatMul ...
2025-07-22 08:09:33,849 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/mlp/fc11/MatMul ...
2025-07-22 08:09:33,849 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/mlp/fc12/MatMul ...
2025-07-22 08:09:33,855 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/mlp/fc12/MatMul ...
2025-07-22 08:09:33,855 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/mlp/Sigmoid ...
2025-07-22 08:09:33,855 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/mlp/Mul ...
2025-07-22 08:09:33,855 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/mlp/Mul_1 ...
2025-07-22 08:09:33,855 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/mlp/fc2/MatMul ...
2025-07-22 08:09:33,861 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/mlp/fc2/MatMul ...
2025-07-22 08:09:33,861 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/Add_1 ...
2025-07-22 08:09:33,861 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/ReduceMean ...
2025-07-22 08:09:33,861 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Sub ...
2025-07-22 08:09:33,861 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Pow ...
2025-07-22 08:09:33,861 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/ReduceMean_1 ...
2025-07-22 08:09:33,861 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Add ...
2025-07-22 08:09:33,861 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Sqrt ...
2025-07-22 08:09:33,862 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Div ...
2025-07-22 08:09:33,862 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Mul ...
2025-07-22 08:09:33,862 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Add_1 ...
2025-07-22 08:09:33,862 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_1 ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_1 ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Concat ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Reshape ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather ...
2025-07-22 08:09:33,867 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Cast ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Range ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Neg ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Einsum ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Cos ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Sin ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:33,868 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_3 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_4 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_5 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose_1 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose_2 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/MatMul ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/MatMul ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Div_1 ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Add ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Softmax ...
2025-07-22 08:09:33,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/MatMul_1 ...
2025-07-22 08:09:33,870 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,870 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/MatMul_1 ...
2025-07-22 08:09:33,870 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose_3 ...
2025-07-22 08:09:33,870 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_3 ...
2025-07-22 08:09:33,870 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_6 ...
2025-07-22 08:09:33,870 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_7 ...
2025-07-22 08:09:33,870 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_3 ...
2025-07-22 08:09:33,870 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_4 ...
2025-07-22 08:09:33,870 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Concat_1 ...
2025-07-22 08:09:33,870 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Reshape_1 ...
2025-07-22 08:09:33,870 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/out_proj/MatMul ...
2025-07-22 08:09:33,873 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/out_proj/MatMul ...
2025-07-22 08:09:33,873 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/Add ...
2025-07-22 08:09:33,873 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/ReduceMean ...
2025-07-22 08:09:33,873 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Sub ...
2025-07-22 08:09:33,873 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Pow ...
2025-07-22 08:09:33,873 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/ReduceMean_1 ...
2025-07-22 08:09:33,873 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Add ...
2025-07-22 08:09:33,873 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Sqrt ...
2025-07-22 08:09:33,873 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Div ...
2025-07-22 08:09:33,873 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Mul ...
2025-07-22 08:09:33,873 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Add_1 ...
2025-07-22 08:09:33,873 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/mlp/fc11/MatMul ...
2025-07-22 08:09:33,879 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/mlp/fc11/MatMul ...
2025-07-22 08:09:33,879 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/mlp/fc12/MatMul ...
2025-07-22 08:09:33,886 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/mlp/fc12/MatMul ...
2025-07-22 08:09:33,886 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/mlp/Sigmoid ...
2025-07-22 08:09:33,886 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/mlp/Mul ...
2025-07-22 08:09:33,886 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/mlp/Mul_1 ...
2025-07-22 08:09:33,886 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/mlp/fc2/MatMul ...
2025-07-22 08:09:33,892 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/mlp/fc2/MatMul ...
2025-07-22 08:09:33,892 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/Add_1 ...
2025-07-22 08:09:33,892 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/ReduceMean ...
2025-07-22 08:09:33,892 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Sub ...
2025-07-22 08:09:33,892 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Pow ...
2025-07-22 08:09:33,892 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/ReduceMean_1 ...
2025-07-22 08:09:33,893 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Add ...
2025-07-22 08:09:33,893 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Sqrt ...
2025-07-22 08:09:33,893 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Div ...
2025-07-22 08:09:33,893 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Mul ...
2025-07-22 08:09:33,893 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Add_1 ...
2025-07-22 08:09:33,893 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_1 ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_1 ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Concat ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Reshape ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:33,898 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Cast ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Range ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Neg ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Einsum ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Cos ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Sin ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape ...
2025-07-22 08:09:33,899 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_3 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_4 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_5 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose_1 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose_2 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/MatMul ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/MatMul ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Div_1 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Add ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Softmax ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/MatMul_1 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/MatMul_1 ...
2025-07-22 08:09:33,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose_3 ...
2025-07-22 08:09:33,901 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_3 ...
2025-07-22 08:09:33,901 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_6 ...
2025-07-22 08:09:33,901 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_7 ...
2025-07-22 08:09:33,901 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_3 ...
2025-07-22 08:09:33,901 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_4 ...
2025-07-22 08:09:33,901 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Concat_1 ...
2025-07-22 08:09:33,901 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Reshape_1 ...
2025-07-22 08:09:33,901 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/out_proj/MatMul ...
2025-07-22 08:09:33,904 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/out_proj/MatMul ...
2025-07-22 08:09:33,904 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/Add ...
2025-07-22 08:09:33,904 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/ReduceMean ...
2025-07-22 08:09:33,904 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Sub ...
2025-07-22 08:09:33,904 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Pow ...
2025-07-22 08:09:33,905 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/ReduceMean_1 ...
2025-07-22 08:09:33,905 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Add ...
2025-07-22 08:09:33,905 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Sqrt ...
2025-07-22 08:09:33,905 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Div ...
2025-07-22 08:09:33,905 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Mul ...
2025-07-22 08:09:33,905 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Add_1 ...
2025-07-22 08:09:33,905 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/mlp/fc11/MatMul ...
2025-07-22 08:09:33,911 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/mlp/fc11/MatMul ...
2025-07-22 08:09:33,911 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/mlp/fc12/MatMul ...
2025-07-22 08:09:33,918 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/mlp/fc12/MatMul ...
2025-07-22 08:09:33,918 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/mlp/Sigmoid ...
2025-07-22 08:09:33,918 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/mlp/Mul ...
2025-07-22 08:09:33,918 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/mlp/Mul_1 ...
2025-07-22 08:09:33,918 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/mlp/fc2/MatMul ...
2025-07-22 08:09:33,924 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/mlp/fc2/MatMul ...
2025-07-22 08:09:33,924 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/Add_1 ...
2025-07-22 08:09:33,924 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/ReduceMean ...
2025-07-22 08:09:33,924 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Sub ...
2025-07-22 08:09:33,924 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Pow ...
2025-07-22 08:09:33,924 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/ReduceMean_1 ...
2025-07-22 08:09:33,924 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Add ...
2025-07-22 08:09:33,924 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Sqrt ...
2025-07-22 08:09:33,924 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Div ...
2025-07-22 08:09:33,924 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Mul ...
2025-07-22 08:09:33,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Add_1 ...
2025-07-22 08:09:33,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_1 ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_1 ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Concat ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Reshape ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:33,930 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Cast ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Range ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Neg ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Einsum ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Cos ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Sin ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:33,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_3 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_4 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_5 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose_1 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose_2 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/MatMul ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/MatMul ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Div_1 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Add ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Softmax ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/MatMul_1 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/MatMul_1 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose_3 ...
2025-07-22 08:09:33,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_3 ...
2025-07-22 08:09:33,933 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_6 ...
2025-07-22 08:09:33,933 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_7 ...
2025-07-22 08:09:33,933 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_3 ...
2025-07-22 08:09:33,933 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_4 ...
2025-07-22 08:09:33,933 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Concat_1 ...
2025-07-22 08:09:33,933 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Reshape_1 ...
2025-07-22 08:09:33,933 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/out_proj/MatMul ...
2025-07-22 08:09:33,936 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/out_proj/MatMul ...
2025-07-22 08:09:33,936 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/Add ...
2025-07-22 08:09:33,936 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/ReduceMean ...
2025-07-22 08:09:33,936 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Sub ...
2025-07-22 08:09:33,936 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Pow ...
2025-07-22 08:09:33,936 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/ReduceMean_1 ...
2025-07-22 08:09:33,936 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Add ...
2025-07-22 08:09:33,936 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Sqrt ...
2025-07-22 08:09:33,936 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Div ...
2025-07-22 08:09:33,936 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Mul ...
2025-07-22 08:09:33,936 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Add_1 ...
2025-07-22 08:09:33,936 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/mlp/fc11/MatMul ...
2025-07-22 08:09:33,943 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/mlp/fc11/MatMul ...
2025-07-22 08:09:33,943 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/mlp/fc12/MatMul ...
2025-07-22 08:09:33,949 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/mlp/fc12/MatMul ...
2025-07-22 08:09:33,949 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/mlp/Sigmoid ...
2025-07-22 08:09:33,949 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/mlp/Mul ...
2025-07-22 08:09:33,949 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/mlp/Mul_1 ...
2025-07-22 08:09:33,949 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/mlp/fc2/MatMul ...
2025-07-22 08:09:33,955 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/mlp/fc2/MatMul ...
2025-07-22 08:09:33,955 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/Add_1 ...
2025-07-22 08:09:33,955 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/ReduceMean ...
2025-07-22 08:09:33,955 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Sub ...
2025-07-22 08:09:33,955 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Pow ...
2025-07-22 08:09:33,955 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/ReduceMean_1 ...
2025-07-22 08:09:33,955 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Add ...
2025-07-22 08:09:33,955 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Sqrt ...
2025-07-22 08:09:33,955 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Div ...
2025-07-22 08:09:33,955 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Mul ...
2025-07-22 08:09:33,955 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Add_1 ...
2025-07-22 08:09:33,956 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_1 ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_1 ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Concat ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Reshape ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:33,961 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Cast ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Range ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Neg ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Einsum ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Cos ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Sin ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:33,962 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_3 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_4 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_5 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose_1 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose_2 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/MatMul ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/MatMul ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Div_1 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Add ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Softmax ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/MatMul_1 ...
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/MatMul_1 ...
2025-07-22 08:09:33,964 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose_3 ...
2025-07-22 08:09:33,964 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_3 ...
2025-07-22 08:09:33,964 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_6 ...
2025-07-22 08:09:33,964 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_7 ...
2025-07-22 08:09:33,964 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_3 ...
2025-07-22 08:09:33,964 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_4 ...
2025-07-22 08:09:33,964 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Concat_1 ...
2025-07-22 08:09:33,964 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Reshape_1 ...
2025-07-22 08:09:33,964 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/out_proj/MatMul ...
2025-07-22 08:09:33,967 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/out_proj/MatMul ...
2025-07-22 08:09:33,967 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/Add ...
2025-07-22 08:09:33,967 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/ReduceMean ...
2025-07-22 08:09:33,967 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Sub ...
2025-07-22 08:09:33,967 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Pow ...
2025-07-22 08:09:33,967 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/ReduceMean_1 ...
2025-07-22 08:09:33,967 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Add ...
2025-07-22 08:09:33,967 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Sqrt ...
2025-07-22 08:09:33,967 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Div ...
2025-07-22 08:09:33,967 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Mul ...
2025-07-22 08:09:33,967 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Add_1 ...
2025-07-22 08:09:33,967 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/mlp/fc11/MatMul ...
2025-07-22 08:09:33,974 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/mlp/fc11/MatMul ...
2025-07-22 08:09:33,974 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/mlp/fc12/MatMul ...
2025-07-22 08:09:33,980 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/mlp/fc12/MatMul ...
2025-07-22 08:09:33,980 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/mlp/Sigmoid ...
2025-07-22 08:09:33,980 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/mlp/Mul ...
2025-07-22 08:09:33,980 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/mlp/Mul_1 ...
2025-07-22 08:09:33,980 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/mlp/fc2/MatMul ...
2025-07-22 08:09:33,986 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/mlp/fc2/MatMul ...
2025-07-22 08:09:33,986 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/Add_1 ...
2025-07-22 08:09:33,986 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/ReduceMean ...
2025-07-22 08:09:33,986 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Sub ...
2025-07-22 08:09:33,987 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Pow ...
2025-07-22 08:09:33,987 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/ReduceMean_1 ...
2025-07-22 08:09:33,987 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Add ...
2025-07-22 08:09:33,987 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Sqrt ...
2025-07-22 08:09:33,987 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Div ...
2025-07-22 08:09:33,987 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Mul ...
2025-07-22 08:09:33,987 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Add_1 ...
2025-07-22 08:09:33,987 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/Wqkv/MatMul ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_1 ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_1 ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Concat ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Reshape ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:33,992 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Cast ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Range ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Neg ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Einsum ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Cos ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Sin ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:33,993 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_3 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_4 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_5 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose_1 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose_2 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/MatMul ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/MatMul ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Div_1 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Add ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Softmax ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/MatMul_1 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/MatMul_1 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose_3 ...
2025-07-22 08:09:33,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_3 ...
2025-07-22 08:09:33,995 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_6 ...
2025-07-22 08:09:33,995 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_7 ...
2025-07-22 08:09:33,995 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_3 ...
2025-07-22 08:09:33,995 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_4 ...
2025-07-22 08:09:33,995 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Concat_1 ...
2025-07-22 08:09:33,995 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Reshape_1 ...
2025-07-22 08:09:33,995 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/out_proj/MatMul ...
2025-07-22 08:09:33,998 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/out_proj/MatMul ...
2025-07-22 08:09:33,998 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/Add ...
2025-07-22 08:09:33,998 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/ReduceMean ...
2025-07-22 08:09:33,998 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Sub ...
2025-07-22 08:09:33,998 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Pow ...
2025-07-22 08:09:33,998 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/ReduceMean_1 ...
2025-07-22 08:09:33,998 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Add ...
2025-07-22 08:09:33,998 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Sqrt ...
2025-07-22 08:09:33,998 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Div ...
2025-07-22 08:09:33,998 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Mul ...
2025-07-22 08:09:33,998 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Add_1 ...
2025-07-22 08:09:33,998 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/mlp/fc11/MatMul ...
2025-07-22 08:09:34,005 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/mlp/fc11/MatMul ...
2025-07-22 08:09:34,005 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/mlp/fc12/MatMul ...
2025-07-22 08:09:34,011 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/mlp/fc12/MatMul ...
2025-07-22 08:09:34,011 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/mlp/Sigmoid ...
2025-07-22 08:09:34,011 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/mlp/Mul ...
2025-07-22 08:09:34,011 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/mlp/Mul_1 ...
2025-07-22 08:09:34,011 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/mlp/fc2/MatMul ...
2025-07-22 08:09:34,017 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/mlp/fc2/MatMul ...
2025-07-22 08:09:34,017 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/Add_1 ...
2025-07-22 08:09:34,017 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/ReduceMean ...
2025-07-22 08:09:34,017 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Sub ...
2025-07-22 08:09:34,017 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Pow ...
2025-07-22 08:09:34,017 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/ReduceMean_1 ...
2025-07-22 08:09:34,018 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Add ...
2025-07-22 08:09:34,018 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Sqrt ...
2025-07-22 08:09:34,018 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Div ...
2025-07-22 08:09:34,018 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Mul ...
2025-07-22 08:09:34,018 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Add_1 ...


 - Quantizing to q4:  60%|██████    | 3/5 [00:10<00:06,  3.01s/it]

 - Quantizing to q4f16:  60%|██████    | 3/5 [00:10<00:06,  3.01s/it]2025-07-22 08:09:34,763 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/word_embeddings/Gather ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/token_type_embeddings/Gather ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/Add ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Cast ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/ReduceMean ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Sub ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Sub ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Mul ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Pow ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/ReduceMean_1 ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Add ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Sqrt ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Div ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Mul ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Add_1 ...
2025-07-22 08:09:34,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_1 ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_1 ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Concat ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Reshape ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:34,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Cast ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Range ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Neg ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Einsum ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Cos ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Sin ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:34,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_3 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_4 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_5 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose_1 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose_2 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/MatMul ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/MatMul ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Div_1 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Add ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Softmax ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/MatMul_1 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/MatMul_1 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose_3 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_3 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_6 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_7 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_3 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_4 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Concat_1 ...
2025-07-22 08:09:34,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Reshape_1 ...
2025-07-22 08:09:34,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/out_proj/MatMul ...
2025-07-22 08:09:34,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/out_proj/MatMul ...
2025-07-22 08:09:34,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/Add ...
2025-07-22 08:09:34,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/ReduceMean ...
2025-07-22 08:09:34,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Sub ...
2025-07-22 08:09:34,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Pow ...
2025-07-22 08:09:34,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/ReduceMean_1 ...
2025-07-22 08:09:34,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Add ...
2025-07-22 08:09:34,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Sqrt ...
2025-07-22 08:09:34,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Div ...
2025-07-22 08:09:34,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Mul ...
2025-07-22 08:09:34,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Add_1 ...
2025-07-22 08:09:34,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/mlp/fc11/MatMul ...
2025-07-22 08:09:34,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/mlp/fc11/MatMul ...
2025-07-22 08:09:34,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/mlp/fc12/MatMul ...
2025-07-22 08:09:34,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/mlp/fc12/MatMul ...
2025-07-22 08:09:34,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/mlp/Sigmoid ...
2025-07-22 08:09:34,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/mlp/Mul ...
2025-07-22 08:09:34,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/mlp/Mul_1 ...
2025-07-22 08:09:34,788 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/mlp/fc2/MatMul ...
2025-07-22 08:09:34,793 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/mlp/fc2/MatMul ...
2025-07-22 08:09:34,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/Add_1 ...
2025-07-22 08:09:34,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/ReduceMean ...
2025-07-22 08:09:34,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Sub ...
2025-07-22 08:09:34,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Pow ...
2025-07-22 08:09:34,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/ReduceMean_1 ...
2025-07-22 08:09:34,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Add ...
2025-07-22 08:09:34,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Sqrt ...
2025-07-22 08:09:34,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Div ...
2025-07-22 08:09:34,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Mul ...
2025-07-22 08:09:34,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Add_1 ...
2025-07-22 08:09:34,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape ...
2025-07-22 08:09:34,799 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_1 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_1 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Concat ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Reshape ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Cast ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Range ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Neg ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Einsum ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Cos ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Sin ...
2025-07-22 08:09:34,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_3 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_4 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_5 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose_1 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose_2 ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/MatMul ...
2025-07-22 08:09:34,801 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/MatMul ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Div_1 ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Add ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Softmax ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/MatMul_1 ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/MatMul_1 ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose_3 ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_3 ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_6 ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_7 ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_3 ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_4 ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Concat_1 ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Reshape_1 ...
2025-07-22 08:09:34,802 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/out_proj/MatMul ...
2025-07-22 08:09:34,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/out_proj/MatMul ...
2025-07-22 08:09:34,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/Add ...
2025-07-22 08:09:34,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/ReduceMean ...
2025-07-22 08:09:34,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Sub ...
2025-07-22 08:09:34,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Pow ...
2025-07-22 08:09:34,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/ReduceMean_1 ...
2025-07-22 08:09:34,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Add ...
2025-07-22 08:09:34,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Sqrt ...
2025-07-22 08:09:34,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Div ...
2025-07-22 08:09:34,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Mul ...
2025-07-22 08:09:34,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Add_1 ...
2025-07-22 08:09:34,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/mlp/fc11/MatMul ...
2025-07-22 08:09:34,812 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/mlp/fc11/MatMul ...
2025-07-22 08:09:34,812 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/mlp/fc12/MatMul ...
2025-07-22 08:09:34,819 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/mlp/fc12/MatMul ...
2025-07-22 08:09:34,819 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/mlp/Sigmoid ...
2025-07-22 08:09:34,819 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/mlp/Mul ...
2025-07-22 08:09:34,819 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/mlp/Mul_1 ...
2025-07-22 08:09:34,819 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/mlp/fc2/MatMul ...
2025-07-22 08:09:34,825 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/mlp/fc2/MatMul ...
2025-07-22 08:09:34,825 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/Add_1 ...
2025-07-22 08:09:34,825 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/ReduceMean ...
2025-07-22 08:09:34,825 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Sub ...
2025-07-22 08:09:34,825 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Pow ...
2025-07-22 08:09:34,825 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/ReduceMean_1 ...
2025-07-22 08:09:34,825 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Add ...
2025-07-22 08:09:34,825 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Sqrt ...
2025-07-22 08:09:34,826 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Div ...
2025-07-22 08:09:34,826 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Mul ...
2025-07-22 08:09:34,826 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Add_1 ...
2025-07-22 08:09:34,826 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,831 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,831 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape ...
2025-07-22 08:09:34,831 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather ...
2025-07-22 08:09:34,831 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_1 ...
2025-07-22 08:09:34,831 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze ...
2025-07-22 08:09:34,831 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_1 ...
2025-07-22 08:09:34,831 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Concat ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Reshape ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Cast ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Range ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Neg ...
2025-07-22 08:09:34,832 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Einsum ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Cos ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Sin ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:34,833 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_3 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_4 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_5 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose_1 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose_2 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/MatMul ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/MatMul ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Div_1 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Add ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Softmax ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/MatMul_1 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/MatMul_1 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose_3 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_3 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_6 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_7 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_3 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_4 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Concat_1 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Reshape_1 ...
2025-07-22 08:09:34,834 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/out_proj/MatMul ...
2025-07-22 08:09:34,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/out_proj/MatMul ...
2025-07-22 08:09:34,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/Add ...
2025-07-22 08:09:34,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/ReduceMean ...
2025-07-22 08:09:34,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Sub ...
2025-07-22 08:09:34,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Pow ...
2025-07-22 08:09:34,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/ReduceMean_1 ...
2025-07-22 08:09:34,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Add ...
2025-07-22 08:09:34,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Sqrt ...
2025-07-22 08:09:34,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Div ...
2025-07-22 08:09:34,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Mul ...
2025-07-22 08:09:34,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Add_1 ...
2025-07-22 08:09:34,838 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/mlp/fc11/MatMul ...
2025-07-22 08:09:34,844 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/mlp/fc11/MatMul ...
2025-07-22 08:09:34,844 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/mlp/fc12/MatMul ...
2025-07-22 08:09:34,851 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/mlp/fc12/MatMul ...
2025-07-22 08:09:34,851 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/mlp/Sigmoid ...
2025-07-22 08:09:34,851 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/mlp/Mul ...
2025-07-22 08:09:34,851 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/mlp/Mul_1 ...
2025-07-22 08:09:34,851 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/mlp/fc2/MatMul ...
2025-07-22 08:09:34,857 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/mlp/fc2/MatMul ...
2025-07-22 08:09:34,857 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/Add_1 ...
2025-07-22 08:09:34,857 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/ReduceMean ...
2025-07-22 08:09:34,857 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Sub ...
2025-07-22 08:09:34,857 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Pow ...
2025-07-22 08:09:34,857 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/ReduceMean_1 ...
2025-07-22 08:09:34,857 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Add ...
2025-07-22 08:09:34,857 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Sqrt ...
2025-07-22 08:09:34,857 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Div ...
2025-07-22 08:09:34,857 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Mul ...
2025-07-22 08:09:34,857 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Add_1 ...
2025-07-22 08:09:34,857 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_1 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_1 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Concat ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Reshape ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Cast ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:34,863 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Range ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Neg ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Einsum ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Cos ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Sin ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:34,864 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_3 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_4 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_5 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose_1 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose_2 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/MatMul ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/MatMul ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Div_1 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Add ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Softmax ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/MatMul_1 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/MatMul_1 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose_3 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_3 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_6 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_7 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_3 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_4 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Concat_1 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Reshape_1 ...
2025-07-22 08:09:34,865 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/out_proj/MatMul ...
2025-07-22 08:09:34,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/out_proj/MatMul ...
2025-07-22 08:09:34,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/Add ...
2025-07-22 08:09:34,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/ReduceMean ...
2025-07-22 08:09:34,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Sub ...
2025-07-22 08:09:34,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Pow ...
2025-07-22 08:09:34,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/ReduceMean_1 ...
2025-07-22 08:09:34,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Add ...
2025-07-22 08:09:34,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Sqrt ...
2025-07-22 08:09:34,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Div ...
2025-07-22 08:09:34,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Mul ...
2025-07-22 08:09:34,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Add_1 ...
2025-07-22 08:09:34,869 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/mlp/fc11/MatMul ...
2025-07-22 08:09:34,875 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/mlp/fc11/MatMul ...
2025-07-22 08:09:34,875 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/mlp/fc12/MatMul ...
2025-07-22 08:09:34,882 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/mlp/fc12/MatMul ...
2025-07-22 08:09:34,882 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/mlp/Sigmoid ...
2025-07-22 08:09:34,882 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/mlp/Mul ...
2025-07-22 08:09:34,882 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/mlp/Mul_1 ...
2025-07-22 08:09:34,882 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/mlp/fc2/MatMul ...
2025-07-22 08:09:34,888 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/mlp/fc2/MatMul ...
2025-07-22 08:09:34,888 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/Add_1 ...
2025-07-22 08:09:34,888 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/ReduceMean ...
2025-07-22 08:09:34,888 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Sub ...
2025-07-22 08:09:34,888 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Pow ...
2025-07-22 08:09:34,888 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/ReduceMean_1 ...
2025-07-22 08:09:34,888 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Add ...
2025-07-22 08:09:34,888 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Sqrt ...
2025-07-22 08:09:34,888 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Div ...
2025-07-22 08:09:34,888 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Mul ...
2025-07-22 08:09:34,888 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Add_1 ...
2025-07-22 08:09:34,888 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_1 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_1 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Concat ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Reshape ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Cast ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:34,894 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Range ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Neg ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Einsum ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Cos ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Sin ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:34,895 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_3 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_4 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_5 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose_1 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose_2 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/MatMul ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/MatMul ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Div_1 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Add ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Softmax ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/MatMul_1 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/MatMul_1 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose_3 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_3 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_6 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_7 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_3 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_4 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Concat_1 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Reshape_1 ...
2025-07-22 08:09:34,896 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/out_proj/MatMul ...
2025-07-22 08:09:34,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/out_proj/MatMul ...
2025-07-22 08:09:34,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/Add ...
2025-07-22 08:09:34,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/ReduceMean ...
2025-07-22 08:09:34,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Sub ...
2025-07-22 08:09:34,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Pow ...
2025-07-22 08:09:34,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/ReduceMean_1 ...
2025-07-22 08:09:34,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Add ...
2025-07-22 08:09:34,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Sqrt ...
2025-07-22 08:09:34,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Div ...
2025-07-22 08:09:34,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Mul ...
2025-07-22 08:09:34,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Add_1 ...
2025-07-22 08:09:34,900 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/mlp/fc11/MatMul ...
2025-07-22 08:09:34,906 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/mlp/fc11/MatMul ...
2025-07-22 08:09:34,906 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/mlp/fc12/MatMul ...
2025-07-22 08:09:34,913 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/mlp/fc12/MatMul ...
2025-07-22 08:09:34,913 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/mlp/Sigmoid ...
2025-07-22 08:09:34,913 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/mlp/Mul ...
2025-07-22 08:09:34,913 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/mlp/Mul_1 ...
2025-07-22 08:09:34,913 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/mlp/fc2/MatMul ...
2025-07-22 08:09:34,919 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/mlp/fc2/MatMul ...
2025-07-22 08:09:34,919 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/Add_1 ...
2025-07-22 08:09:34,919 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/ReduceMean ...
2025-07-22 08:09:34,919 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Sub ...
2025-07-22 08:09:34,919 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Pow ...
2025-07-22 08:09:34,919 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/ReduceMean_1 ...
2025-07-22 08:09:34,919 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Add ...
2025-07-22 08:09:34,919 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Sqrt ...
2025-07-22 08:09:34,919 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Div ...
2025-07-22 08:09:34,919 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Mul ...
2025-07-22 08:09:34,919 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Add_1 ...
2025-07-22 08:09:34,919 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_1 ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_1 ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Concat ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Reshape ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:34,925 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Cast ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Range ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Neg ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Einsum ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Cos ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Sin ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape ...
2025-07-22 08:09:34,926 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_3 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_4 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_5 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose_1 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose_2 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/MatMul ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/MatMul ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Div_1 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Add ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Softmax ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/MatMul_1 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/MatMul_1 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose_3 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_3 ...
2025-07-22 08:09:34,927 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_6 ...
2025-07-22 08:09:34,928 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_7 ...
2025-07-22 08:09:34,928 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_3 ...
2025-07-22 08:09:34,928 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_4 ...
2025-07-22 08:09:34,928 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Concat_1 ...
2025-07-22 08:09:34,928 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Reshape_1 ...
2025-07-22 08:09:34,928 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/out_proj/MatMul ...
2025-07-22 08:09:34,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/out_proj/MatMul ...
2025-07-22 08:09:34,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/Add ...
2025-07-22 08:09:34,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/ReduceMean ...
2025-07-22 08:09:34,931 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Sub ...
2025-07-22 08:09:34,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Pow ...
2025-07-22 08:09:34,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/ReduceMean_1 ...
2025-07-22 08:09:34,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Add ...
2025-07-22 08:09:34,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Sqrt ...
2025-07-22 08:09:34,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Div ...
2025-07-22 08:09:34,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Mul ...
2025-07-22 08:09:34,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Add_1 ...
2025-07-22 08:09:34,932 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/mlp/fc11/MatMul ...
2025-07-22 08:09:34,938 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/mlp/fc11/MatMul ...
2025-07-22 08:09:34,938 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/mlp/fc12/MatMul ...
2025-07-22 08:09:34,944 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/mlp/fc12/MatMul ...
2025-07-22 08:09:34,944 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/mlp/Sigmoid ...
2025-07-22 08:09:34,944 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/mlp/Mul ...
2025-07-22 08:09:34,944 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/mlp/Mul_1 ...
2025-07-22 08:09:34,944 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/mlp/fc2/MatMul ...
2025-07-22 08:09:34,950 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/mlp/fc2/MatMul ...
2025-07-22 08:09:34,950 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/Add_1 ...
2025-07-22 08:09:34,950 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/ReduceMean ...
2025-07-22 08:09:34,951 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Sub ...
2025-07-22 08:09:34,951 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Pow ...
2025-07-22 08:09:34,951 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/ReduceMean_1 ...
2025-07-22 08:09:34,951 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Add ...
2025-07-22 08:09:34,951 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Sqrt ...
2025-07-22 08:09:34,951 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Div ...
2025-07-22 08:09:34,951 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Mul ...
2025-07-22 08:09:34,951 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Add_1 ...
2025-07-22 08:09:34,951 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,956 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,956 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape ...
2025-07-22 08:09:34,956 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_1 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_1 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Concat ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Reshape ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Cast ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Range ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Neg ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Einsum ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:34,957 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Cos ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Sin ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_3 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_4 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_5 ...
2025-07-22 08:09:34,958 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose_1 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose_2 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/MatMul ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/MatMul ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Div_1 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Add ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Softmax ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/MatMul_1 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/MatMul_1 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose_3 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_3 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_6 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_7 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_3 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_4 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Concat_1 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Reshape_1 ...
2025-07-22 08:09:34,959 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/out_proj/MatMul ...
2025-07-22 08:09:34,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/out_proj/MatMul ...
2025-07-22 08:09:34,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/Add ...
2025-07-22 08:09:34,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/ReduceMean ...
2025-07-22 08:09:34,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Sub ...
2025-07-22 08:09:34,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Pow ...
2025-07-22 08:09:34,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/ReduceMean_1 ...
2025-07-22 08:09:34,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Add ...
2025-07-22 08:09:34,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Sqrt ...
2025-07-22 08:09:34,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Div ...
2025-07-22 08:09:34,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Mul ...
2025-07-22 08:09:34,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Add_1 ...
2025-07-22 08:09:34,963 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/mlp/fc11/MatMul ...
2025-07-22 08:09:34,969 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/mlp/fc11/MatMul ...
2025-07-22 08:09:34,969 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/mlp/fc12/MatMul ...
2025-07-22 08:09:34,976 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/mlp/fc12/MatMul ...
2025-07-22 08:09:34,976 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/mlp/Sigmoid ...
2025-07-22 08:09:34,976 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/mlp/Mul ...
2025-07-22 08:09:34,976 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/mlp/Mul_1 ...
2025-07-22 08:09:34,976 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/mlp/fc2/MatMul ...
2025-07-22 08:09:34,982 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/mlp/fc2/MatMul ...
2025-07-22 08:09:34,982 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/Add_1 ...
2025-07-22 08:09:34,982 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/ReduceMean ...
2025-07-22 08:09:34,982 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Sub ...
2025-07-22 08:09:34,982 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Pow ...
2025-07-22 08:09:34,982 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/ReduceMean_1 ...
2025-07-22 08:09:34,982 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Add ...
2025-07-22 08:09:34,982 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Sqrt ...
2025-07-22 08:09:34,982 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Div ...
2025-07-22 08:09:34,982 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Mul ...
2025-07-22 08:09:34,982 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Add_1 ...
2025-07-22 08:09:34,982 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/Wqkv/MatMul ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_1 ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_1 ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Concat ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Reshape ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:34,988 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Cast ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Range ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Neg ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Einsum ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Cos ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Sin ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:34,989 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_3 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_4 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_5 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose_1 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose_2 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/MatMul ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/MatMul ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Div_1 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Add ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Softmax ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/MatMul_1 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/MatMul_1 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose_3 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_3 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_6 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_7 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_3 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_4 ...
2025-07-22 08:09:34,990 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Concat_1 ...
2025-07-22 08:09:34,991 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Reshape_1 ...
2025-07-22 08:09:34,991 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/out_proj/MatMul ...
2025-07-22 08:09:34,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/out_proj/MatMul ...
2025-07-22 08:09:34,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/Add ...
2025-07-22 08:09:34,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/ReduceMean ...
2025-07-22 08:09:34,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Sub ...
2025-07-22 08:09:34,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Pow ...
2025-07-22 08:09:34,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/ReduceMean_1 ...
2025-07-22 08:09:34,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Add ...
2025-07-22 08:09:34,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Sqrt ...
2025-07-22 08:09:34,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Div ...
2025-07-22 08:09:34,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Mul ...
2025-07-22 08:09:34,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Add_1 ...
2025-07-22 08:09:34,994 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/mlp/fc11/MatMul ...
2025-07-22 08:09:35,000 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/mlp/fc11/MatMul ...
2025-07-22 08:09:35,001 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/mlp/fc12/MatMul ...
2025-07-22 08:09:35,007 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/mlp/fc12/MatMul ...
2025-07-22 08:09:35,007 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/mlp/Sigmoid ...
2025-07-22 08:09:35,007 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/mlp/Mul ...
2025-07-22 08:09:35,007 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/mlp/Mul_1 ...
2025-07-22 08:09:35,007 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/mlp/fc2/MatMul ...
2025-07-22 08:09:35,013 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/mlp/fc2/MatMul ...
2025-07-22 08:09:35,013 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/Add_1 ...
2025-07-22 08:09:35,014 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/ReduceMean ...
2025-07-22 08:09:35,014 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Sub ...
2025-07-22 08:09:35,014 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Pow ...
2025-07-22 08:09:35,014 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/ReduceMean_1 ...
2025-07-22 08:09:35,014 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Add ...
2025-07-22 08:09:35,014 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Sqrt ...
2025-07-22 08:09:35,014 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Div ...
2025-07-22 08:09:35,014 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Mul ...
2025-07-22 08:09:35,014 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Add_1 ...
2025-07-22 08:09:35,014 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/Wqkv/MatMul ...
2025-07-22 08:09:35,019 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/Wqkv/MatMul ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_1 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_1 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Concat ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Reshape ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Cast ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Range ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Neg ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Einsum ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:35,020 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Cos ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Sin ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_3 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_4 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_5 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose_1 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose_2 ...
2025-07-22 08:09:35,021 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/MatMul ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/MatMul ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Div_1 ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Add ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Softmax ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/MatMul_1 ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/MatMul_1 ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose_3 ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_3 ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_6 ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_7 ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_3 ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_4 ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Concat_1 ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Reshape_1 ...
2025-07-22 08:09:35,022 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/out_proj/MatMul ...
2025-07-22 08:09:35,026 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/out_proj/MatMul ...
2025-07-22 08:09:35,026 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/Add ...
2025-07-22 08:09:35,026 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/ReduceMean ...
2025-07-22 08:09:35,026 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Sub ...
2025-07-22 08:09:35,026 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Pow ...
2025-07-22 08:09:35,026 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/ReduceMean_1 ...
2025-07-22 08:09:35,026 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Add ...
2025-07-22 08:09:35,026 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Sqrt ...
2025-07-22 08:09:35,026 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Div ...
2025-07-22 08:09:35,026 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Mul ...
2025-07-22 08:09:35,026 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Add_1 ...
2025-07-22 08:09:35,026 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/mlp/fc11/MatMul ...
2025-07-22 08:09:35,032 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/mlp/fc11/MatMul ...
2025-07-22 08:09:35,032 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/mlp/fc12/MatMul ...
2025-07-22 08:09:35,039 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/mlp/fc12/MatMul ...
2025-07-22 08:09:35,039 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/mlp/Sigmoid ...
2025-07-22 08:09:35,039 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/mlp/Mul ...
2025-07-22 08:09:35,039 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/mlp/Mul_1 ...
2025-07-22 08:09:35,039 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/mlp/fc2/MatMul ...
2025-07-22 08:09:35,045 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/mlp/fc2/MatMul ...
2025-07-22 08:09:35,045 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/Add_1 ...
2025-07-22 08:09:35,045 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/ReduceMean ...
2025-07-22 08:09:35,045 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Sub ...
2025-07-22 08:09:35,046 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Pow ...
2025-07-22 08:09:35,046 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/ReduceMean_1 ...
2025-07-22 08:09:35,046 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Add ...
2025-07-22 08:09:35,046 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Sqrt ...
2025-07-22 08:09:35,046 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Div ...
2025-07-22 08:09:35,046 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Mul ...
2025-07-22 08:09:35,046 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Add_1 ...
2025-07-22 08:09:35,046 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/Wqkv/MatMul ...
2025-07-22 08:09:35,051 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/Wqkv/MatMul ...
2025-07-22 08:09:35,051 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape ...
2025-07-22 08:09:35,051 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather ...
2025-07-22 08:09:35,051 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_1 ...
2025-07-22 08:09:35,051 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze ...
2025-07-22 08:09:35,051 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_1 ...
2025-07-22 08:09:35,051 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Concat ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Reshape ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Cast ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Range ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Neg ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Einsum ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Cos ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Sin ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:35,052 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_3 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_4 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_5 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose_1 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose_2 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/MatMul ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/MatMul ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Div_1 ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Add ...
2025-07-22 08:09:35,053 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Softmax ...
2025-07-22 08:09:35,054 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/MatMul_1 ...
2025-07-22 08:09:35,054 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:35,054 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/MatMul_1 ...
2025-07-22 08:09:35,054 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose_3 ...
2025-07-22 08:09:35,054 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_3 ...
2025-07-22 08:09:35,054 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_6 ...
2025-07-22 08:09:35,054 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_7 ...
2025-07-22 08:09:35,054 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_3 ...
2025-07-22 08:09:35,054 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_4 ...
2025-07-22 08:09:35,054 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Concat_1 ...
2025-07-22 08:09:35,054 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Reshape_1 ...
2025-07-22 08:09:35,054 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/out_proj/MatMul ...
2025-07-22 08:09:35,058 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/out_proj/MatMul ...
2025-07-22 08:09:35,058 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/Add ...
2025-07-22 08:09:35,058 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/ReduceMean ...
2025-07-22 08:09:35,058 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Sub ...
2025-07-22 08:09:35,058 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Pow ...
2025-07-22 08:09:35,058 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/ReduceMean_1 ...
2025-07-22 08:09:35,058 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Add ...
2025-07-22 08:09:35,058 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Sqrt ...
2025-07-22 08:09:35,058 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Div ...
2025-07-22 08:09:35,058 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Mul ...
2025-07-22 08:09:35,058 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Add_1 ...
2025-07-22 08:09:35,058 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/mlp/fc11/MatMul ...
2025-07-22 08:09:35,064 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/mlp/fc11/MatMul ...
2025-07-22 08:09:35,064 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/mlp/fc12/MatMul ...
2025-07-22 08:09:35,070 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/mlp/fc12/MatMul ...
2025-07-22 08:09:35,070 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/mlp/Sigmoid ...
2025-07-22 08:09:35,070 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/mlp/Mul ...
2025-07-22 08:09:35,070 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/mlp/Mul_1 ...
2025-07-22 08:09:35,070 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/mlp/fc2/MatMul ...
2025-07-22 08:09:35,077 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/mlp/fc2/MatMul ...
2025-07-22 08:09:35,077 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/Add_1 ...
2025-07-22 08:09:35,077 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/ReduceMean ...
2025-07-22 08:09:35,077 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Sub ...
2025-07-22 08:09:35,077 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Pow ...
2025-07-22 08:09:35,077 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/ReduceMean_1 ...
2025-07-22 08:09:35,077 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Add ...
2025-07-22 08:09:35,077 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Sqrt ...
2025-07-22 08:09:35,077 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Div ...
2025-07-22 08:09:35,077 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Mul ...
2025-07-22 08:09:35,077 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Add_1 ...
2025-07-22 08:09:35,077 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/Wqkv/MatMul ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/Wqkv/MatMul ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_1 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_1 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Concat ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Reshape ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Cast ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Range ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Neg ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:35,083 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Einsum ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Cos ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Sin ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_3 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_4 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_5 ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose ...
2025-07-22 08:09:35,084 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose_1 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose_2 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/MatMul ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/MatMul ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Div_1 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Add ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Softmax ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/MatMul_1 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/MatMul_1 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose_3 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_3 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_6 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_7 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_3 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_4 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Concat_1 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Reshape_1 ...
2025-07-22 08:09:35,085 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/out_proj/MatMul ...
2025-07-22 08:09:35,089 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/out_proj/MatMul ...
2025-07-22 08:09:35,089 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/Add ...
2025-07-22 08:09:35,089 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/ReduceMean ...
2025-07-22 08:09:35,089 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Sub ...
2025-07-22 08:09:35,089 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Pow ...
2025-07-22 08:09:35,089 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/ReduceMean_1 ...
2025-07-22 08:09:35,089 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Add ...
2025-07-22 08:09:35,089 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Sqrt ...
2025-07-22 08:09:35,089 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Div ...
2025-07-22 08:09:35,089 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Mul ...
2025-07-22 08:09:35,089 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Add_1 ...
2025-07-22 08:09:35,089 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/mlp/fc11/MatMul ...
2025-07-22 08:09:35,095 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/mlp/fc11/MatMul ...
2025-07-22 08:09:35,095 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/mlp/fc12/MatMul ...
2025-07-22 08:09:35,102 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/mlp/fc12/MatMul ...
2025-07-22 08:09:35,102 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/mlp/Sigmoid ...
2025-07-22 08:09:35,102 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/mlp/Mul ...
2025-07-22 08:09:35,102 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/mlp/Mul_1 ...
2025-07-22 08:09:35,102 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/mlp/fc2/MatMul ...
2025-07-22 08:09:35,108 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/mlp/fc2/MatMul ...
2025-07-22 08:09:35,108 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/Add_1 ...
2025-07-22 08:09:35,108 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/ReduceMean ...
2025-07-22 08:09:35,108 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Sub ...
2025-07-22 08:09:35,108 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Pow ...
2025-07-22 08:09:35,108 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/ReduceMean_1 ...
2025-07-22 08:09:35,108 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Add ...
2025-07-22 08:09:35,108 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Sqrt ...
2025-07-22 08:09:35,108 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Div ...
2025-07-22 08:09:35,108 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Mul ...
2025-07-22 08:09:35,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Add_1 ...
2025-07-22 08:09:35,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/Wqkv/MatMul ...
2025-07-22 08:09:35,114 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/Wqkv/MatMul ...
2025-07-22 08:09:35,114 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape ...
2025-07-22 08:09:35,114 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather ...
2025-07-22 08:09:35,114 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_1 ...
2025-07-22 08:09:35,114 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze ...
2025-07-22 08:09:35,114 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_1 ...
2025-07-22 08:09:35,114 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Concat ...
2025-07-22 08:09:35,114 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Reshape ...
2025-07-22 08:09:35,114 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Cast ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Range ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Neg ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Einsum ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Cos ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Sin ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:35,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_3 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_4 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_5 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose_1 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose_2 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/MatMul ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/MatMul ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Div_1 ...
2025-07-22 08:09:35,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Add ...
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Softmax ...
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/MatMul_1 ...
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/MatMul_1 ...
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose_3 ...
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_3 ...
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_6 ...
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_7 ...
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_3 ...
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_4 ...
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Concat_1 ...
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Reshape_1 ...
2025-07-22 08:09:35,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/out_proj/MatMul ...
2025-07-22 08:09:35,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/out_proj/MatMul ...
2025-07-22 08:09:35,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/Add ...
2025-07-22 08:09:35,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/ReduceMean ...
2025-07-22 08:09:35,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Sub ...
2025-07-22 08:09:35,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Pow ...
2025-07-22 08:09:35,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/ReduceMean_1 ...
2025-07-22 08:09:35,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Add ...
2025-07-22 08:09:35,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Sqrt ...
2025-07-22 08:09:35,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Div ...
2025-07-22 08:09:35,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Mul ...
2025-07-22 08:09:35,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Add_1 ...
2025-07-22 08:09:35,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/mlp/fc11/MatMul ...
2025-07-22 08:09:35,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/mlp/fc11/MatMul ...
2025-07-22 08:09:35,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/mlp/fc12/MatMul ...
2025-07-22 08:09:35,133 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/mlp/fc12/MatMul ...
2025-07-22 08:09:35,133 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/mlp/Sigmoid ...
2025-07-22 08:09:35,133 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/mlp/Mul ...
2025-07-22 08:09:35,133 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/mlp/Mul_1 ...
2025-07-22 08:09:35,133 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/mlp/fc2/MatMul ...
2025-07-22 08:09:35,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/mlp/fc2/MatMul ...
2025-07-22 08:09:35,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/Add_1 ...
2025-07-22 08:09:35,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/ReduceMean ...
2025-07-22 08:09:35,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Sub ...
2025-07-22 08:09:35,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Pow ...
2025-07-22 08:09:35,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/ReduceMean_1 ...
2025-07-22 08:09:35,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Add ...
2025-07-22 08:09:35,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Sqrt ...
2025-07-22 08:09:35,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Div ...
2025-07-22 08:09:35,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Mul ...
2025-07-22 08:09:35,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Add_1 ...
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.2307730834493213e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.2338328136962673e-09 will be truncated to -1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:85: UserWarning: the float32 number -3.4028234663852886e+38 will be truncated to -10000.0
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 9.999999960041972e-13 will be truncated to 1e-07
  warnings.warn(

 - Quantizing to q4f16:  60%|██████    | 3/5 [00:12<00:08,  4.32s/it]

Processing /tmp/tmpnbc83gzs/model.onnx:   0%|          | 0/1 [00:12<?, ?it/s]
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 377, in <module>
    main()
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 374, in main
    quantize(input_folder, output_folder, quantization_args)
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 326, in quantize
    quantize_fp16(
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 223, in quantize_fp16
    check_and_save_model(model_fp16, save_path)
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/utils.py", line 29, in check_and_save_model
    strict_check_model(model)
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/utils.py", line 21, in strict_check_model
    raise e
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/utils.py", line 16, in strict_check_model
    onnx.checker.check_model(model_or_path, full_check=True)
  File "/home/ubuntu/.cache/uv/archive-v0/iAncxVR1WPOl_8LkA6LpD/lib/python3.12/site-packages/onnx/checker.py", line 179, in check_model
    C.check_model(
onnx.onnx_cpp2py_export.shape_inference.InferenceError: [ShapeInferenceError] (op_type:Range, node name: /encoder/layers.0/attn/rotary_emb/Range): start typestr: T, has unsupported type: tensor(float16)

❌ Based on model.onnx without slimming

0%|          | 0/1 [00:00<?, ?it/s]
Processing /tmp/tmppds0d9jk/model.onnx:   0%|          | 0/1 [00:00<?, ?it/s]

  0%|          | 0/5 [00:00<?, ?it/s]

 - Quantizing to int8:   0%|          | 0/5 [00:00<?, ?it/s]2025-07-22 08:09:43,061 root [INFO] - Quantization parameters for tensor:"/emb_ln/Add_1_output_0" not specified
2025-07-22 08:09:43,068 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.0/attn/MatMul]
2025-07-22 08:09:43,068 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.0/attn/MatMul_1]
2025-07-22 08:09:43,070 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:43,073 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/norm1/Add_1_output_0" not specified
2025-07-22 08:09:43,091 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:43,100 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/norm2/Add_1_output_0" not specified
2025-07-22 08:09:43,107 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.1/attn/MatMul]
2025-07-22 08:09:43,107 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.1/attn/MatMul_1]
2025-07-22 08:09:43,109 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:43,113 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/norm1/Add_1_output_0" not specified
2025-07-22 08:09:43,130 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:43,138 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/norm2/Add_1_output_0" not specified
2025-07-22 08:09:43,146 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.2/attn/MatMul]
2025-07-22 08:09:43,146 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.2/attn/MatMul_1]
2025-07-22 08:09:43,148 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:43,151 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/norm1/Add_1_output_0" not specified
2025-07-22 08:09:43,169 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:43,178 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/norm2/Add_1_output_0" not specified
2025-07-22 08:09:43,185 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.3/attn/MatMul]
2025-07-22 08:09:43,186 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.3/attn/MatMul_1]
2025-07-22 08:09:43,187 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:43,191 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/norm1/Add_1_output_0" not specified
2025-07-22 08:09:43,208 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:43,217 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/norm2/Add_1_output_0" not specified
2025-07-22 08:09:43,224 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.4/attn/MatMul]
2025-07-22 08:09:43,225 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.4/attn/MatMul_1]
2025-07-22 08:09:43,226 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:43,230 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/norm1/Add_1_output_0" not specified
2025-07-22 08:09:43,247 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:43,257 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/norm2/Add_1_output_0" not specified
2025-07-22 08:09:43,265 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.5/attn/MatMul]
2025-07-22 08:09:43,265 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.5/attn/MatMul_1]
2025-07-22 08:09:43,267 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:43,271 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/norm1/Add_1_output_0" not specified
2025-07-22 08:09:43,289 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:43,298 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/norm2/Add_1_output_0" not specified
2025-07-22 08:09:43,307 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.6/attn/MatMul]
2025-07-22 08:09:43,307 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.6/attn/MatMul_1]
2025-07-22 08:09:43,309 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:43,312 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/norm1/Add_1_output_0" not specified
2025-07-22 08:09:43,331 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:43,341 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/norm2/Add_1_output_0" not specified
2025-07-22 08:09:43,349 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.7/attn/MatMul]
2025-07-22 08:09:43,350 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.7/attn/MatMul_1]
2025-07-22 08:09:43,351 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:43,355 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/norm1/Add_1_output_0" not specified
2025-07-22 08:09:43,374 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:43,384 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/norm2/Add_1_output_0" not specified
2025-07-22 08:09:43,393 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.8/attn/MatMul]
2025-07-22 08:09:43,393 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.8/attn/MatMul_1]
2025-07-22 08:09:43,395 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:43,399 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/norm1/Add_1_output_0" not specified
2025-07-22 08:09:43,418 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:43,429 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/norm2/Add_1_output_0" not specified
2025-07-22 08:09:43,437 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.9/attn/MatMul]
2025-07-22 08:09:43,438 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.9/attn/MatMul_1]
2025-07-22 08:09:43,440 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:43,444 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/norm1/Add_1_output_0" not specified
2025-07-22 08:09:43,461 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:43,472 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/norm2/Add_1_output_0" not specified
2025-07-22 08:09:43,481 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.10/attn/MatMul]
2025-07-22 08:09:43,481 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.10/attn/MatMul_1]
2025-07-22 08:09:43,483 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:43,487 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/norm1/Add_1_output_0" not specified
2025-07-22 08:09:43,506 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:43,517 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/norm2/Add_1_output_0" not specified
2025-07-22 08:09:43,526 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.11/attn/MatMul]
2025-07-22 08:09:43,526 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.11/attn/MatMul_1]
2025-07-22 08:09:43,528 root [INFO] - Quantization parameters for tensor:"/encoder/layers.11/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:43,532 root [INFO] - Quantization parameters for tensor:"/encoder/layers.11/norm1/Add_1_output_0" not specified
2025-07-22 08:09:43,552 root [INFO] - Quantization parameters for tensor:"/encoder/layers.11/mlp/Mul_1_output_0" not specified


 - Quantizing to int8:  20%|██        | 1/5 [00:05<00:21,  5.31s/it]

 - Quantizing to uint8:  20%|██        | 1/5 [00:05<00:21,  5.31s/it]2025-07-22 08:09:47,298 root [INFO] - Quantization parameters for tensor:"/emb_ln/Add_1_output_0" not specified
2025-07-22 08:09:47,305 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.0/attn/MatMul]
2025-07-22 08:09:47,305 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.0/attn/MatMul_1]
2025-07-22 08:09:47,307 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:47,310 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/norm1/Add_1_output_0" not specified
2025-07-22 08:09:47,328 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:47,336 root [INFO] - Quantization parameters for tensor:"/encoder/layers.0/norm2/Add_1_output_0" not specified
2025-07-22 08:09:47,343 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.1/attn/MatMul]
2025-07-22 08:09:47,344 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.1/attn/MatMul_1]
2025-07-22 08:09:47,345 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:47,349 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/norm1/Add_1_output_0" not specified
2025-07-22 08:09:47,365 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:47,374 root [INFO] - Quantization parameters for tensor:"/encoder/layers.1/norm2/Add_1_output_0" not specified
2025-07-22 08:09:47,381 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.2/attn/MatMul]
2025-07-22 08:09:47,382 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.2/attn/MatMul_1]
2025-07-22 08:09:47,383 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:47,387 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/norm1/Add_1_output_0" not specified
2025-07-22 08:09:47,403 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:47,413 root [INFO] - Quantization parameters for tensor:"/encoder/layers.2/norm2/Add_1_output_0" not specified
2025-07-22 08:09:47,421 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.3/attn/MatMul]
2025-07-22 08:09:47,421 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.3/attn/MatMul_1]
2025-07-22 08:09:47,423 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:47,426 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/norm1/Add_1_output_0" not specified
2025-07-22 08:09:47,442 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:47,451 root [INFO] - Quantization parameters for tensor:"/encoder/layers.3/norm2/Add_1_output_0" not specified
2025-07-22 08:09:47,459 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.4/attn/MatMul]
2025-07-22 08:09:47,459 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.4/attn/MatMul_1]
2025-07-22 08:09:47,461 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:47,465 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/norm1/Add_1_output_0" not specified
2025-07-22 08:09:47,483 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:47,492 root [INFO] - Quantization parameters for tensor:"/encoder/layers.4/norm2/Add_1_output_0" not specified
2025-07-22 08:09:47,500 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.5/attn/MatMul]
2025-07-22 08:09:47,500 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.5/attn/MatMul_1]
2025-07-22 08:09:47,502 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:47,506 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/norm1/Add_1_output_0" not specified
2025-07-22 08:09:47,524 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:47,534 root [INFO] - Quantization parameters for tensor:"/encoder/layers.5/norm2/Add_1_output_0" not specified
2025-07-22 08:09:47,543 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.6/attn/MatMul]
2025-07-22 08:09:47,543 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.6/attn/MatMul_1]
2025-07-22 08:09:47,545 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:47,549 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/norm1/Add_1_output_0" not specified
2025-07-22 08:09:47,568 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:47,578 root [INFO] - Quantization parameters for tensor:"/encoder/layers.6/norm2/Add_1_output_0" not specified
2025-07-22 08:09:47,586 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.7/attn/MatMul]
2025-07-22 08:09:47,586 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.7/attn/MatMul_1]
2025-07-22 08:09:47,588 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:47,592 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/norm1/Add_1_output_0" not specified
2025-07-22 08:09:47,610 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:47,620 root [INFO] - Quantization parameters for tensor:"/encoder/layers.7/norm2/Add_1_output_0" not specified
2025-07-22 08:09:47,629 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.8/attn/MatMul]
2025-07-22 08:09:47,629 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.8/attn/MatMul_1]
2025-07-22 08:09:47,631 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:47,635 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/norm1/Add_1_output_0" not specified
2025-07-22 08:09:47,654 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:47,663 root [INFO] - Quantization parameters for tensor:"/encoder/layers.8/norm2/Add_1_output_0" not specified
2025-07-22 08:09:47,672 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.9/attn/MatMul]
2025-07-22 08:09:47,672 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.9/attn/MatMul_1]
2025-07-22 08:09:47,674 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:47,678 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/norm1/Add_1_output_0" not specified
2025-07-22 08:09:47,698 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:47,707 root [INFO] - Quantization parameters for tensor:"/encoder/layers.9/norm2/Add_1_output_0" not specified
2025-07-22 08:09:47,716 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.10/attn/MatMul]
2025-07-22 08:09:47,717 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.10/attn/MatMul_1]
2025-07-22 08:09:47,719 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:47,723 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/norm1/Add_1_output_0" not specified
2025-07-22 08:09:47,742 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/mlp/Mul_1_output_0" not specified
2025-07-22 08:09:47,752 root [INFO] - Quantization parameters for tensor:"/encoder/layers.10/norm2/Add_1_output_0" not specified
2025-07-22 08:09:47,761 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.11/attn/MatMul]
2025-07-22 08:09:47,761 root [INFO] - Ignore MatMul due to non constant B: /[/encoder/layers.11/attn/MatMul_1]
2025-07-22 08:09:47,763 root [INFO] - Quantization parameters for tensor:"/encoder/layers.11/attn/Reshape_1_output_0" not specified
2025-07-22 08:09:47,767 root [INFO] - Quantization parameters for tensor:"/encoder/layers.11/norm1/Add_1_output_0" not specified
2025-07-22 08:09:47,787 root [INFO] - Quantization parameters for tensor:"/encoder/layers.11/mlp/Mul_1_output_0" not specified


 - Quantizing to uint8:  40%|████      | 2/5 [00:09<00:13,  4.62s/it]

 - Quantizing to q4:  40%|████      | 2/5 [00:09<00:13,  4.62s/it]   2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/word_embeddings/Gather ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/token_type_embeddings/Gather ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/Constant ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/Add ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/ReduceMean ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Sub ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Constant ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Pow ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/ReduceMean_1 ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Constant_1 ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Add ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Sqrt ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Div ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Mul ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Add_1 ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Constant ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Constant_1 ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_1 ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Cast ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Constant_2 ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Sub ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Constant_3 ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Mul ...
2025-07-22 08:09:49,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape ...
2025-07-22 08:09:49,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant ...
2025-07-22 08:09:49,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather ...
2025-07-22 08:09:49,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_1 ...
2025-07-22 08:09:49,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_1 ...
2025-07-22 08:09:49,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_1 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_2 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_2 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_2 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_3 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Div ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Cast ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Cast_1 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_1 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_4 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_2 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_5 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Concat ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Reshape ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Cast ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Range ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Einsum ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Cos ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Sin ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:49,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Equal ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Where ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape ...
2025-07-22 08:09:49,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Add ...
2025-07-22 08:09:49,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Div ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Neg ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:49,377 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:49,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:49,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_75 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_3 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_4 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_5 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose_1 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose_2 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/MatMul ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/MatMul ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_6 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Div_1 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Add ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Softmax ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/MatMul_1 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/MatMul_1 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose_3 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_3 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_7 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_6 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_4 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_8 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_7 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_5 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_9 ...
2025-07-22 08:09:49,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_8 ...
2025-07-22 08:09:49,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_6 ...
2025-07-22 08:09:49,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_10 ...
2025-07-22 08:09:49,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_9 ...
2025-07-22 08:09:49,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_11 ...
2025-07-22 08:09:49,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Mul ...
2025-07-22 08:09:49,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Mul_1 ...
2025-07-22 08:09:49,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_3 ...
2025-07-22 08:09:49,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_4 ...
2025-07-22 08:09:49,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_5 ...
2025-07-22 08:09:49,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Concat_1 ...
2025-07-22 08:09:49,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Reshape_1 ...
2025-07-22 08:09:49,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/out_proj/MatMul ...
2025-07-22 08:09:49,384 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/out_proj/MatMul ...
2025-07-22 08:09:49,384 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/Add ...
2025-07-22 08:09:49,384 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/Cast ...
2025-07-22 08:09:49,384 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/ReduceMean ...
2025-07-22 08:09:49,384 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Sub ...
2025-07-22 08:09:49,384 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Constant ...
2025-07-22 08:09:49,384 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Pow ...
2025-07-22 08:09:49,384 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/ReduceMean_1 ...
2025-07-22 08:09:49,384 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Constant_1 ...
2025-07-22 08:09:49,384 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Add ...
2025-07-22 08:09:49,384 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Sqrt ...
2025-07-22 08:09:49,384 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Div ...
2025-07-22 08:09:49,385 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Mul ...
2025-07-22 08:09:49,385 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Add_1 ...
2025-07-22 08:09:49,385 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/mlp/fc11/MatMul ...
2025-07-22 08:09:49,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/mlp/fc11/MatMul ...
2025-07-22 08:09:49,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/mlp/fc12/MatMul ...
2025-07-22 08:09:49,397 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/mlp/fc12/MatMul ...
2025-07-22 08:09:49,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/mlp/Sigmoid ...
2025-07-22 08:09:49,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/mlp/Mul ...
2025-07-22 08:09:49,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/mlp/Mul_1 ...
2025-07-22 08:09:49,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/mlp/fc2/MatMul ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/mlp/fc2/MatMul ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/Add_1 ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/Cast_1 ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/ReduceMean ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Sub ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Constant ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Pow ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/ReduceMean_1 ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Constant_1 ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Add ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Sqrt ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Div ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Mul ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Add_1 ...
2025-07-22 08:09:49,404 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_1 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_1 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_1 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_2 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_2 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_2 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_3 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Div ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Cast ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Cast_1 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_1 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_4 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_2 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_5 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Concat ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Reshape ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Cast ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Range ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Einsum ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Cos ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Sin ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:49,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:49,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Equal ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Where ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:49,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Add ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Div ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Neg ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:49,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:49,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:49,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_3 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_4 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_5 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose_1 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose_2 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/MatMul ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/MatMul ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_6 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Div_1 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Add ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Softmax ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/MatMul_1 ...
2025-07-22 08:09:49,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/MatMul_1 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose_3 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_3 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_7 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_6 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_4 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_8 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_7 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_5 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_9 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_8 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_6 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_10 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_9 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_11 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Mul ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Mul_1 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_3 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_4 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_5 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Concat_1 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Reshape_1 ...
2025-07-22 08:09:49,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/out_proj/MatMul ...
2025-07-22 08:09:49,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/out_proj/MatMul ...
2025-07-22 08:09:49,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/Add ...
2025-07-22 08:09:49,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/Cast ...
2025-07-22 08:09:49,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/ReduceMean ...
2025-07-22 08:09:49,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Sub ...
2025-07-22 08:09:49,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Constant ...
2025-07-22 08:09:49,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Pow ...
2025-07-22 08:09:49,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/ReduceMean_1 ...
2025-07-22 08:09:49,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Constant_1 ...
2025-07-22 08:09:49,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Add ...
2025-07-22 08:09:49,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Sqrt ...
2025-07-22 08:09:49,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Div ...
2025-07-22 08:09:49,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Mul ...
2025-07-22 08:09:49,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Add_1 ...
2025-07-22 08:09:49,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/mlp/fc11/MatMul ...
2025-07-22 08:09:49,427 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/mlp/fc11/MatMul ...
2025-07-22 08:09:49,427 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/mlp/fc12/MatMul ...
2025-07-22 08:09:49,434 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/mlp/fc12/MatMul ...
2025-07-22 08:09:49,434 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/mlp/Sigmoid ...
2025-07-22 08:09:49,434 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/mlp/Mul ...
2025-07-22 08:09:49,434 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/mlp/Mul_1 ...
2025-07-22 08:09:49,434 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/mlp/fc2/MatMul ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/mlp/fc2/MatMul ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/Add_1 ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/Cast_1 ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/ReduceMean ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Sub ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Constant ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Pow ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/ReduceMean_1 ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Constant_1 ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Add ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Sqrt ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Div ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Mul ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Add_1 ...
2025-07-22 08:09:49,440 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_1 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_1 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_1 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_2 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_2 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_2 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_3 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Div ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Cast ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Cast_1 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_1 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_4 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_2 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_5 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Concat ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Reshape ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Cast ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Range ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Einsum ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Cos ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:49,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Sin ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:49,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Equal ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Where ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:49,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Add ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Div ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Neg ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:49,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:49,450 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:49,451 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_3 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_4 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_5 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose_1 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose_2 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/MatMul ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/MatMul ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_6 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Div_1 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Add ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Softmax ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/MatMul_1 ...
2025-07-22 08:09:49,452 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/MatMul_1 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose_3 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_3 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_7 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_6 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_4 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_8 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_7 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_5 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_9 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_8 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_6 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_10 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_9 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_11 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Mul ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Mul_1 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_3 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_4 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_5 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Concat_1 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Reshape_1 ...
2025-07-22 08:09:49,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/out_proj/MatMul ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/out_proj/MatMul ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/Add ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/Cast ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/ReduceMean ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Sub ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Constant ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Pow ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/ReduceMean_1 ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Constant_1 ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Add ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Sqrt ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Div ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Mul ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Add_1 ...
2025-07-22 08:09:49,457 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/mlp/fc11/MatMul ...
2025-07-22 08:09:49,463 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/mlp/fc11/MatMul ...
2025-07-22 08:09:49,463 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/mlp/fc12/MatMul ...
2025-07-22 08:09:49,470 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/mlp/fc12/MatMul ...
2025-07-22 08:09:49,470 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/mlp/Sigmoid ...
2025-07-22 08:09:49,470 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/mlp/Mul ...
2025-07-22 08:09:49,470 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/mlp/Mul_1 ...
2025-07-22 08:09:49,470 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/mlp/fc2/MatMul ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/mlp/fc2/MatMul ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/Add_1 ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/Cast_1 ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/ReduceMean ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Sub ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Constant ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Pow ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/ReduceMean_1 ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Constant_1 ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Add ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Sqrt ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Div ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Mul ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Add_1 ...
2025-07-22 08:09:49,476 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_1 ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_1 ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_1 ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_2 ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_2 ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_2 ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_3 ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Div ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Cast ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Cast_1 ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_1 ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_4 ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_2 ...
2025-07-22 08:09:49,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_5 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Concat ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Reshape ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Cast ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Range ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Einsum ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Cos ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Sin ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:49,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Equal ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Where ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:49,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Add ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Div ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Neg ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:49,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:49,486 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:49,487 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_3 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_4 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_5 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose_1 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose_2 ...
2025-07-22 08:09:49,488 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/MatMul ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/MatMul ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_6 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Div_1 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Add ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Softmax ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/MatMul_1 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/MatMul_1 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose_3 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_3 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_7 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_6 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_4 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_8 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_7 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_5 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_9 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_8 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_6 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_10 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_9 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_11 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Mul ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Mul_1 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_3 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_4 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_5 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Concat_1 ...
2025-07-22 08:09:49,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Reshape_1 ...
2025-07-22 08:09:49,490 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/out_proj/MatMul ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/out_proj/MatMul ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/Add ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/Cast ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/ReduceMean ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Sub ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Constant ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Pow ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/ReduceMean_1 ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Constant_1 ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Add ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Sqrt ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Div ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Mul ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Add_1 ...
2025-07-22 08:09:49,493 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/mlp/fc11/MatMul ...
2025-07-22 08:09:49,500 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/mlp/fc11/MatMul ...
2025-07-22 08:09:49,500 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/mlp/fc12/MatMul ...
2025-07-22 08:09:49,506 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/mlp/fc12/MatMul ...
2025-07-22 08:09:49,506 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/mlp/Sigmoid ...
2025-07-22 08:09:49,506 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/mlp/Mul ...
2025-07-22 08:09:49,506 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/mlp/Mul_1 ...
2025-07-22 08:09:49,506 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/mlp/fc2/MatMul ...
2025-07-22 08:09:49,512 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/mlp/fc2/MatMul ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/Add_1 ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/Cast_1 ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/ReduceMean ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Sub ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Constant ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Pow ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/ReduceMean_1 ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Constant_1 ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Add ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Sqrt ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Div ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Mul ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Add_1 ...
2025-07-22 08:09:49,513 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_1 ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_1 ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_1 ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_2 ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_2 ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_2 ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_3 ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Div ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Cast ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Cast_1 ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_1 ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_4 ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_2 ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_5 ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Concat ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Reshape ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant ...
2025-07-22 08:09:49,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Cast ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Range ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Einsum ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Cos ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Sin ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:49,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Equal ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Where ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:49,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Add ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Div ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Neg ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:49,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:49,523 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:49,524 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_3 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_4 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_5 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose_1 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose_2 ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/MatMul ...
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/MatMul ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_6 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Div_1 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Add ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Softmax ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/MatMul_1 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/MatMul_1 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose_3 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_3 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_7 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_6 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_4 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_8 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_7 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_5 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_9 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_8 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_6 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_10 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_9 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_11 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Mul ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Mul_1 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_3 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_4 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_5 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Concat_1 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Reshape_1 ...
2025-07-22 08:09:49,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/out_proj/MatMul ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/out_proj/MatMul ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/Add ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/Cast ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/ReduceMean ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Sub ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Constant ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Pow ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/ReduceMean_1 ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Constant_1 ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Add ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Sqrt ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Div ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Mul ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Add_1 ...
2025-07-22 08:09:49,530 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/mlp/fc11/MatMul ...
2025-07-22 08:09:49,536 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/mlp/fc11/MatMul ...
2025-07-22 08:09:49,537 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/mlp/fc12/MatMul ...
2025-07-22 08:09:49,543 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/mlp/fc12/MatMul ...
2025-07-22 08:09:49,543 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/mlp/Sigmoid ...
2025-07-22 08:09:49,543 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/mlp/Mul ...
2025-07-22 08:09:49,543 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/mlp/Mul_1 ...
2025-07-22 08:09:49,543 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/mlp/fc2/MatMul ...
2025-07-22 08:09:49,549 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/mlp/fc2/MatMul ...
2025-07-22 08:09:49,549 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/Add_1 ...
2025-07-22 08:09:49,549 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/Cast_1 ...
2025-07-22 08:09:49,549 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/ReduceMean ...
2025-07-22 08:09:49,549 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Sub ...
2025-07-22 08:09:49,549 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Constant ...
2025-07-22 08:09:49,549 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Pow ...
2025-07-22 08:09:49,550 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/ReduceMean_1 ...
2025-07-22 08:09:49,550 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Constant_1 ...
2025-07-22 08:09:49,550 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Add ...
2025-07-22 08:09:49,550 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Sqrt ...
2025-07-22 08:09:49,550 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Div ...
2025-07-22 08:09:49,550 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Mul ...
2025-07-22 08:09:49,550 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Add_1 ...
2025-07-22 08:09:49,550 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape ...
2025-07-22 08:09:49,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant ...
2025-07-22 08:09:49,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather ...
2025-07-22 08:09:49,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_1 ...
2025-07-22 08:09:49,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_1 ...
2025-07-22 08:09:49,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_1 ...
2025-07-22 08:09:49,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_2 ...
2025-07-22 08:09:49,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_2 ...
2025-07-22 08:09:49,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_2 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_3 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Div ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Cast ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Cast_1 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_1 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_4 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_2 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_5 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Concat ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Reshape ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Cast ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Range ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Einsum ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Cos ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Sin ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul ...
2025-07-22 08:09:49,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Equal ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Where ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:49,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:49,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Add ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Div ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Neg ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:49,559 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:49,560 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:49,561 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_3 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_4 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_5 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose_1 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose_2 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/MatMul ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/MatMul ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_6 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Div_1 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Add ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Softmax ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/MatMul_1 ...
2025-07-22 08:09:49,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/MatMul_1 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose_3 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_3 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_7 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_6 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_4 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_8 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_7 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_5 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_9 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_8 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_6 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_10 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_9 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_11 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Mul ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Mul_1 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_3 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_4 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_5 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Concat_1 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Reshape_1 ...
2025-07-22 08:09:49,563 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/out_proj/MatMul ...
2025-07-22 08:09:49,566 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/out_proj/MatMul ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/Add ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/Cast ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/ReduceMean ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Sub ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Constant ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Pow ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/ReduceMean_1 ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Constant_1 ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Add ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Sqrt ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Div ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Mul ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Add_1 ...
2025-07-22 08:09:49,567 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/mlp/fc11/MatMul ...
2025-07-22 08:09:49,573 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/mlp/fc11/MatMul ...
2025-07-22 08:09:49,573 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/mlp/fc12/MatMul ...
2025-07-22 08:09:49,579 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/mlp/fc12/MatMul ...
2025-07-22 08:09:49,580 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/mlp/Sigmoid ...
2025-07-22 08:09:49,580 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/mlp/Mul ...
2025-07-22 08:09:49,580 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/mlp/Mul_1 ...
2025-07-22 08:09:49,580 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/mlp/fc2/MatMul ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/mlp/fc2/MatMul ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/Add_1 ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/Cast_1 ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/ReduceMean ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Sub ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Constant ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Pow ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/ReduceMean_1 ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Constant_1 ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Add ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Sqrt ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Div ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Mul ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Add_1 ...
2025-07-22 08:09:49,586 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_1 ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_1 ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_1 ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_2 ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_2 ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_2 ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_3 ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Div ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Cast ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Cast_1 ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_1 ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_4 ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_2 ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_5 ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Concat ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Reshape ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape ...
2025-07-22 08:09:49,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Cast ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Range ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Einsum ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Cos ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Sin ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:49,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Equal ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Where ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:49,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Add ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Div ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Neg ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:49,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:49,596 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:49,597 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_3 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_4 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_5 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose_1 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose_2 ...
2025-07-22 08:09:49,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/MatMul ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/MatMul ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_6 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Div_1 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Add ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Softmax ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/MatMul_1 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/MatMul_1 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose_3 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_3 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_7 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_6 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_4 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_8 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_7 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_5 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_9 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_8 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_6 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_10 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_9 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_11 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Mul ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Mul_1 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_3 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_4 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_5 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Concat_1 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Reshape_1 ...
2025-07-22 08:09:49,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/out_proj/MatMul ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/out_proj/MatMul ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/Add ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/Cast ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/ReduceMean ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Sub ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Constant ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Pow ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/ReduceMean_1 ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Constant_1 ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Add ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Sqrt ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Div ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Mul ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Add_1 ...
2025-07-22 08:09:49,603 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/mlp/fc11/MatMul ...
2025-07-22 08:09:49,610 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/mlp/fc11/MatMul ...
2025-07-22 08:09:49,610 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/mlp/fc12/MatMul ...
2025-07-22 08:09:49,616 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/mlp/fc12/MatMul ...
2025-07-22 08:09:49,616 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/mlp/Sigmoid ...
2025-07-22 08:09:49,616 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/mlp/Mul ...
2025-07-22 08:09:49,616 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/mlp/Mul_1 ...
2025-07-22 08:09:49,616 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/mlp/fc2/MatMul ...
2025-07-22 08:09:49,622 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/mlp/fc2/MatMul ...
2025-07-22 08:09:49,622 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/Add_1 ...
2025-07-22 08:09:49,622 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/Cast_1 ...
2025-07-22 08:09:49,622 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/ReduceMean ...
2025-07-22 08:09:49,622 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Sub ...
2025-07-22 08:09:49,622 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Constant ...
2025-07-22 08:09:49,623 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Pow ...
2025-07-22 08:09:49,623 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/ReduceMean_1 ...
2025-07-22 08:09:49,623 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Constant_1 ...
2025-07-22 08:09:49,623 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Add ...
2025-07-22 08:09:49,623 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Sqrt ...
2025-07-22 08:09:49,623 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Div ...
2025-07-22 08:09:49,623 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Mul ...
2025-07-22 08:09:49,623 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Add_1 ...
2025-07-22 08:09:49,623 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape ...
2025-07-22 08:09:49,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_1 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_1 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_1 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_2 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_2 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_2 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_3 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Div ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Cast ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Cast_1 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_1 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_4 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_2 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_5 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Concat ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Reshape ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Cast ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Range ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Einsum ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Cos ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Sin ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:49,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Equal ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Where ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand ...
2025-07-22 08:09:49,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:49,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Add ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Div ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Neg ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:49,632 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:49,633 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:49,634 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_3 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_4 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_5 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose_1 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose_2 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/MatMul ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/MatMul ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_6 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Div_1 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Add ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Softmax ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/MatMul_1 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/MatMul_1 ...
2025-07-22 08:09:49,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose_3 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_3 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_7 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_6 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_4 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_8 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_7 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_5 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_9 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_8 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_6 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_10 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_9 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_11 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Mul ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Mul_1 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_3 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_4 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_5 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Concat_1 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Reshape_1 ...
2025-07-22 08:09:49,636 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/out_proj/MatMul ...
2025-07-22 08:09:49,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/out_proj/MatMul ...
2025-07-22 08:09:49,639 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/Add ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/Cast ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/ReduceMean ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Sub ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Constant ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Pow ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/ReduceMean_1 ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Constant_1 ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Add ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Sqrt ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Div ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Mul ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Add_1 ...
2025-07-22 08:09:49,640 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/mlp/fc11/MatMul ...
2025-07-22 08:09:49,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/mlp/fc11/MatMul ...
2025-07-22 08:09:49,646 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/mlp/fc12/MatMul ...
2025-07-22 08:09:49,653 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/mlp/fc12/MatMul ...
2025-07-22 08:09:49,653 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/mlp/Sigmoid ...
2025-07-22 08:09:49,653 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/mlp/Mul ...
2025-07-22 08:09:49,653 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/mlp/Mul_1 ...
2025-07-22 08:09:49,653 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/mlp/fc2/MatMul ...
2025-07-22 08:09:49,659 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/mlp/fc2/MatMul ...
2025-07-22 08:09:49,659 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/Add_1 ...
2025-07-22 08:09:49,659 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/Cast_1 ...
2025-07-22 08:09:49,659 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/ReduceMean ...
2025-07-22 08:09:49,659 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Sub ...
2025-07-22 08:09:49,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Constant ...
2025-07-22 08:09:49,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Pow ...
2025-07-22 08:09:49,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/ReduceMean_1 ...
2025-07-22 08:09:49,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Constant_1 ...
2025-07-22 08:09:49,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Add ...
2025-07-22 08:09:49,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Sqrt ...
2025-07-22 08:09:49,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Div ...
2025-07-22 08:09:49,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Mul ...
2025-07-22 08:09:49,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Add_1 ...
2025-07-22 08:09:49,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_1 ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_1 ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_1 ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_2 ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_2 ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_2 ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_3 ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Div ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Cast ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Cast_1 ...
2025-07-22 08:09:49,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_1 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_4 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_2 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_5 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Concat ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Reshape ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Cast ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Range ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Einsum ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Cos ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Sin ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:49,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Equal ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Where ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:49,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Add ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Div ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:49,668 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Neg ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:49,669 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:49,670 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:49,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_3 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_4 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_5 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose_1 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose_2 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/MatMul ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/MatMul ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_6 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Div_1 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Add ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Softmax ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/MatMul_1 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/MatMul_1 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose_3 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_3 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_7 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_6 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_4 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_8 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_7 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_5 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_9 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_8 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_6 ...
2025-07-22 08:09:49,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_10 ...
2025-07-22 08:09:49,673 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_9 ...
2025-07-22 08:09:49,673 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_11 ...
2025-07-22 08:09:49,673 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Mul ...
2025-07-22 08:09:49,673 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Mul_1 ...
2025-07-22 08:09:49,673 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_3 ...
2025-07-22 08:09:49,673 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_4 ...
2025-07-22 08:09:49,673 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_5 ...
2025-07-22 08:09:49,673 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Concat_1 ...
2025-07-22 08:09:49,673 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Reshape_1 ...
2025-07-22 08:09:49,673 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/out_proj/MatMul ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/out_proj/MatMul ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/Add ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/Cast ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/ReduceMean ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Sub ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Constant ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Pow ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/ReduceMean_1 ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Constant_1 ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Add ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Sqrt ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Div ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Mul ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Add_1 ...
2025-07-22 08:09:49,676 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/mlp/fc11/MatMul ...
2025-07-22 08:09:49,683 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/mlp/fc11/MatMul ...
2025-07-22 08:09:49,683 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/mlp/fc12/MatMul ...
2025-07-22 08:09:49,689 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/mlp/fc12/MatMul ...
2025-07-22 08:09:49,689 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/mlp/Sigmoid ...
2025-07-22 08:09:49,689 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/mlp/Mul ...
2025-07-22 08:09:49,689 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/mlp/Mul_1 ...
2025-07-22 08:09:49,689 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/mlp/fc2/MatMul ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/mlp/fc2/MatMul ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/Add_1 ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/Cast_1 ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/ReduceMean ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Sub ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Constant ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Pow ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/ReduceMean_1 ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Constant_1 ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Add ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Sqrt ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Div ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Mul ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Add_1 ...
2025-07-22 08:09:49,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_1 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_1 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_1 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_2 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_2 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_2 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_3 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Div ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Cast ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Cast_1 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_1 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_4 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_2 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_5 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Concat ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Reshape ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Cast ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Range ...
2025-07-22 08:09:49,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Einsum ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Cos ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Sin ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:49,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Equal ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Where ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:49,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Add ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Div ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Neg ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:49,705 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:49,706 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:49,707 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_3 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_4 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_5 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose_1 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose_2 ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/MatMul ...
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/MatMul ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_6 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Div_1 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Add ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Softmax ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/MatMul_1 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/MatMul_1 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose_3 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_3 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_7 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_6 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_4 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_8 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_7 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_5 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_9 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_8 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_6 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_10 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_9 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_11 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Mul ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Mul_1 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_3 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_4 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_5 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Concat_1 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Reshape_1 ...
2025-07-22 08:09:49,709 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/out_proj/MatMul ...
2025-07-22 08:09:49,713 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/out_proj/MatMul ...
2025-07-22 08:09:49,713 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/Add ...
2025-07-22 08:09:49,713 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/Cast ...
2025-07-22 08:09:49,713 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/ReduceMean ...
2025-07-22 08:09:49,713 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Sub ...
2025-07-22 08:09:49,713 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Constant ...
2025-07-22 08:09:49,713 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Pow ...
2025-07-22 08:09:49,713 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/ReduceMean_1 ...
2025-07-22 08:09:49,713 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Constant_1 ...
2025-07-22 08:09:49,713 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Add ...
2025-07-22 08:09:49,713 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Sqrt ...
2025-07-22 08:09:49,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Div ...
2025-07-22 08:09:49,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Mul ...
2025-07-22 08:09:49,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Add_1 ...
2025-07-22 08:09:49,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/mlp/fc11/MatMul ...
2025-07-22 08:09:49,720 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/mlp/fc11/MatMul ...
2025-07-22 08:09:49,720 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/mlp/fc12/MatMul ...
2025-07-22 08:09:49,726 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/mlp/fc12/MatMul ...
2025-07-22 08:09:49,726 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/mlp/Sigmoid ...
2025-07-22 08:09:49,726 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/mlp/Mul ...
2025-07-22 08:09:49,726 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/mlp/Mul_1 ...
2025-07-22 08:09:49,726 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/mlp/fc2/MatMul ...
2025-07-22 08:09:49,732 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/mlp/fc2/MatMul ...
2025-07-22 08:09:49,732 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/Add_1 ...
2025-07-22 08:09:49,732 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/Cast_1 ...
2025-07-22 08:09:49,732 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/ReduceMean ...
2025-07-22 08:09:49,732 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Sub ...
2025-07-22 08:09:49,732 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Constant ...
2025-07-22 08:09:49,732 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Pow ...
2025-07-22 08:09:49,732 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/ReduceMean_1 ...
2025-07-22 08:09:49,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Constant_1 ...
2025-07-22 08:09:49,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Add ...
2025-07-22 08:09:49,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Sqrt ...
2025-07-22 08:09:49,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Div ...
2025-07-22 08:09:49,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Mul ...
2025-07-22 08:09:49,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Add_1 ...
2025-07-22 08:09:49,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape ...
2025-07-22 08:09:49,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant ...
2025-07-22 08:09:49,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather ...
2025-07-22 08:09:49,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_1 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_1 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_1 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_2 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_2 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_2 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_3 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Div ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Cast ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Cast_1 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_1 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_4 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_2 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_5 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Concat ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Reshape ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Cast ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Range ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Einsum ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Cos ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Sin ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:49,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Equal ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Where ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat ...
2025-07-22 08:09:49,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:49,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Add ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Div ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Neg ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:49,742 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:49,743 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:49,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_3 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_4 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_5 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose_1 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose_2 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/MatMul ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/MatMul ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_6 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Div_1 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Add ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Softmax ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/MatMul_1 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/MatMul_1 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose_3 ...
2025-07-22 08:09:49,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_3 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_7 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_6 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_4 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_8 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_7 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_5 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_9 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_8 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_6 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_10 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_9 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_11 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Mul ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Mul_1 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_3 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_4 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_5 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Concat_1 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Reshape_1 ...
2025-07-22 08:09:49,746 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/out_proj/MatMul ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/out_proj/MatMul ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/Add ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/Cast ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/ReduceMean ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Sub ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Constant ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Pow ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/ReduceMean_1 ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Constant_1 ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Add ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Sqrt ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Div ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Mul ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Add_1 ...
2025-07-22 08:09:49,750 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/mlp/fc11/MatMul ...
2025-07-22 08:09:49,756 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/mlp/fc11/MatMul ...
2025-07-22 08:09:49,756 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/mlp/fc12/MatMul ...
2025-07-22 08:09:49,763 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/mlp/fc12/MatMul ...
2025-07-22 08:09:49,763 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/mlp/Sigmoid ...
2025-07-22 08:09:49,763 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/mlp/Mul ...
2025-07-22 08:09:49,763 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/mlp/Mul_1 ...
2025-07-22 08:09:49,763 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/mlp/fc2/MatMul ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/mlp/fc2/MatMul ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/Add_1 ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/Cast_1 ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/ReduceMean ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Sub ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Constant ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Pow ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/ReduceMean_1 ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Constant_1 ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Add ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Sqrt ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Div ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Mul ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Add_1 ...
2025-07-22 08:09:49,769 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/Wqkv/MatMul ...
2025-07-22 08:09:49,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape ...
2025-07-22 08:09:49,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant ...
2025-07-22 08:09:49,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather ...
2025-07-22 08:09:49,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_1 ...
2025-07-22 08:09:49,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_1 ...
2025-07-22 08:09:49,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_1 ...
2025-07-22 08:09:49,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_2 ...
2025-07-22 08:09:49,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_2 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_2 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_3 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Div ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Cast ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Cast_1 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_1 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_4 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_2 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_5 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Concat ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Reshape ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Cast ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Range ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Einsum ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Cos ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Sin ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:49,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Equal ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Where ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape ...
2025-07-22 08:09:49,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:49,778 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Add ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Div ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Neg ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:49,779 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:49,780 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:49,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_3 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_4 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_5 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose_1 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose_2 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/MatMul ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/MatMul ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_6 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Div_1 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Add ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Softmax ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/MatMul_1 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/MatMul_1 ...
2025-07-22 08:09:49,782 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose_3 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_3 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_7 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_6 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_4 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_8 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_7 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_5 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_9 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_8 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_6 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_10 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_9 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_11 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Mul ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Mul_1 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_3 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_4 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_5 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Concat_1 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Reshape_1 ...
2025-07-22 08:09:49,783 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/out_proj/MatMul ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/out_proj/MatMul ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/Add ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/Cast ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/ReduceMean ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Sub ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Constant ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Pow ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/ReduceMean_1 ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Constant_1 ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Add ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Sqrt ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Div ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Mul ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Add_1 ...
2025-07-22 08:09:49,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/mlp/fc11/MatMul ...
2025-07-22 08:09:49,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/mlp/fc11/MatMul ...
2025-07-22 08:09:49,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/mlp/fc12/MatMul ...
2025-07-22 08:09:49,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/mlp/fc12/MatMul ...
2025-07-22 08:09:49,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/mlp/Sigmoid ...
2025-07-22 08:09:49,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/mlp/Mul ...
2025-07-22 08:09:49,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/mlp/Mul_1 ...
2025-07-22 08:09:49,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/mlp/fc2/MatMul ...
2025-07-22 08:09:49,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/mlp/fc2/MatMul ...
2025-07-22 08:09:49,806 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/Add_1 ...
2025-07-22 08:09:49,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/Cast_1 ...
2025-07-22 08:09:49,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/ReduceMean ...
2025-07-22 08:09:49,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Sub ...
2025-07-22 08:09:49,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Constant ...
2025-07-22 08:09:49,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Pow ...
2025-07-22 08:09:49,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/ReduceMean_1 ...
2025-07-22 08:09:49,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Constant_1 ...
2025-07-22 08:09:49,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Add ...
2025-07-22 08:09:49,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Sqrt ...
2025-07-22 08:09:49,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Div ...
2025-07-22 08:09:49,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Mul ...
2025-07-22 08:09:49,807 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Add_1 ...


 - Quantizing to q4:  60%|██████    | 3/5 [00:10<00:05,  2.96s/it]

 - Quantizing to q4f16:  60%|██████    | 3/5 [00:10<00:05,  2.96s/it]2025-07-22 08:09:50,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/word_embeddings/Gather ...
2025-07-22 08:09:50,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/token_type_embeddings/Gather ...
2025-07-22 08:09:50,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/Constant ...
2025-07-22 08:09:50,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /embeddings/Add ...
2025-07-22 08:09:50,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/ReduceMean ...
2025-07-22 08:09:50,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Sub ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Constant ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Pow ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/ReduceMean_1 ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Constant_1 ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Add ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Sqrt ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Div ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Mul ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /emb_ln/Add_1 ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Constant ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Constant_1 ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_1 ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Cast ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Constant_2 ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Sub ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Constant_3 ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Mul ...
2025-07-22 08:09:50,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,368 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,368 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape ...
2025-07-22 08:09:50,368 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant ...
2025-07-22 08:09:50,368 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather ...
2025-07-22 08:09:50,368 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_1 ...
2025-07-22 08:09:50,368 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_1 ...
2025-07-22 08:09:50,368 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_1 ...
2025-07-22 08:09:50,368 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_2 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_2 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_2 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_3 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Div ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Cast ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Cast_1 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_1 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_4 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_2 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_5 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Concat ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Reshape ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Cast ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Range ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Einsum ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Cos ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Sin ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul ...
2025-07-22 08:09:50,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Equal ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Where ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:50,370 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:50,371 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Add ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Div ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Neg ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:50,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:50,373 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:50,374 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Constant_75 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_3 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_4 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_5 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose_1 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose_2 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/MatMul ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/MatMul ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_6 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Div_1 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Add ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Softmax ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/MatMul_1 ...
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/MatMul_1 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Transpose_3 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_3 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_7 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_6 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_4 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_8 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_7 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_5 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_9 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_8 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Shape_6 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_10 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Gather_9 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Constant_11 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Mul ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Mul_1 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_3 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_4 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Unsqueeze_5 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Concat_1 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/attn/Reshape_1 ...
2025-07-22 08:09:50,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/attn/out_proj/MatMul ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/attn/out_proj/MatMul ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/Add ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/Cast ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/ReduceMean ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Sub ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Constant ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Pow ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/ReduceMean_1 ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Constant_1 ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Add ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Sqrt ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Div ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Mul ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm1/Add_1 ...
2025-07-22 08:09:50,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/mlp/fc11/MatMul ...
2025-07-22 08:09:50,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/mlp/fc11/MatMul ...
2025-07-22 08:09:50,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/mlp/fc12/MatMul ...
2025-07-22 08:09:50,393 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/mlp/fc12/MatMul ...
2025-07-22 08:09:50,393 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/mlp/Sigmoid ...
2025-07-22 08:09:50,393 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/mlp/Mul ...
2025-07-22 08:09:50,393 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/mlp/Mul_1 ...
2025-07-22 08:09:50,393 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.0/mlp/fc2/MatMul ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.0/mlp/fc2/MatMul ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/Add_1 ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/Cast_1 ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/ReduceMean ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Sub ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Constant ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Pow ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/ReduceMean_1 ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Constant_1 ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Add ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Sqrt ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Div ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Mul ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.0/norm2/Add_1 ...
2025-07-22 08:09:50,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_1 ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_1 ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_1 ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_2 ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_2 ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_2 ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_3 ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Div ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Cast ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Cast_1 ...
2025-07-22 08:09:50,405 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_1 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_4 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_2 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_5 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Concat ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Reshape ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Cast ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Range ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Einsum ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Cos ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Sin ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:50,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Equal ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Where ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:50,407 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Add ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Div ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:50,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Neg ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:50,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:50,410 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:50,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_3 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_4 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_5 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose_1 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose_2 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/MatMul ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/MatMul ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_6 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Div_1 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Add ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Softmax ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/MatMul_1 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/MatMul_1 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Transpose_3 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_3 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_7 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_6 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_4 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_8 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_7 ...
2025-07-22 08:09:50,412 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_5 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_9 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_8 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Shape_6 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_10 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Gather_9 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Constant_11 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Mul ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Mul_1 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_3 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_4 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Unsqueeze_5 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Concat_1 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/attn/Reshape_1 ...
2025-07-22 08:09:50,413 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/attn/out_proj/MatMul ...
2025-07-22 08:09:50,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/attn/out_proj/MatMul ...
2025-07-22 08:09:50,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/Add ...
2025-07-22 08:09:50,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/Cast ...
2025-07-22 08:09:50,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/ReduceMean ...
2025-07-22 08:09:50,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Sub ...
2025-07-22 08:09:50,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Constant ...
2025-07-22 08:09:50,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Pow ...
2025-07-22 08:09:50,416 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/ReduceMean_1 ...
2025-07-22 08:09:50,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Constant_1 ...
2025-07-22 08:09:50,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Add ...
2025-07-22 08:09:50,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Sqrt ...
2025-07-22 08:09:50,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Div ...
2025-07-22 08:09:50,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Mul ...
2025-07-22 08:09:50,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm1/Add_1 ...
2025-07-22 08:09:50,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/mlp/fc11/MatMul ...
2025-07-22 08:09:50,423 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/mlp/fc11/MatMul ...
2025-07-22 08:09:50,423 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/mlp/fc12/MatMul ...
2025-07-22 08:09:50,429 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/mlp/fc12/MatMul ...
2025-07-22 08:09:50,429 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/mlp/Sigmoid ...
2025-07-22 08:09:50,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/mlp/Mul ...
2025-07-22 08:09:50,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/mlp/Mul_1 ...
2025-07-22 08:09:50,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.1/mlp/fc2/MatMul ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.1/mlp/fc2/MatMul ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/Add_1 ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/Cast_1 ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/ReduceMean ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Sub ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Constant ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Pow ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/ReduceMean_1 ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Constant_1 ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Add ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Sqrt ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Div ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Mul ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.1/norm2/Add_1 ...
2025-07-22 08:09:50,436 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_1 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_1 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_1 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_2 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_2 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_2 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_3 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Div ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Cast ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Cast_1 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_1 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_4 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_2 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_5 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Concat ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Reshape ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Cast ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Range ...
2025-07-22 08:09:50,442 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Einsum ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Cos ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Sin ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:50,443 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Equal ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Where ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:50,444 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Add ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Div ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Neg ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:50,445 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:50,446 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:50,447 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_3 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_4 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_5 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose_1 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose_2 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/MatMul ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/MatMul ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_6 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Div_1 ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Add ...
2025-07-22 08:09:50,448 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Softmax ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/MatMul_1 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/MatMul_1 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Transpose_3 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_3 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_7 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_6 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_4 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_8 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_7 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_5 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_9 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_8 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Shape_6 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_10 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Gather_9 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Constant_11 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Mul ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Mul_1 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_3 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_4 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Unsqueeze_5 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Concat_1 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/attn/Reshape_1 ...
2025-07-22 08:09:50,449 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/attn/out_proj/MatMul ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/attn/out_proj/MatMul ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/Add ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/Cast ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/ReduceMean ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Sub ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Constant ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Pow ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/ReduceMean_1 ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Constant_1 ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Add ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Sqrt ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Div ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Mul ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm1/Add_1 ...
2025-07-22 08:09:50,453 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/mlp/fc11/MatMul ...
2025-07-22 08:09:50,459 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/mlp/fc11/MatMul ...
2025-07-22 08:09:50,459 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/mlp/fc12/MatMul ...
2025-07-22 08:09:50,466 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/mlp/fc12/MatMul ...
2025-07-22 08:09:50,466 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/mlp/Sigmoid ...
2025-07-22 08:09:50,466 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/mlp/Mul ...
2025-07-22 08:09:50,466 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/mlp/Mul_1 ...
2025-07-22 08:09:50,466 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.2/mlp/fc2/MatMul ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.2/mlp/fc2/MatMul ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/Add_1 ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/Cast_1 ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/ReduceMean ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Sub ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Constant ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Pow ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/ReduceMean_1 ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Constant_1 ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Add ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Sqrt ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Div ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Mul ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.2/norm2/Add_1 ...
2025-07-22 08:09:50,472 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_1 ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_1 ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_1 ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_2 ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_2 ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_2 ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_3 ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Div ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Cast ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Cast_1 ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_1 ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_4 ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_2 ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_5 ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Concat ...
2025-07-22 08:09:50,478 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Reshape ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Cast ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Range ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Einsum ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Cos ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Sin ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:50,479 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Equal ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Where ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:50,480 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Add ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Div ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Neg ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:50,481 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:50,482 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:50,483 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_3 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_4 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_5 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose_1 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose_2 ...
2025-07-22 08:09:50,484 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/MatMul ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/MatMul ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_6 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Div_1 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Add ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Softmax ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/MatMul_1 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/MatMul_1 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Transpose_3 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_3 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_7 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_6 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_4 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_8 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_7 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_5 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_9 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_8 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Shape_6 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_10 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Gather_9 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Constant_11 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Mul ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Mul_1 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_3 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_4 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Unsqueeze_5 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Concat_1 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/attn/Reshape_1 ...
2025-07-22 08:09:50,485 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/attn/out_proj/MatMul ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/attn/out_proj/MatMul ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/Add ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/Cast ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/ReduceMean ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Sub ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Constant ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Pow ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/ReduceMean_1 ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Constant_1 ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Add ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Sqrt ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Div ...
2025-07-22 08:09:50,489 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Mul ...
2025-07-22 08:09:50,490 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm1/Add_1 ...
2025-07-22 08:09:50,490 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/mlp/fc11/MatMul ...
2025-07-22 08:09:50,496 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/mlp/fc11/MatMul ...
2025-07-22 08:09:50,496 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/mlp/fc12/MatMul ...
2025-07-22 08:09:50,502 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/mlp/fc12/MatMul ...
2025-07-22 08:09:50,502 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/mlp/Sigmoid ...
2025-07-22 08:09:50,502 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/mlp/Mul ...
2025-07-22 08:09:50,502 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/mlp/Mul_1 ...
2025-07-22 08:09:50,502 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.3/mlp/fc2/MatMul ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.3/mlp/fc2/MatMul ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/Add_1 ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/Cast_1 ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/ReduceMean ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Sub ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Constant ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Pow ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/ReduceMean_1 ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Constant_1 ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Add ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Sqrt ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Div ...
2025-07-22 08:09:50,508 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Mul ...
2025-07-22 08:09:50,509 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.3/norm2/Add_1 ...
2025-07-22 08:09:50,509 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_1 ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_1 ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_1 ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_2 ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_2 ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_2 ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_3 ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Div ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Cast ...
2025-07-22 08:09:50,514 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Cast_1 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_1 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_4 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_2 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_5 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Concat ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Reshape ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Cast ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Range ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Einsum ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Cos ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Sin ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:50,515 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Equal ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Where ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:50,516 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Add ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Div ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Neg ...
2025-07-22 08:09:50,517 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:50,518 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:50,519 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:50,520 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_3 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_4 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_5 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose_1 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose_2 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/MatMul ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/MatMul ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_6 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Div_1 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Add ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Softmax ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/MatMul_1 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/MatMul_1 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Transpose_3 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_3 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_7 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_6 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_4 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_8 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_7 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_5 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_9 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_8 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Shape_6 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_10 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Gather_9 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Constant_11 ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Mul ...
2025-07-22 08:09:50,521 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Mul_1 ...
2025-07-22 08:09:50,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_3 ...
2025-07-22 08:09:50,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_4 ...
2025-07-22 08:09:50,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Unsqueeze_5 ...
2025-07-22 08:09:50,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Concat_1 ...
2025-07-22 08:09:50,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/attn/Reshape_1 ...
2025-07-22 08:09:50,522 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/attn/out_proj/MatMul ...
2025-07-22 08:09:50,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/attn/out_proj/MatMul ...
2025-07-22 08:09:50,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/Add ...
2025-07-22 08:09:50,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/Cast ...
2025-07-22 08:09:50,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/ReduceMean ...
2025-07-22 08:09:50,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Sub ...
2025-07-22 08:09:50,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Constant ...
2025-07-22 08:09:50,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Pow ...
2025-07-22 08:09:50,525 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/ReduceMean_1 ...
2025-07-22 08:09:50,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Constant_1 ...
2025-07-22 08:09:50,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Add ...
2025-07-22 08:09:50,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Sqrt ...
2025-07-22 08:09:50,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Div ...
2025-07-22 08:09:50,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Mul ...
2025-07-22 08:09:50,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm1/Add_1 ...
2025-07-22 08:09:50,526 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/mlp/fc11/MatMul ...
2025-07-22 08:09:50,532 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/mlp/fc11/MatMul ...
2025-07-22 08:09:50,532 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/mlp/fc12/MatMul ...
2025-07-22 08:09:50,538 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/mlp/fc12/MatMul ...
2025-07-22 08:09:50,538 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/mlp/Sigmoid ...
2025-07-22 08:09:50,538 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/mlp/Mul ...
2025-07-22 08:09:50,538 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/mlp/Mul_1 ...
2025-07-22 08:09:50,538 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.4/mlp/fc2/MatMul ...
2025-07-22 08:09:50,544 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.4/mlp/fc2/MatMul ...
2025-07-22 08:09:50,544 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/Add_1 ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/Cast_1 ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/ReduceMean ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Sub ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Constant ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Pow ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/ReduceMean_1 ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Constant_1 ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Add ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Sqrt ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Div ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Mul ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.4/norm2/Add_1 ...
2025-07-22 08:09:50,545 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,550 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,550 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape ...
2025-07-22 08:09:50,550 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant ...
2025-07-22 08:09:50,550 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_1 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_1 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_1 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_2 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_2 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_2 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_3 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Div ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Cast ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Cast_1 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_1 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_4 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_2 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_5 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Concat ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Reshape ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Cast ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Range ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Einsum ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Cos ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Sin ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:50,551 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Equal ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Where ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:50,552 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:50,553 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Add ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Div ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Neg ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:50,554 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:50,555 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:50,556 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_3 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_4 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_5 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose_1 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose_2 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/MatMul ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/MatMul ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_6 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Div_1 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Add ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Softmax ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/MatMul_1 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/MatMul_1 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Transpose_3 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_3 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_7 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_6 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_4 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_8 ...
2025-07-22 08:09:50,557 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_7 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_5 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_9 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_8 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Shape_6 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_10 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Gather_9 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Constant_11 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Mul ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Mul_1 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_3 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_4 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Unsqueeze_5 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Concat_1 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/attn/Reshape_1 ...
2025-07-22 08:09:50,558 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/attn/out_proj/MatMul ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/attn/out_proj/MatMul ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/Add ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/Cast ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/ReduceMean ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Sub ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Constant ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Pow ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/ReduceMean_1 ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Constant_1 ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Add ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Sqrt ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Div ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Mul ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm1/Add_1 ...
2025-07-22 08:09:50,562 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/mlp/fc11/MatMul ...
2025-07-22 08:09:50,568 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/mlp/fc11/MatMul ...
2025-07-22 08:09:50,568 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/mlp/fc12/MatMul ...
2025-07-22 08:09:50,574 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/mlp/fc12/MatMul ...
2025-07-22 08:09:50,575 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/mlp/Sigmoid ...
2025-07-22 08:09:50,575 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/mlp/Mul ...
2025-07-22 08:09:50,575 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/mlp/Mul_1 ...
2025-07-22 08:09:50,575 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.5/mlp/fc2/MatMul ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.5/mlp/fc2/MatMul ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/Add_1 ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/Cast_1 ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/ReduceMean ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Sub ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Constant ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Pow ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/ReduceMean_1 ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Constant_1 ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Add ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Sqrt ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Div ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Mul ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.5/norm2/Add_1 ...
2025-07-22 08:09:50,581 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_1 ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_1 ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_1 ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_2 ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_2 ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_2 ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_3 ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Div ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Cast ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Cast_1 ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_1 ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_4 ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_2 ...
2025-07-22 08:09:50,587 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_5 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Concat ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Reshape ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Cast ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Range ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Einsum ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Cos ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Sin ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:50,588 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Equal ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Where ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:50,589 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Add ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Div ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Neg ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:50,590 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:50,591 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:50,592 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_3 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_4 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_5 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose_1 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose_2 ...
2025-07-22 08:09:50,593 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/MatMul ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/MatMul ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_6 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Div_1 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Add ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Softmax ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/MatMul_1 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/MatMul_1 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Transpose_3 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_3 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_7 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_6 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_4 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_8 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_7 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_5 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_9 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_8 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Shape_6 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_10 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Gather_9 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Constant_11 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Mul ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Mul_1 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_3 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_4 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Unsqueeze_5 ...
2025-07-22 08:09:50,594 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Concat_1 ...
2025-07-22 08:09:50,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/attn/Reshape_1 ...
2025-07-22 08:09:50,595 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/attn/out_proj/MatMul ...
2025-07-22 08:09:50,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/attn/out_proj/MatMul ...
2025-07-22 08:09:50,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/Add ...
2025-07-22 08:09:50,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/Cast ...
2025-07-22 08:09:50,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/ReduceMean ...
2025-07-22 08:09:50,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Sub ...
2025-07-22 08:09:50,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Constant ...
2025-07-22 08:09:50,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Pow ...
2025-07-22 08:09:50,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/ReduceMean_1 ...
2025-07-22 08:09:50,598 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Constant_1 ...
2025-07-22 08:09:50,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Add ...
2025-07-22 08:09:50,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Sqrt ...
2025-07-22 08:09:50,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Div ...
2025-07-22 08:09:50,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Mul ...
2025-07-22 08:09:50,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm1/Add_1 ...
2025-07-22 08:09:50,599 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/mlp/fc11/MatMul ...
2025-07-22 08:09:50,605 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/mlp/fc11/MatMul ...
2025-07-22 08:09:50,605 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/mlp/fc12/MatMul ...
2025-07-22 08:09:50,611 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/mlp/fc12/MatMul ...
2025-07-22 08:09:50,611 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/mlp/Sigmoid ...
2025-07-22 08:09:50,611 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/mlp/Mul ...
2025-07-22 08:09:50,611 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/mlp/Mul_1 ...
2025-07-22 08:09:50,611 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.6/mlp/fc2/MatMul ...
2025-07-22 08:09:50,617 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.6/mlp/fc2/MatMul ...
2025-07-22 08:09:50,617 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/Add_1 ...
2025-07-22 08:09:50,617 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/Cast_1 ...
2025-07-22 08:09:50,617 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/ReduceMean ...
2025-07-22 08:09:50,617 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Sub ...
2025-07-22 08:09:50,617 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Constant ...
2025-07-22 08:09:50,618 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Pow ...
2025-07-22 08:09:50,618 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/ReduceMean_1 ...
2025-07-22 08:09:50,618 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Constant_1 ...
2025-07-22 08:09:50,618 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Add ...
2025-07-22 08:09:50,618 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Sqrt ...
2025-07-22 08:09:50,618 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Div ...
2025-07-22 08:09:50,618 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Mul ...
2025-07-22 08:09:50,618 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.6/norm2/Add_1 ...
2025-07-22 08:09:50,618 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,623 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_1 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_1 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_1 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_2 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_2 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_2 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_3 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Div ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Cast ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Cast_1 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_1 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_4 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_2 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_5 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Concat ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Reshape ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Cast ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Range ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Einsum ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Cos ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Sin ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:50,624 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Equal ...
2025-07-22 08:09:50,625 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Where ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:50,626 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Add ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Div ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Neg ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:50,627 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:50,628 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:50,629 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_3 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_4 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_5 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose_1 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose_2 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/MatMul ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/MatMul ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_6 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Div_1 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Add ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Softmax ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/MatMul_1 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/MatMul_1 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Transpose_3 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_3 ...
2025-07-22 08:09:50,630 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_7 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_6 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_4 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_8 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_7 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_5 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_9 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_8 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Shape_6 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_10 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Gather_9 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Constant_11 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Mul ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Mul_1 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_3 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_4 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Unsqueeze_5 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Concat_1 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/attn/Reshape_1 ...
2025-07-22 08:09:50,631 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/attn/out_proj/MatMul ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/attn/out_proj/MatMul ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/Add ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/Cast ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/ReduceMean ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Sub ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Constant ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Pow ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/ReduceMean_1 ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Constant_1 ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Add ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Sqrt ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Div ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Mul ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm1/Add_1 ...
2025-07-22 08:09:50,635 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/mlp/fc11/MatMul ...
2025-07-22 08:09:50,641 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/mlp/fc11/MatMul ...
2025-07-22 08:09:50,641 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/mlp/fc12/MatMul ...
2025-07-22 08:09:50,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/mlp/fc12/MatMul ...
2025-07-22 08:09:50,647 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/mlp/Sigmoid ...
2025-07-22 08:09:50,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/mlp/Mul ...
2025-07-22 08:09:50,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/mlp/Mul_1 ...
2025-07-22 08:09:50,648 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.7/mlp/fc2/MatMul ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.7/mlp/fc2/MatMul ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/Add_1 ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/Cast_1 ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/ReduceMean ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Sub ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Constant ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Pow ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/ReduceMean_1 ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Constant_1 ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Add ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Sqrt ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Div ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Mul ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.7/norm2/Add_1 ...
2025-07-22 08:09:50,654 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_1 ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_1 ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_1 ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_2 ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_2 ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_2 ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_3 ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Div ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Cast ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Cast_1 ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_1 ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_4 ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_2 ...
2025-07-22 08:09:50,660 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_5 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Concat ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Reshape ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Cast ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Range ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Einsum ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Cos ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Sin ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:50,661 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Equal ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Where ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:50,662 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Add ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Div ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Neg ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:50,663 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:50,664 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:50,665 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_3 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_4 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_5 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose_1 ...
2025-07-22 08:09:50,666 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose_2 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/MatMul ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/MatMul ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_6 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Div_1 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Add ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Softmax ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/MatMul_1 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/MatMul_1 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Transpose_3 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_3 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_7 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_6 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_4 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_8 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_7 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_5 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_9 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_8 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Shape_6 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_10 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Gather_9 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Constant_11 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Mul ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Mul_1 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_3 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_4 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Unsqueeze_5 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Concat_1 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/attn/Reshape_1 ...
2025-07-22 08:09:50,667 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/attn/out_proj/MatMul ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/attn/out_proj/MatMul ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/Add ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/Cast ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/ReduceMean ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Sub ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Constant ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Pow ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/ReduceMean_1 ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Constant_1 ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Add ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Sqrt ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Div ...
2025-07-22 08:09:50,671 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Mul ...
2025-07-22 08:09:50,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm1/Add_1 ...
2025-07-22 08:09:50,672 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/mlp/fc11/MatMul ...
2025-07-22 08:09:50,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/mlp/fc11/MatMul ...
2025-07-22 08:09:50,678 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/mlp/fc12/MatMul ...
2025-07-22 08:09:50,684 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/mlp/fc12/MatMul ...
2025-07-22 08:09:50,684 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/mlp/Sigmoid ...
2025-07-22 08:09:50,684 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/mlp/Mul ...
2025-07-22 08:09:50,684 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/mlp/Mul_1 ...
2025-07-22 08:09:50,684 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.8/mlp/fc2/MatMul ...
2025-07-22 08:09:50,690 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.8/mlp/fc2/MatMul ...
2025-07-22 08:09:50,690 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/Add_1 ...
2025-07-22 08:09:50,690 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/Cast_1 ...
2025-07-22 08:09:50,691 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/ReduceMean ...
2025-07-22 08:09:50,691 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Sub ...
2025-07-22 08:09:50,691 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Constant ...
2025-07-22 08:09:50,691 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Pow ...
2025-07-22 08:09:50,691 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/ReduceMean_1 ...
2025-07-22 08:09:50,691 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Constant_1 ...
2025-07-22 08:09:50,691 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Add ...
2025-07-22 08:09:50,691 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Sqrt ...
2025-07-22 08:09:50,691 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Div ...
2025-07-22 08:09:50,691 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Mul ...
2025-07-22 08:09:50,691 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.8/norm2/Add_1 ...
2025-07-22 08:09:50,691 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,696 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_1 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_1 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_1 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_2 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_2 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_2 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_3 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Div ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Cast ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Cast_1 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_1 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_4 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_2 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_5 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Concat ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Reshape ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Cast ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Range ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Einsum ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Cos ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Sin ...
2025-07-22 08:09:50,697 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Equal ...
2025-07-22 08:09:50,698 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Where ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:50,699 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Add ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Div ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Neg ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:50,700 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:50,701 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:50,702 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_3 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_4 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_5 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose_1 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose_2 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/MatMul ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/MatMul ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_6 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Div_1 ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Add ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Softmax ...
2025-07-22 08:09:50,703 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/MatMul_1 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/MatMul_1 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Transpose_3 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_3 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_7 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_6 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_4 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_8 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_7 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_5 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_9 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_8 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Shape_6 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_10 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Gather_9 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Constant_11 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Mul ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Mul_1 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_3 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_4 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Unsqueeze_5 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Concat_1 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/attn/Reshape_1 ...
2025-07-22 08:09:50,704 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/attn/out_proj/MatMul ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/attn/out_proj/MatMul ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/Add ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/Cast ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/ReduceMean ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Sub ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Constant ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Pow ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/ReduceMean_1 ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Constant_1 ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Add ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Sqrt ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Div ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Mul ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm1/Add_1 ...
2025-07-22 08:09:50,708 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/mlp/fc11/MatMul ...
2025-07-22 08:09:50,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/mlp/fc11/MatMul ...
2025-07-22 08:09:50,714 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/mlp/fc12/MatMul ...
2025-07-22 08:09:50,721 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/mlp/fc12/MatMul ...
2025-07-22 08:09:50,721 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/mlp/Sigmoid ...
2025-07-22 08:09:50,721 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/mlp/Mul ...
2025-07-22 08:09:50,721 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/mlp/Mul_1 ...
2025-07-22 08:09:50,721 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.9/mlp/fc2/MatMul ...
2025-07-22 08:09:50,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.9/mlp/fc2/MatMul ...
2025-07-22 08:09:50,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/Add_1 ...
2025-07-22 08:09:50,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/Cast_1 ...
2025-07-22 08:09:50,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/ReduceMean ...
2025-07-22 08:09:50,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Sub ...
2025-07-22 08:09:50,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Constant ...
2025-07-22 08:09:50,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Pow ...
2025-07-22 08:09:50,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/ReduceMean_1 ...
2025-07-22 08:09:50,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Constant_1 ...
2025-07-22 08:09:50,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Add ...
2025-07-22 08:09:50,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Sqrt ...
2025-07-22 08:09:50,727 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Div ...
2025-07-22 08:09:50,728 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Mul ...
2025-07-22 08:09:50,728 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.9/norm2/Add_1 ...
2025-07-22 08:09:50,728 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape ...
2025-07-22 08:09:50,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant ...
2025-07-22 08:09:50,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather ...
2025-07-22 08:09:50,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_1 ...
2025-07-22 08:09:50,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_1 ...
2025-07-22 08:09:50,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_1 ...
2025-07-22 08:09:50,733 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_2 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_2 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_2 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_3 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Div ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Cast ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Cast_1 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_1 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_4 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_2 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_5 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Concat ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Reshape ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Cast ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Range ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Einsum ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Cos ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Sin ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:50,734 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Equal ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Where ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:50,735 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Add ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Div ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:50,736 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Neg ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:50,737 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:50,738 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:50,739 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_3 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_4 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_5 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose_1 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose_2 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/MatMul ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/MatMul ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_6 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Div_1 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Add ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Softmax ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/MatMul_1 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/MatMul_1 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Transpose_3 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_3 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_7 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_6 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_4 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_8 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_7 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_5 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_9 ...
2025-07-22 08:09:50,740 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_8 ...
2025-07-22 08:09:50,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Shape_6 ...
2025-07-22 08:09:50,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_10 ...
2025-07-22 08:09:50,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Gather_9 ...
2025-07-22 08:09:50,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Constant_11 ...
2025-07-22 08:09:50,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Mul ...
2025-07-22 08:09:50,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Mul_1 ...
2025-07-22 08:09:50,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_3 ...
2025-07-22 08:09:50,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_4 ...
2025-07-22 08:09:50,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Unsqueeze_5 ...
2025-07-22 08:09:50,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Concat_1 ...
2025-07-22 08:09:50,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/attn/Reshape_1 ...
2025-07-22 08:09:50,741 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/attn/out_proj/MatMul ...
2025-07-22 08:09:50,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/attn/out_proj/MatMul ...
2025-07-22 08:09:50,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/Add ...
2025-07-22 08:09:50,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/Cast ...
2025-07-22 08:09:50,744 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/ReduceMean ...
2025-07-22 08:09:50,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Sub ...
2025-07-22 08:09:50,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Constant ...
2025-07-22 08:09:50,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Pow ...
2025-07-22 08:09:50,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/ReduceMean_1 ...
2025-07-22 08:09:50,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Constant_1 ...
2025-07-22 08:09:50,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Add ...
2025-07-22 08:09:50,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Sqrt ...
2025-07-22 08:09:50,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Div ...
2025-07-22 08:09:50,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Mul ...
2025-07-22 08:09:50,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm1/Add_1 ...
2025-07-22 08:09:50,745 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/mlp/fc11/MatMul ...
2025-07-22 08:09:50,751 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/mlp/fc11/MatMul ...
2025-07-22 08:09:50,751 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/mlp/fc12/MatMul ...
2025-07-22 08:09:50,757 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/mlp/fc12/MatMul ...
2025-07-22 08:09:50,757 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/mlp/Sigmoid ...
2025-07-22 08:09:50,757 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/mlp/Mul ...
2025-07-22 08:09:50,757 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/mlp/Mul_1 ...
2025-07-22 08:09:50,758 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.10/mlp/fc2/MatMul ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.10/mlp/fc2/MatMul ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/Add_1 ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/Cast_1 ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/ReduceMean ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Sub ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Constant ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Pow ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/ReduceMean_1 ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Constant_1 ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Add ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Sqrt ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Div ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Mul ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.10/norm2/Add_1 ...
2025-07-22 08:09:50,764 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/Wqkv/MatMul ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_1 ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_1 ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_1 ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_2 ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_2 ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_2 ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_3 ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Div ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Cast ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Cast_1 ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_1 ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_4 ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_2 ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_5 ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Concat ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Reshape ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Cast ...
2025-07-22 08:09:50,770 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_1 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_2 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Range ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Einsum ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Cos ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Cast_1 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Sin ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Cast_2 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_1 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_1 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_3 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_2 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_4 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_2 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_5 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_3 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_6 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_7 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_8 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_9 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_10 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_1 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_11 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_1 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_3 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_12 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_4 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_4 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_13 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_5 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_14 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_1 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_2 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_15 ...
2025-07-22 08:09:50,771 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_16 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/ConstantOfShape ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_17 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_2 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_18 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Equal ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Where ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_3 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_19 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_4 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_5 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_20 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_6 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_6 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_21 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_7 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_22 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_3 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_5 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_23 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_24 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/ConstantOfShape_1 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_25 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_4 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_26 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Equal_1 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Where_1 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand_1 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_6 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_27 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_7 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_1 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape_1 ...
2025-07-22 08:09:50,772 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_28 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_29 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_8 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_30 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_2 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_5 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_7 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_31 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_8 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_32 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_33 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Add ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_34 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Div ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_35 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_6 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_3 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_36 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_7 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_4 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Neg ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_2 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_8 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Add_1 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_37 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_9 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_38 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_39 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_5 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_3 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_9 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_8 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_40 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_10 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_41 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_42 ...
2025-07-22 08:09:50,773 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_10 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_43 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_6 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_44 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_45 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_11 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_46 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_7 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_9 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_47 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_11 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_10 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_48 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_12 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_49 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_9 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_12 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_50 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_51 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/ConstantOfShape_2 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_52 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_10 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_53 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Equal_2 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Where_2 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand_2 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_13 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_54 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_14 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_4 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape_2 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_11 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_55 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_13 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_12 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_56 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_14 ...
2025-07-22 08:09:50,774 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_57 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_11 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_15 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_58 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_59 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/ConstantOfShape_3 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_60 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_12 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_61 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Equal_3 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Where_3 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Expand_3 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_16 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_62 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_17 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_5 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Reshape_3 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_63 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_64 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_18 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_65 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_8 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_13 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Shape_13 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_66 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_15 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_67 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_68 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Add_2 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_69 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Div_1 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_70 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_14 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_9 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_71 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_15 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_10 ...
2025-07-22 08:09:50,775 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Neg_1 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_6 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Mul_16 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Add_3 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_72 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_19 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_73 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Constant_74 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Slice_11 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_7 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Gather_16 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_20 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_21 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Unsqueeze_22 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/rotary_emb/Concat_8 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_3 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_4 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_5 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose_1 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose_2 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/MatMul ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/MatMul ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_6 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Div_1 ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Add ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Softmax ...
2025-07-22 08:09:50,776 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/MatMul_1 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/MatMul_1 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Transpose_3 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_3 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_7 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_6 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_4 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_8 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_7 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_5 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_9 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_8 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Shape_6 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_10 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Gather_9 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Constant_11 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Mul ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Mul_1 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_3 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_4 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Unsqueeze_5 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Concat_1 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/attn/Reshape_1 ...
2025-07-22 08:09:50,777 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/attn/out_proj/MatMul ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/attn/out_proj/MatMul ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/Add ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/Cast ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/ReduceMean ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Sub ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Constant ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Pow ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/ReduceMean_1 ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Constant_1 ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Add ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Sqrt ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Div ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Mul ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm1/Add_1 ...
2025-07-22 08:09:50,781 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/mlp/fc11/MatMul ...
2025-07-22 08:09:50,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/mlp/fc11/MatMul ...
2025-07-22 08:09:50,787 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/mlp/fc12/MatMul ...
2025-07-22 08:09:50,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/mlp/fc12/MatMul ...
2025-07-22 08:09:50,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/mlp/Sigmoid ...
2025-07-22 08:09:50,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/mlp/Mul ...
2025-07-22 08:09:50,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/mlp/Mul_1 ...
2025-07-22 08:09:50,794 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /encoder/layers.11/mlp/fc2/MatMul ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /encoder/layers.11/mlp/fc2/MatMul ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/Add_1 ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/Cast_1 ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/ReduceMean ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Sub ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Constant ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Pow ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/ReduceMean_1 ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Constant_1 ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Add ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Sqrt ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Div ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Mul ...
2025-07-22 08:09:50,800 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /encoder/layers.11/norm2/Add_1 ...
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 9.999999960041972e-13 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:85: UserWarning: the float32 number -3.4028234663852886e+38 will be truncated to -10000.0
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.2307730834493213e-08 will be truncated to 1e-07
  warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.2338328136962673e-09 will be truncated to -1e-07
  warnings.warn(

 - Quantizing to q4f16:  60%|██████    | 3/5 [00:12<00:08,  4.18s/it]

Processing /tmp/tmppds0d9jk/model.onnx:   0%|          | 0/1 [00:12<?, ?it/s]
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 377, in <module>
    main()
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 374, in main
    quantize(input_folder, output_folder, quantization_args)
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 326, in quantize
    quantize_fp16(
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 223, in quantize_fp16
    check_and_save_model(model_fp16, save_path)
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/utils.py", line 29, in check_and_save_model
    strict_check_model(model)
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/utils.py", line 21, in strict_check_model
    raise e
  File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/utils.py", line 16, in strict_check_model
    onnx.checker.check_model(model_or_path, full_check=True)
  File "/home/ubuntu/.cache/uv/archive-v0/iAncxVR1WPOl_8LkA6LpD/lib/python3.12/site-packages/onnx/checker.py", line 179, in check_model
    C.check_model(
onnx.onnx_cpp2py_export.shape_inference.InferenceError: [ShapeInferenceError] (op_type:Range, node name: /encoder/layers.0/attn/rotary_emb/Range): start typestr: T, has unsupported type: tensor(float16)
Add/update the quantized ONNX model files and README.md for Transformers.js v33a2fd95a
Xenova changed pull request status to merged

Sign up or log in to comment