Add/update the quantized ONNX model files and README.md for Transformers.js v3
#2
by
whitphx
HF Staff
- opened
Applied Quantizations
β Based on model.onnx
with slimming
0%| | 0/1 [00:00<?, ?it/s]
Processing /tmp/tmpjajl2j8i/model.onnx: 0%| | 0/1 [00:00<?, ?it/s]
0%| | 0/1 [00:00<?, ?it/s][A
- Quantizing to q4f16: 0%| | 0/1 [00:00<?, ?it/s][A2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_1 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Mod ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Mod_2 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Mul_186 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Mul_187 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Sub ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Sub_1 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_191 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_192 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Mod_1 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Mod_3 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_2 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_3 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_1 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_2 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Transpose ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_1 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Pad ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Sub_3 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /conv_first/Conv ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_3 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_3 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_4 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_1 ...
2025-07-07 02:20:43,103 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_3 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_142 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_143 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Div ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Div_1 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Mul_1 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Div_8 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Div_9 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_2 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_80 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Cast_6 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Unsqueeze_31 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Unsqueeze_5 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Unsqueeze_6 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Unsqueeze_16 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Unsqueeze_17 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Transpose_1 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ConstantOfShape_139 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_start/ReduceMean ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_77 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Div_6 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_36 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_start/Sub ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_40 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_41 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_74 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_start/Pow ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ConstantOfShape_140 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_1 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_2 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_start/ReduceMean_1 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_180 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_38 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_39 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_start/Add ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_46 ...
2025-07-07 02:20:43,104 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_47 ...
2025-07-07 02:20:43,105 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_start/Sqrt ...
2025-07-07 02:20:43,105 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Add_8 ...
2025-07-07 02:20:43,105 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_start/Div ...
2025-07-07 02:20:43,105 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Add_9 ...
2025-07-07 02:20:43,105 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_start/Mul ...
2025-07-07 02:20:43,105 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_80 ...
2025-07-07 02:20:43,105 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_start/Add_1 ...
2025-07-07 02:20:43,105 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Equal_138 ...
2025-07-07 02:20:43,105 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.0/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.0/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Where_138 ...
2025-07-07 02:20:43,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/qkv/body/Add ...
2025-07-07 02:20:43,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_181 ...
2025-07-07 02:20:43,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_182 ...
2025-07-07 02:20:43,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_183 ...
2025-07-07 02:20:43,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_184 ...
2025-07-07 02:20:43,109 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/Split ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_144 ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_145 ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_146 ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_147 ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Shape ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_81 ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Gather ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ScatterND_42 ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_89 ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_41 ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Concat ...
2025-07-07 02:20:43,110 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Concat_13 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_44 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_45 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_86 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Reshape ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ConstantOfShape_145 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_5 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_6 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Slice ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Slice_1 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_185 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_43 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_44 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,111 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,112 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_50 ...
2025-07-07 02:20:43,112 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_51 ...
2025-07-07 02:20:43,112 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,112 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Slice_2 ...
2025-07-07 02:20:43,112 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Slice_3 ...
2025-07-07 02:20:43,112 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Div ...
2025-07-07 02:20:43,112 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,112 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,112 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Add_11 ...
2025-07-07 02:20:43,112 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.0/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.0/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Concat_2 ...
2025-07-07 02:20:43,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Add_12 ...
2025-07-07 02:20:43,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_92 ...
2025-07-07 02:20:43,115 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Equal_142 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Div ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Where_142 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_186 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_187 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_188 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_189 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Concat_3 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_148 ...
2025-07-07 02:20:43,116 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_149 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_150 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_151 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_83 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Transpose ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ScatterND_43 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_101 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_46 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,117 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_48 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_49 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_98 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ConstantOfShape_150 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_9 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_10 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,118 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_190 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_48 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_49 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Abs ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_54 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_55 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Pow ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Add_14 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Add_15 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,119 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_104 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Clip ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Equal_146 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Expand ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Where_146 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_191 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_192 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_193 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_194 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_152 ...
2025-07-07 02:20:43,120 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_153 ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_154 ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_155 ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.0/attn/window_attn/MatMul ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.0/attn/window_attn/MatMul ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_85 ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Shape ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ScatterND_44 ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Gather ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_113 ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_51 ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_52 ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_53 ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_110 ...
2025-07-07 02:20:43,121 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.0/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.0/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ConstantOfShape_155 ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_13 ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_14 ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.0/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.0/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_195 ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_53 ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_54 ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_58 ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_59 ...
2025-07-07 02:20:43,122 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Add_17 ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.0/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.0/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Add_18 ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.0/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.0/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_116 ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Equal_150 ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Where_150 ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,123 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_196 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_197 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_198 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_199 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_156 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_157 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_158 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_159 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_87 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ScatterND_45 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_125 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_56 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_57 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_17 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_18 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_58 ...
2025-07-07 02:20:43,124 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_59 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_62 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_63 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_202 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_203 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_161 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_162 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_89 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ScatterND_46 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_137 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_60 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_61 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_21 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_22 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_63 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_64 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_66 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_67 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_207 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_208 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_165 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_166 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_91 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ScatterND_47 ...
2025-07-07 02:20:43,125 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_149 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_66 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_64 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_65 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_146 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ConstantOfShape_170 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_25 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_26 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_210 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_68 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_69 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_70 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_71 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Add_26 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Add_27 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_152 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Equal_162 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Where_162 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_211 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_212 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_213 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_214 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_168 ...
2025-07-07 02:20:43,126 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_169 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_170 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_171 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_93 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ScatterND_48 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_161 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_68 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_69 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_29 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_30 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_73 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_74 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_74 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_75 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_217 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_218 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_173 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_174 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_95 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ScatterND_49 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_173 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_72 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_73 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_33 ...
2025-07-07 02:20:43,127 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Range_34 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_78 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_79 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_78 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_79 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_222 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Expand_223 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_177 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_178 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_97 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /ScatterND_50 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_183 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_76 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_77 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Div_9 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Div_10 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_181 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_182 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_99 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_81 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Transpose_2 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_82 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_185 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_186 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Sub_4 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Equal_174 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Not ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Where_174 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Where_175 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Shape_4 ...
2025-07-07 02:20:43,128 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Unsqueeze_4 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Gather_5 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Div ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Unsqueeze_7 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Unsqueeze_6 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Concat_2 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Reshape_3 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Add_1 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/attn_transform/Reshape_4 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.0/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.0/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Div_7 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Concat_10 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Slice_4 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Slice_5 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Concat_11 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Slice_6 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Slice_7 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Concat_12 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/window_attn/Reshape_9 ...
2025-07-07 02:20:43,129 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/Concat ...
2025-07-07 02:20:43,130 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.0/attn/proj/MatMul ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.0/attn/proj/MatMul ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/attn/proj/Add ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm1/ReduceMean ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm1/Sub ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm1/Pow ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm1/Add ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm1/Sqrt ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm1/Div ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm1/Mul ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm1/Add_1 ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/Add ...
2025-07-07 02:20:43,132 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.0/mlp/fc1/MatMul ...
2025-07-07 02:20:43,135 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.0/mlp/fc1/MatMul ...
2025-07-07 02:20:43,135 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/mlp/fc1/Add ...
2025-07-07 02:20:43,135 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/mlp/act/Div ...
2025-07-07 02:20:43,135 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/mlp/act/Erf ...
2025-07-07 02:20:43,135 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/mlp/act/Add ...
2025-07-07 02:20:43,135 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/mlp/act/Mul ...
2025-07-07 02:20:43,135 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/mlp/act/Mul_1 ...
2025-07-07 02:20:43,135 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.0/mlp/fc2/MatMul ...
2025-07-07 02:20:43,137 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.0/mlp/fc2/MatMul ...
2025-07-07 02:20:43,137 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/mlp/fc2/Add ...
2025-07-07 02:20:43,138 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm2/ReduceMean ...
2025-07-07 02:20:43,138 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm2/Sub ...
2025-07-07 02:20:43,138 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm2/Pow ...
2025-07-07 02:20:43,138 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,138 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm2/Add ...
2025-07-07 02:20:43,138 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm2/Sqrt ...
2025-07-07 02:20:43,138 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm2/Div ...
2025-07-07 02:20:43,138 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm2/Mul ...
2025-07-07 02:20:43,138 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/norm2/Add_1 ...
2025-07-07 02:20:43,138 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.0/Add_1 ...
2025-07-07 02:20:43,138 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.1/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.1/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/qkv/body/Add ...
2025-07-07 02:20:43,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/Split ...
2025-07-07 02:20:43,140 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Shape ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Gather ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Concat ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Reshape ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Div ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,141 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Div ...
2025-07-07 02:20:43,142 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,142 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,142 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.1/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.1/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Transpose ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,144 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Abs ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Pow ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,145 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Clip ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Expand ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.1/attn/window_attn/MatMul ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.1/attn/window_attn/MatMul ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,146 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.1/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.1/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.1/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.1/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,147 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.1/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.1/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Concat_7 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.1/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.1/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.1/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.1/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,148 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,149 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,149 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,149 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,149 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,149 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,149 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,149 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/Concat ...
2025-07-07 02:20:43,149 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.1/attn/proj/MatMul ...
2025-07-07 02:20:43,151 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.1/attn/proj/MatMul ...
2025-07-07 02:20:43,151 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/attn/proj/Add ...
2025-07-07 02:20:43,151 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm1/ReduceMean ...
2025-07-07 02:20:43,151 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm1/Sub ...
2025-07-07 02:20:43,151 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm1/Pow ...
2025-07-07 02:20:43,151 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,151 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm1/Add ...
2025-07-07 02:20:43,151 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm1/Sqrt ...
2025-07-07 02:20:43,151 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm1/Div ...
2025-07-07 02:20:43,151 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm1/Mul ...
2025-07-07 02:20:43,151 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm1/Add_1 ...
2025-07-07 02:20:43,151 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/Add ...
2025-07-07 02:20:43,152 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.1/mlp/fc1/MatMul ...
2025-07-07 02:20:43,154 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.1/mlp/fc1/MatMul ...
2025-07-07 02:20:43,154 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/mlp/fc1/Add ...
2025-07-07 02:20:43,154 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/mlp/act/Div ...
2025-07-07 02:20:43,154 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/mlp/act/Erf ...
2025-07-07 02:20:43,154 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/mlp/act/Add ...
2025-07-07 02:20:43,154 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/mlp/act/Mul ...
2025-07-07 02:20:43,154 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/mlp/act/Mul_1 ...
2025-07-07 02:20:43,154 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.1/mlp/fc2/MatMul ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.1/mlp/fc2/MatMul ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/mlp/fc2/Add ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm2/ReduceMean ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm2/Sub ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm2/Pow ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm2/Add ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm2/Sqrt ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm2/Div ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm2/Mul ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/norm2/Add_1 ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.1/Add_1 ...
2025-07-07 02:20:43,157 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.2/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,159 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.2/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,159 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,159 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,159 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/qkv/body/Add ...
2025-07-07 02:20:43,159 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,159 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/Split ...
2025-07-07 02:20:43,159 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Shape ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Gather ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Concat ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Concat_13 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Reshape ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Slice ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Slice_1 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Slice_2 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Slice_3 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Div ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,160 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,161 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.2/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.2/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Concat_2 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Div ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Concat_3 ...
2025-07-07 02:20:43,163 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Transpose ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,164 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Abs ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Pow ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Clip ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Expand ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,165 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.2/attn/window_attn/MatMul ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.2/attn/window_attn/MatMul ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/attn_transform/Shape ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/attn_transform/Gather ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/attn_transform/Div ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.2/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.2/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/attn_transform/Unsqueeze_4 ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.2/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.2/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/attn_transform/Concat_2 ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,166 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/attn_transform/Reshape_2 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/attn_transform/Add_1 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.2/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.2/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/attn_transform/Reshape_3 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.2/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.2/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.2/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.2/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,167 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Concat_10 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Slice_4 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Slice_5 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Concat_11 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Slice_6 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Slice_7 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Concat_12 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/window_attn/Reshape_9 ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/Concat ...
2025-07-07 02:20:43,168 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.2/attn/proj/MatMul ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.2/attn/proj/MatMul ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/attn/proj/Add ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm1/ReduceMean ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm1/Sub ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm1/Pow ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm1/Add ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm1/Sqrt ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm1/Div ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm1/Mul ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm1/Add_1 ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/Add ...
2025-07-07 02:20:43,171 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.2/mlp/fc1/MatMul ...
2025-07-07 02:20:43,173 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.2/mlp/fc1/MatMul ...
2025-07-07 02:20:43,173 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/mlp/fc1/Add ...
2025-07-07 02:20:43,174 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/mlp/act/Div ...
2025-07-07 02:20:43,174 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/mlp/act/Erf ...
2025-07-07 02:20:43,174 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/mlp/act/Add ...
2025-07-07 02:20:43,174 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/mlp/act/Mul ...
2025-07-07 02:20:43,174 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/mlp/act/Mul_1 ...
2025-07-07 02:20:43,174 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.2/mlp/fc2/MatMul ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.2/mlp/fc2/MatMul ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/mlp/fc2/Add ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm2/ReduceMean ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm2/Sub ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm2/Pow ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm2/Add ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm2/Sqrt ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm2/Div ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm2/Mul ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/norm2/Add_1 ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.2/Add_1 ...
2025-07-07 02:20:43,176 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.3/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.3/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/qkv/body/Add ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/Split ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Shape ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Gather ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Concat ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Reshape ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,179 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Div ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Div ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,180 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.3/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,182 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.3/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,182 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,182 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,182 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Transpose ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Abs ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,183 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Pow ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Clip ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Expand ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,184 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.3/attn/window_attn/MatMul ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.3/attn/window_attn/MatMul ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.3/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.3/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,185 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.3/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.3/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.3/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.3/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Concat_7 ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.3/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.3/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,186 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.3/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.3/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/Concat ...
2025-07-07 02:20:43,187 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.3/attn/proj/MatMul ...
2025-07-07 02:20:43,189 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.3/attn/proj/MatMul ...
2025-07-07 02:20:43,190 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/attn/proj/Add ...
2025-07-07 02:20:43,190 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm1/ReduceMean ...
2025-07-07 02:20:43,190 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm1/Sub ...
2025-07-07 02:20:43,190 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm1/Pow ...
2025-07-07 02:20:43,190 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,190 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm1/Add ...
2025-07-07 02:20:43,190 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm1/Sqrt ...
2025-07-07 02:20:43,190 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm1/Div ...
2025-07-07 02:20:43,190 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm1/Mul ...
2025-07-07 02:20:43,190 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm1/Add_1 ...
2025-07-07 02:20:43,190 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/Add ...
2025-07-07 02:20:43,190 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.3/mlp/fc1/MatMul ...
2025-07-07 02:20:43,192 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.3/mlp/fc1/MatMul ...
2025-07-07 02:20:43,192 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/mlp/fc1/Add ...
2025-07-07 02:20:43,192 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/mlp/act/Div ...
2025-07-07 02:20:43,192 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/mlp/act/Erf ...
2025-07-07 02:20:43,192 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/mlp/act/Add ...
2025-07-07 02:20:43,192 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/mlp/act/Mul ...
2025-07-07 02:20:43,192 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/mlp/act/Mul_1 ...
2025-07-07 02:20:43,192 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.0/blocks.3/mlp/fc2/MatMul ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.0/blocks.3/mlp/fc2/MatMul ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/mlp/fc2/Add ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm2/ReduceMean ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm2/Sub ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm2/Pow ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm2/Add ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm2/Sqrt ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm2/Div ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm2/Mul ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/norm2/Add_1 ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/blocks.3/Add_1 ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/Shape ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/Transpose ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/Gather ...
2025-07-07 02:20:43,195 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/Unsqueeze ...
2025-07-07 02:20:43,196 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/Concat ...
2025-07-07 02:20:43,196 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/Reshape ...
2025-07-07 02:20:43,196 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/conv/Conv ...
2025-07-07 02:20:43,196 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/Shape_2 ...
2025-07-07 02:20:43,196 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/Slice ...
2025-07-07 02:20:43,196 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/Concat_1 ...
2025-07-07 02:20:43,196 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/Reshape_1 ...
2025-07-07 02:20:43,196 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/Transpose_1 ...
2025-07-07 02:20:43,196 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.0/Add ...
2025-07-07 02:20:43,196 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.0/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,198 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.0/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,198 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,198 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,198 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/qkv/body/Add ...
2025-07-07 02:20:43,198 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,198 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/Split ...
2025-07-07 02:20:43,198 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,198 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,198 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Shape ...
2025-07-07 02:20:43,198 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,198 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Gather ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Concat ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Concat_13 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Reshape ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Slice ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Slice_1 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Slice_2 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Slice_3 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Div ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,199 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.0/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.0/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Concat_2 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Div ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Concat_3 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,202 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Transpose ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Abs ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,203 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Pow ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Clip ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Expand ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.0/attn/window_attn/MatMul ...
2025-07-07 02:20:43,204 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.0/attn/window_attn/MatMul ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/attn_transform/Shape ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/attn_transform/Gather ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/attn_transform/Div ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.0/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.0/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/attn_transform/Unsqueeze_4 ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.0/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.0/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/attn_transform/Concat_2 ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/attn_transform/Reshape_2 ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/attn_transform/Add_1 ...
2025-07-07 02:20:43,205 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.0/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.0/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/attn_transform/Reshape_3 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.0/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.0/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.0/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.0/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,206 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Concat_10 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Slice_4 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Slice_5 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Concat_11 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Slice_6 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Slice_7 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Concat_12 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/window_attn/Reshape_9 ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/Concat ...
2025-07-07 02:20:43,207 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.0/attn/proj/MatMul ...
2025-07-07 02:20:43,209 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.0/attn/proj/MatMul ...
2025-07-07 02:20:43,209 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/attn/proj/Add ...
2025-07-07 02:20:43,210 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm1/ReduceMean ...
2025-07-07 02:20:43,210 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm1/Sub ...
2025-07-07 02:20:43,210 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm1/Pow ...
2025-07-07 02:20:43,210 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,210 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm1/Add ...
2025-07-07 02:20:43,210 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm1/Sqrt ...
2025-07-07 02:20:43,210 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm1/Div ...
2025-07-07 02:20:43,210 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm1/Mul ...
2025-07-07 02:20:43,210 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm1/Add_1 ...
2025-07-07 02:20:43,210 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/Add ...
2025-07-07 02:20:43,210 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.0/mlp/fc1/MatMul ...
2025-07-07 02:20:43,212 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.0/mlp/fc1/MatMul ...
2025-07-07 02:20:43,212 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/mlp/fc1/Add ...
2025-07-07 02:20:43,213 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/mlp/act/Div ...
2025-07-07 02:20:43,213 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/mlp/act/Erf ...
2025-07-07 02:20:43,213 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/mlp/act/Add ...
2025-07-07 02:20:43,213 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/mlp/act/Mul ...
2025-07-07 02:20:43,213 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/mlp/act/Mul_1 ...
2025-07-07 02:20:43,213 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.0/mlp/fc2/MatMul ...
2025-07-07 02:20:43,215 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.0/mlp/fc2/MatMul ...
2025-07-07 02:20:43,215 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/mlp/fc2/Add ...
2025-07-07 02:20:43,215 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm2/ReduceMean ...
2025-07-07 02:20:43,215 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm2/Sub ...
2025-07-07 02:20:43,215 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm2/Pow ...
2025-07-07 02:20:43,215 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,215 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm2/Add ...
2025-07-07 02:20:43,215 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm2/Sqrt ...
2025-07-07 02:20:43,215 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm2/Div ...
2025-07-07 02:20:43,215 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm2/Mul ...
2025-07-07 02:20:43,215 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/norm2/Add_1 ...
2025-07-07 02:20:43,215 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.0/Add_1 ...
2025-07-07 02:20:43,216 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.1/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.1/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/qkv/body/Add ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/Split ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Shape ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Gather ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,218 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Concat ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Reshape ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Div ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Div ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,219 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.1/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.1/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Transpose ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,222 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Abs ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Pow ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,223 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Clip ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Expand ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.1/attn/window_attn/MatMul ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.1/attn/window_attn/MatMul ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,224 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.1/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.1/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.1/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.1/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.1/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.1/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,225 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Concat_7 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.1/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.1/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.1/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.1/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,226 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/Concat ...
2025-07-07 02:20:43,227 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.1/attn/proj/MatMul ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.1/attn/proj/MatMul ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/attn/proj/Add ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm1/ReduceMean ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm1/Sub ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm1/Pow ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm1/Add ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm1/Sqrt ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm1/Div ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm1/Mul ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm1/Add_1 ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/Add ...
2025-07-07 02:20:43,229 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.1/mlp/fc1/MatMul ...
2025-07-07 02:20:43,232 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.1/mlp/fc1/MatMul ...
2025-07-07 02:20:43,232 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/mlp/fc1/Add ...
2025-07-07 02:20:43,232 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/mlp/act/Div ...
2025-07-07 02:20:43,232 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/mlp/act/Erf ...
2025-07-07 02:20:43,232 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/mlp/act/Add ...
2025-07-07 02:20:43,232 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/mlp/act/Mul ...
2025-07-07 02:20:43,232 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/mlp/act/Mul_1 ...
2025-07-07 02:20:43,232 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.1/mlp/fc2/MatMul ...
2025-07-07 02:20:43,234 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.1/mlp/fc2/MatMul ...
2025-07-07 02:20:43,234 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/mlp/fc2/Add ...
2025-07-07 02:20:43,234 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm2/ReduceMean ...
2025-07-07 02:20:43,234 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm2/Sub ...
2025-07-07 02:20:43,234 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm2/Pow ...
2025-07-07 02:20:43,234 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,234 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm2/Add ...
2025-07-07 02:20:43,234 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm2/Sqrt ...
2025-07-07 02:20:43,234 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm2/Div ...
2025-07-07 02:20:43,234 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm2/Mul ...
2025-07-07 02:20:43,235 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/norm2/Add_1 ...
2025-07-07 02:20:43,235 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.1/Add_1 ...
2025-07-07 02:20:43,235 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.2/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.2/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/qkv/body/Add ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/Split ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Shape ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Gather ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,237 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Concat ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Concat_13 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Reshape ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Slice ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Slice_1 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Slice_2 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Slice_3 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Div ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,238 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.2/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.2/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Concat_2 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Div ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Concat_3 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,241 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Transpose ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Abs ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,242 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Pow ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Clip ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Expand ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.2/attn/window_attn/MatMul ...
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,243 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.2/attn/window_attn/MatMul ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/attn_transform/Shape ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/attn_transform/Gather ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/attn_transform/Div ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.2/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.2/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/attn_transform/Unsqueeze_4 ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.2/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.2/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/attn_transform/Concat_2 ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,244 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/attn_transform/Reshape_2 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/attn_transform/Add_1 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.2/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.2/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/attn_transform/Reshape_3 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.2/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.2/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.2/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.2/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,245 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Concat_10 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Slice_4 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Slice_5 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Concat_11 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Slice_6 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Slice_7 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Concat_12 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/window_attn/Reshape_9 ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/Concat ...
2025-07-07 02:20:43,246 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.2/attn/proj/MatMul ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.2/attn/proj/MatMul ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/attn/proj/Add ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm1/ReduceMean ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm1/Sub ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm1/Pow ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm1/Add ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm1/Sqrt ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm1/Div ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm1/Mul ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm1/Add_1 ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/Add ...
2025-07-07 02:20:43,249 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.2/mlp/fc1/MatMul ...
2025-07-07 02:20:43,251 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.2/mlp/fc1/MatMul ...
2025-07-07 02:20:43,252 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/mlp/fc1/Add ...
2025-07-07 02:20:43,252 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/mlp/act/Div ...
2025-07-07 02:20:43,252 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/mlp/act/Erf ...
2025-07-07 02:20:43,252 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/mlp/act/Add ...
2025-07-07 02:20:43,252 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/mlp/act/Mul ...
2025-07-07 02:20:43,252 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/mlp/act/Mul_1 ...
2025-07-07 02:20:43,252 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.2/mlp/fc2/MatMul ...
2025-07-07 02:20:43,254 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.2/mlp/fc2/MatMul ...
2025-07-07 02:20:43,254 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/mlp/fc2/Add ...
2025-07-07 02:20:43,254 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm2/ReduceMean ...
2025-07-07 02:20:43,254 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm2/Sub ...
2025-07-07 02:20:43,254 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm2/Pow ...
2025-07-07 02:20:43,254 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,254 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm2/Add ...
2025-07-07 02:20:43,254 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm2/Sqrt ...
2025-07-07 02:20:43,254 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm2/Div ...
2025-07-07 02:20:43,254 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm2/Mul ...
2025-07-07 02:20:43,254 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/norm2/Add_1 ...
2025-07-07 02:20:43,254 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.2/Add_1 ...
2025-07-07 02:20:43,255 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.3/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.3/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/qkv/body/Add ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/Split ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Shape ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Gather ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,257 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Concat ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Reshape ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Div ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Div ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,258 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.3/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.3/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Transpose ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,261 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Abs ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Pow ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Clip ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,262 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Expand ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.3/attn/window_attn/MatMul ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.3/attn/window_attn/MatMul ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.3/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,263 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.3/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.3/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.3/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.3/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.3/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,264 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Concat_7 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.3/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.3/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.3/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.3/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/Concat ...
2025-07-07 02:20:43,265 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.3/attn/proj/MatMul ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.3/attn/proj/MatMul ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/attn/proj/Add ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm1/ReduceMean ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm1/Sub ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm1/Pow ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm1/Add ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm1/Sqrt ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm1/Div ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm1/Mul ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm1/Add_1 ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/Add ...
2025-07-07 02:20:43,268 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.3/mlp/fc1/MatMul ...
2025-07-07 02:20:43,271 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.3/mlp/fc1/MatMul ...
2025-07-07 02:20:43,271 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/mlp/fc1/Add ...
2025-07-07 02:20:43,271 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/mlp/act/Div ...
2025-07-07 02:20:43,271 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/mlp/act/Erf ...
2025-07-07 02:20:43,271 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/mlp/act/Add ...
2025-07-07 02:20:43,271 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/mlp/act/Mul ...
2025-07-07 02:20:43,271 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/mlp/act/Mul_1 ...
2025-07-07 02:20:43,271 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.1/blocks.3/mlp/fc2/MatMul ...
2025-07-07 02:20:43,273 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.1/blocks.3/mlp/fc2/MatMul ...
2025-07-07 02:20:43,273 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/mlp/fc2/Add ...
2025-07-07 02:20:43,273 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm2/ReduceMean ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm2/Sub ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm2/Pow ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm2/Add ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm2/Sqrt ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm2/Div ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm2/Mul ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/norm2/Add_1 ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/blocks.3/Add_1 ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/Shape ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/Transpose ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/Gather ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/Unsqueeze ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/Concat ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/Reshape ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/conv/Conv ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/Shape_2 ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/Slice ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/Concat_1 ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/Reshape_1 ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/Transpose_1 ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.1/Add ...
2025-07-07 02:20:43,274 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.0/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.0/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/qkv/body/Add ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/Split ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Shape ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Gather ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Concat ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Concat_13 ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Reshape ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Slice ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Slice_1 ...
2025-07-07 02:20:43,277 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,278 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,278 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,278 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,278 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,278 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,278 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,278 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Slice_2 ...
2025-07-07 02:20:43,278 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Slice_3 ...
2025-07-07 02:20:43,278 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Div ...
2025-07-07 02:20:43,278 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,278 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,278 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.0/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,280 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.0/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,280 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Concat_2 ...
2025-07-07 02:20:43,280 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,280 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,280 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,280 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,280 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,280 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,280 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,280 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Div ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Concat_3 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Transpose ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,281 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Abs ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Pow ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Clip ...
2025-07-07 02:20:43,282 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Expand ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.0/attn/window_attn/MatMul ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.0/attn/window_attn/MatMul ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/attn_transform/Shape ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/attn_transform/Gather ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/attn_transform/Div ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.0/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.0/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,283 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/attn_transform/Unsqueeze_4 ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.0/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.0/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/attn_transform/Concat_2 ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/attn_transform/Reshape_2 ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/attn_transform/Add_1 ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.0/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.0/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/attn_transform/Reshape_3 ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.0/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,284 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.0/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.0/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.0/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Concat_10 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Slice_4 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Slice_5 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Concat_11 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Slice_6 ...
2025-07-07 02:20:43,285 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Slice_7 ...
2025-07-07 02:20:43,286 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Concat_12 ...
2025-07-07 02:20:43,286 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/window_attn/Reshape_9 ...
2025-07-07 02:20:43,286 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/Concat ...
2025-07-07 02:20:43,286 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.0/attn/proj/MatMul ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.0/attn/proj/MatMul ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/attn/proj/Add ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm1/ReduceMean ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm1/Sub ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm1/Pow ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm1/Add ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm1/Sqrt ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm1/Div ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm1/Mul ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm1/Add_1 ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/Add ...
2025-07-07 02:20:43,288 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.0/mlp/fc1/MatMul ...
2025-07-07 02:20:43,291 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.0/mlp/fc1/MatMul ...
2025-07-07 02:20:43,291 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/mlp/fc1/Add ...
2025-07-07 02:20:43,291 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/mlp/act/Div ...
2025-07-07 02:20:43,291 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/mlp/act/Erf ...
2025-07-07 02:20:43,291 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/mlp/act/Add ...
2025-07-07 02:20:43,291 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/mlp/act/Mul ...
2025-07-07 02:20:43,291 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/mlp/act/Mul_1 ...
2025-07-07 02:20:43,291 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.0/mlp/fc2/MatMul ...
2025-07-07 02:20:43,293 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.0/mlp/fc2/MatMul ...
2025-07-07 02:20:43,294 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/mlp/fc2/Add ...
2025-07-07 02:20:43,294 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm2/ReduceMean ...
2025-07-07 02:20:43,294 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm2/Sub ...
2025-07-07 02:20:43,294 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm2/Pow ...
2025-07-07 02:20:43,294 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,294 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm2/Add ...
2025-07-07 02:20:43,294 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm2/Sqrt ...
2025-07-07 02:20:43,294 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm2/Div ...
2025-07-07 02:20:43,294 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm2/Mul ...
2025-07-07 02:20:43,294 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/norm2/Add_1 ...
2025-07-07 02:20:43,294 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.0/Add_1 ...
2025-07-07 02:20:43,294 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.1/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,296 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.1/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,296 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,296 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,296 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/qkv/body/Add ...
2025-07-07 02:20:43,296 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,296 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/Split ...
2025-07-07 02:20:43,296 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,296 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Shape ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Gather ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Concat ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Reshape ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Div ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Div ...
2025-07-07 02:20:43,297 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,298 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,298 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.1/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.1/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Transpose ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,300 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Abs ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Pow ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,301 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Clip ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Expand ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.1/attn/window_attn/MatMul ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.1/attn/window_attn/MatMul ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,302 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.1/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.1/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.1/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.1/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.1/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.1/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,303 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Concat_7 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.1/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.1/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.1/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.1/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,304 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,305 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,305 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/Concat ...
2025-07-07 02:20:43,305 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.1/attn/proj/MatMul ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.1/attn/proj/MatMul ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/attn/proj/Add ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm1/ReduceMean ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm1/Sub ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm1/Pow ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm1/Add ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm1/Sqrt ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm1/Div ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm1/Mul ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm1/Add_1 ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/Add ...
2025-07-07 02:20:43,307 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.1/mlp/fc1/MatMul ...
2025-07-07 02:20:43,310 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.1/mlp/fc1/MatMul ...
2025-07-07 02:20:43,310 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/mlp/fc1/Add ...
2025-07-07 02:20:43,310 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/mlp/act/Div ...
2025-07-07 02:20:43,310 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/mlp/act/Erf ...
2025-07-07 02:20:43,310 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/mlp/act/Add ...
2025-07-07 02:20:43,310 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/mlp/act/Mul ...
2025-07-07 02:20:43,310 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/mlp/act/Mul_1 ...
2025-07-07 02:20:43,310 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.1/mlp/fc2/MatMul ...
2025-07-07 02:20:43,312 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.1/mlp/fc2/MatMul ...
2025-07-07 02:20:43,312 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/mlp/fc2/Add ...
2025-07-07 02:20:43,313 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm2/ReduceMean ...
2025-07-07 02:20:43,313 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm2/Sub ...
2025-07-07 02:20:43,313 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm2/Pow ...
2025-07-07 02:20:43,313 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,313 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm2/Add ...
2025-07-07 02:20:43,313 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm2/Sqrt ...
2025-07-07 02:20:43,313 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm2/Div ...
2025-07-07 02:20:43,313 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm2/Mul ...
2025-07-07 02:20:43,313 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/norm2/Add_1 ...
2025-07-07 02:20:43,313 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.1/Add_1 ...
2025-07-07 02:20:43,313 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.2/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,315 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.2/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,315 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,315 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,315 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/qkv/body/Add ...
2025-07-07 02:20:43,315 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,315 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/Split ...
2025-07-07 02:20:43,315 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,315 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,315 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Shape ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Gather ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Concat ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Concat_13 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Reshape ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Slice ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Slice_1 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Slice_2 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Slice_3 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Div ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,316 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.2/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.2/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Concat_2 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Div ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,319 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Concat_3 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Transpose ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,320 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Abs ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Pow ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Clip ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Expand ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,321 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.2/attn/window_attn/MatMul ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.2/attn/window_attn/MatMul ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/attn_transform/Shape ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/attn_transform/Gather ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/attn_transform/Div ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.2/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.2/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/attn_transform/Unsqueeze_4 ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.2/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.2/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,322 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/attn_transform/Concat_2 ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/attn_transform/Reshape_2 ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/attn_transform/Add_1 ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.2/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.2/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/attn_transform/Reshape_3 ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.2/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.2/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.2/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,323 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.2/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Concat_10 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Slice_4 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Slice_5 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Concat_11 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Slice_6 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Slice_7 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Concat_12 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/window_attn/Reshape_9 ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/Concat ...
2025-07-07 02:20:43,324 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.2/attn/proj/MatMul ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.2/attn/proj/MatMul ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/attn/proj/Add ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm1/ReduceMean ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm1/Sub ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm1/Pow ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm1/Add ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm1/Sqrt ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm1/Div ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm1/Mul ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm1/Add_1 ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/Add ...
2025-07-07 02:20:43,327 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.2/mlp/fc1/MatMul ...
2025-07-07 02:20:43,330 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.2/mlp/fc1/MatMul ...
2025-07-07 02:20:43,330 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/mlp/fc1/Add ...
2025-07-07 02:20:43,330 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/mlp/act/Div ...
2025-07-07 02:20:43,330 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/mlp/act/Erf ...
2025-07-07 02:20:43,330 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/mlp/act/Add ...
2025-07-07 02:20:43,330 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/mlp/act/Mul ...
2025-07-07 02:20:43,330 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/mlp/act/Mul_1 ...
2025-07-07 02:20:43,330 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.2/mlp/fc2/MatMul ...
2025-07-07 02:20:43,332 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.2/mlp/fc2/MatMul ...
2025-07-07 02:20:43,332 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/mlp/fc2/Add ...
2025-07-07 02:20:43,332 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm2/ReduceMean ...
2025-07-07 02:20:43,332 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm2/Sub ...
2025-07-07 02:20:43,332 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm2/Pow ...
2025-07-07 02:20:43,332 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,332 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm2/Add ...
2025-07-07 02:20:43,332 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm2/Sqrt ...
2025-07-07 02:20:43,332 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm2/Div ...
2025-07-07 02:20:43,333 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm2/Mul ...
2025-07-07 02:20:43,333 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/norm2/Add_1 ...
2025-07-07 02:20:43,333 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.2/Add_1 ...
2025-07-07 02:20:43,333 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.3/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.3/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/qkv/body/Add ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/Split ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Shape ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Gather ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,335 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Concat ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Reshape ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Div ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Div ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,336 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.3/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.3/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Transpose ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,339 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Abs ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Pow ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,340 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Clip ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Expand ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.3/attn/window_attn/MatMul ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.3/attn/window_attn/MatMul ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,341 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.3/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.3/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.3/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.3/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.3/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.3/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,342 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Concat_7 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.3/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.3/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.3/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.3/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,343 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,344 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,344 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,344 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/Concat ...
2025-07-07 02:20:43,344 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.3/attn/proj/MatMul ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.3/attn/proj/MatMul ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/attn/proj/Add ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm1/ReduceMean ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm1/Sub ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm1/Pow ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm1/Add ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm1/Sqrt ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm1/Div ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm1/Mul ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm1/Add_1 ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/Add ...
2025-07-07 02:20:43,346 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.3/mlp/fc1/MatMul ...
2025-07-07 02:20:43,349 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.3/mlp/fc1/MatMul ...
2025-07-07 02:20:43,349 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/mlp/fc1/Add ...
2025-07-07 02:20:43,349 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/mlp/act/Div ...
2025-07-07 02:20:43,349 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/mlp/act/Erf ...
2025-07-07 02:20:43,349 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/mlp/act/Add ...
2025-07-07 02:20:43,349 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/mlp/act/Mul ...
2025-07-07 02:20:43,349 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/mlp/act/Mul_1 ...
2025-07-07 02:20:43,349 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.2/blocks.3/mlp/fc2/MatMul ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.2/blocks.3/mlp/fc2/MatMul ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/mlp/fc2/Add ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm2/ReduceMean ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm2/Sub ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm2/Pow ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm2/Add ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm2/Sqrt ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm2/Div ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm2/Mul ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/norm2/Add_1 ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/blocks.3/Add_1 ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/Shape ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/Transpose ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/Gather ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/Unsqueeze ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/Concat ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/Reshape ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/conv/Conv ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/Shape_2 ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/Slice ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/Concat_1 ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/Reshape_1 ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/Transpose_1 ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.2/Add ...
2025-07-07 02:20:43,352 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.0/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.0/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/qkv/body/Add ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/Split ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Shape ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Gather ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Concat ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Concat_13 ...
2025-07-07 02:20:43,355 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Reshape ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Slice ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Slice_1 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Slice_2 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Slice_3 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Div ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,356 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.0/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,358 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.0/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,358 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Concat_2 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Div ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Concat_3 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Transpose ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,359 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Abs ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Pow ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,360 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Clip ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Expand ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.0/attn/window_attn/MatMul ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.0/attn/window_attn/MatMul ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/attn_transform/Shape ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/attn_transform/Gather ...
2025-07-07 02:20:43,361 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/attn_transform/Div ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.0/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.0/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/attn_transform/Unsqueeze_4 ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.0/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.0/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/attn_transform/Concat_2 ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/attn_transform/Reshape_2 ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/attn_transform/Add_1 ...
2025-07-07 02:20:43,362 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.0/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.0/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/attn_transform/Reshape_3 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.0/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.0/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.0/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.0/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,363 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Concat_10 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Slice_4 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Slice_5 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Concat_11 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Slice_6 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Slice_7 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Concat_12 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/window_attn/Reshape_9 ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/Concat ...
2025-07-07 02:20:43,364 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.0/attn/proj/MatMul ...
2025-07-07 02:20:43,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.0/attn/proj/MatMul ...
2025-07-07 02:20:43,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/attn/proj/Add ...
2025-07-07 02:20:43,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm1/ReduceMean ...
2025-07-07 02:20:43,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm1/Sub ...
2025-07-07 02:20:43,366 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm1/Pow ...
2025-07-07 02:20:43,367 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,367 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm1/Add ...
2025-07-07 02:20:43,367 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm1/Sqrt ...
2025-07-07 02:20:43,367 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm1/Div ...
2025-07-07 02:20:43,367 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm1/Mul ...
2025-07-07 02:20:43,367 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm1/Add_1 ...
2025-07-07 02:20:43,367 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/Add ...
2025-07-07 02:20:43,367 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.0/mlp/fc1/MatMul ...
2025-07-07 02:20:43,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.0/mlp/fc1/MatMul ...
2025-07-07 02:20:43,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/mlp/fc1/Add ...
2025-07-07 02:20:43,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/mlp/act/Div ...
2025-07-07 02:20:43,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/mlp/act/Erf ...
2025-07-07 02:20:43,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/mlp/act/Add ...
2025-07-07 02:20:43,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/mlp/act/Mul ...
2025-07-07 02:20:43,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/mlp/act/Mul_1 ...
2025-07-07 02:20:43,369 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.0/mlp/fc2/MatMul ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.0/mlp/fc2/MatMul ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/mlp/fc2/Add ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm2/ReduceMean ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm2/Sub ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm2/Pow ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm2/Add ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm2/Sqrt ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm2/Div ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm2/Mul ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/norm2/Add_1 ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.0/Add_1 ...
2025-07-07 02:20:43,372 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.1/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.1/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/qkv/body/Add ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/Split ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Shape ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Gather ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Concat ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Reshape ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,375 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Div ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Div ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,376 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.1/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.1/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,378 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Transpose ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Abs ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Pow ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,379 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Clip ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Expand ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,380 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.1/attn/window_attn/MatMul ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.1/attn/window_attn/MatMul ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.1/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.1/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,381 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.1/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.1/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.1/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.1/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Concat_7 ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.1/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.1/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,382 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.1/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.1/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/Concat ...
2025-07-07 02:20:43,383 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.1/attn/proj/MatMul ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.1/attn/proj/MatMul ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/attn/proj/Add ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm1/ReduceMean ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm1/Sub ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm1/Pow ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm1/Add ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm1/Sqrt ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm1/Div ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm1/Mul ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm1/Add_1 ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/Add ...
2025-07-07 02:20:43,386 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.1/mlp/fc1/MatMul ...
2025-07-07 02:20:43,388 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.1/mlp/fc1/MatMul ...
2025-07-07 02:20:43,388 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/mlp/fc1/Add ...
2025-07-07 02:20:43,388 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/mlp/act/Div ...
2025-07-07 02:20:43,388 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/mlp/act/Erf ...
2025-07-07 02:20:43,388 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/mlp/act/Add ...
2025-07-07 02:20:43,389 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/mlp/act/Mul ...
2025-07-07 02:20:43,389 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/mlp/act/Mul_1 ...
2025-07-07 02:20:43,389 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.1/mlp/fc2/MatMul ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.1/mlp/fc2/MatMul ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/mlp/fc2/Add ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm2/ReduceMean ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm2/Sub ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm2/Pow ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm2/Add ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm2/Sqrt ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm2/Div ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm2/Mul ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/norm2/Add_1 ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.1/Add_1 ...
2025-07-07 02:20:43,391 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.2/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.2/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/qkv/body/Add ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/Split ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Shape ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Gather ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Concat ...
2025-07-07 02:20:43,394 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Concat_13 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Reshape ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Slice ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Slice_1 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Slice_2 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Slice_3 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Div ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,395 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.2/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,397 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.2/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Concat_2 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Div ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Concat_3 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Transpose ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,398 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Abs ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Pow ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,399 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Clip ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Expand ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.2/attn/window_attn/MatMul ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.2/attn/window_attn/MatMul ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/attn_transform/Shape ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,400 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/attn_transform/Gather ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/attn_transform/Div ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.2/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.2/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/attn_transform/Unsqueeze_4 ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.2/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.2/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/attn_transform/Concat_2 ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/attn_transform/Reshape_2 ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/attn_transform/Add_1 ...
2025-07-07 02:20:43,401 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.2/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.2/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/attn_transform/Reshape_3 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.2/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.2/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.2/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.2/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,402 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Concat_10 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Slice_4 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Slice_5 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Concat_11 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Slice_6 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Slice_7 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Concat_12 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/window_attn/Reshape_9 ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/Concat ...
2025-07-07 02:20:43,403 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.2/attn/proj/MatMul ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.2/attn/proj/MatMul ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/attn/proj/Add ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm1/ReduceMean ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm1/Sub ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm1/Pow ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm1/Add ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm1/Sqrt ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm1/Div ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm1/Mul ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm1/Add_1 ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/Add ...
2025-07-07 02:20:43,406 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.2/mlp/fc1/MatMul ...
2025-07-07 02:20:43,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.2/mlp/fc1/MatMul ...
2025-07-07 02:20:43,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/mlp/fc1/Add ...
2025-07-07 02:20:43,408 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/mlp/act/Div ...
2025-07-07 02:20:43,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/mlp/act/Erf ...
2025-07-07 02:20:43,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/mlp/act/Add ...
2025-07-07 02:20:43,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/mlp/act/Mul ...
2025-07-07 02:20:43,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/mlp/act/Mul_1 ...
2025-07-07 02:20:43,409 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.2/mlp/fc2/MatMul ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.2/mlp/fc2/MatMul ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/mlp/fc2/Add ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm2/ReduceMean ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm2/Sub ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm2/Pow ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm2/Add ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm2/Sqrt ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm2/Div ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm2/Mul ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/norm2/Add_1 ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.2/Add_1 ...
2025-07-07 02:20:43,411 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.3/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.3/attn/qkv/body/MatMul ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Shape ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Transpose ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/qkv/body/Add ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Gather ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/Split ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Unsqueeze ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Concat ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Shape ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Shape ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Reshape ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Gather ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Gather_1 ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Gather ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/pooling/AveragePool ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Unsqueeze ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Unsqueeze_22 ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Unsqueeze ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Shape_2 ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Concat ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Concat ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Concat_9 ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Concat_13 ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Slice ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Reshape ...
2025-07-07 02:20:43,414 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Reshape ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Concat_1 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Shape_3 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Shape_2 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Reshape_1 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Gather_3 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Gather_4 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Gather_5 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Gather_2 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Gather_3 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Gather_4 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Transpose_1 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Div ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Div_1 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Div ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Div_1 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Unsqueeze_4 ...
2025-07-07 02:20:43,415 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.3/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.3/attn/anchor/body.0/reduction/MatMul ...
2025-07-07 02:20:43,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,417 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Unsqueeze_5 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Unsqueeze_6 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/reduction/Add ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Concat_1 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Concat_1 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Shape_3 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Reshape_1 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Reshape_1 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Gather_2 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Transpose ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Transpose ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Unsqueeze_4 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Reshape_2 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Reshape_2 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Concat_2 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Transpose_1 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Transpose_2 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/anchor/body.0/Reshape_2 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Gather_9 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Gather_10 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Gather_11 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Gather_13 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Gather_14 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Gather_15 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Shape_6 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Abs ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Shape_12 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Abs_1 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Shape_13 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Abs_1 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Shape_14 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Abs_2 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Shape_18 ...
2025-07-07 02:20:43,418 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Gather_6 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Gather_7 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Gather_8 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Pow ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Pow_2 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Pow_2 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Pow_4 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Div_2 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Div_3 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Unsqueeze_10 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/ReduceSum ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/ReduceSum_1 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/ReduceSum_1 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/ReduceSum_2 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Unsqueeze_11 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Unsqueeze_12 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Pow_1 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Pow_3 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Pow_3 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Pow_5 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Concat_4 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Clip ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Clip_1 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Clip_1 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Clip_2 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Reshape_4 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Expand ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Expand_1 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Expand_1 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Expand_2 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Transpose_1 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Div_2 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Div_3 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Div_6 ...
2025-07-07 02:20:43,419 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Div_7 ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Transpose_2 ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Transpose_4 ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Reshape_5 ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Transpose_3 ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.3/attn/window_attn/MatMul ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.3/attn/window_attn/MatMul ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Abs ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Shape_13 ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/attn_transform/Mul ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Pow ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/attn_transform/Add ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/ReduceSum ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/softmax/Softmax ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Pow_1 ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.3/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.3/attn/window_attn/MatMul_1 ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Clip ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Transpose_3 ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Expand ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Reshape_5 ...
2025-07-07 02:20:43,420 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Div_5 ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Shape_14 ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.3/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.3/attn/stripe_attn/MatMul ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Transpose_5 ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Gather_15 ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/attn_transform1/Mul ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.3/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.3/attn/stripe_attn/MatMul_2 ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Div_5 ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/attn_transform2/Mul ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/attn_transform1/Add ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Unsqueeze_15 ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/softmax/Softmax ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/attn_transform2/Add ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Concat_7 ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.3/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,421 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.3/attn/stripe_attn/MatMul_1 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/softmax_1/Softmax ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Reshape_7 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.3/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - MatMul doesn't have const weight. Skip to quantize
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.3/attn/stripe_attn/MatMul_3 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Transpose_4 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Transpose_6 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/window_attn/Reshape_8 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Reshape_9 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Shape_19 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Gather_19 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Div_8 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Unsqueeze_24 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Concat_11 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Reshape_11 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Transpose_7 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/stripe_attn/Reshape_12 ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/Concat ...
2025-07-07 02:20:43,422 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.3/attn/proj/MatMul ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.3/attn/proj/MatMul ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/attn/proj/Add ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm1/ReduceMean ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm1/Sub ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm1/Pow ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm1/ReduceMean_1 ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm1/Add ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm1/Sqrt ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm1/Div ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm1/Mul ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm1/Add_1 ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/Add ...
2025-07-07 02:20:43,425 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.3/mlp/fc1/MatMul ...
2025-07-07 02:20:43,427 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.3/mlp/fc1/MatMul ...
2025-07-07 02:20:43,427 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/mlp/fc1/Add ...
2025-07-07 02:20:43,428 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/mlp/act/Div ...
2025-07-07 02:20:43,428 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/mlp/act/Erf ...
2025-07-07 02:20:43,428 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/mlp/act/Add ...
2025-07-07 02:20:43,428 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/mlp/act/Mul ...
2025-07-07 02:20:43,428 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/mlp/act/Mul_1 ...
2025-07-07 02:20:43,428 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - start to quantize /layers.3/blocks.3/mlp/fc2/MatMul ...
2025-07-07 02:20:43,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - complete quantization of /layers.3/blocks.3/mlp/fc2/MatMul ...
2025-07-07 02:20:43,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/mlp/fc2/Add ...
2025-07-07 02:20:43,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm2/ReduceMean ...
2025-07-07 02:20:43,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm2/Sub ...
2025-07-07 02:20:43,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm2/Pow ...
2025-07-07 02:20:43,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm2/ReduceMean_1 ...
2025-07-07 02:20:43,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm2/Add ...
2025-07-07 02:20:43,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm2/Sqrt ...
2025-07-07 02:20:43,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm2/Div ...
2025-07-07 02:20:43,430 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm2/Mul ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/norm2/Add_1 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/blocks.3/Add_1 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/Shape ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/Transpose ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/Gather ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/Unsqueeze ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/Concat ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/Reshape ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/conv/Conv ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/Shape_2 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/Slice ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/Concat_1 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/Reshape_1 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/Transpose_1 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /layers.3/Add ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_end/ReduceMean ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_end/Sub ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_end/Pow ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_end/ReduceMean_1 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_end/Add ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_end/Sqrt ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_end/Div ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_end/Mul ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /norm_end/Add_1 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Shape_186 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Transpose_3 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Gather_79 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Unsqueeze_187 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Concat_101 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Reshape_84 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /conv_after_body/Conv ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Add_35 ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /conv_before_upsample/conv_before_upsample.0/Conv ...
2025-07-07 02:20:43,431 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /conv_before_upsample/conv_before_upsample.1/LeakyRelu ...
2025-07-07 02:20:43,432 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Resize ...
2025-07-07 02:20:43,432 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /conv_up1/Conv ...
2025-07-07 02:20:43,432 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /lrelu/LeakyRelu ...
2025-07-07 02:20:43,432 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Resize_1 ...
2025-07-07 02:20:43,432 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /conv_up2/Conv ...
2025-07-07 02:20:43,432 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /lrelu_1/LeakyRelu ...
2025-07-07 02:20:43,432 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /conv_hr/Conv ...
2025-07-07 02:20:43,432 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /lrelu_2/LeakyRelu ...
2025-07-07 02:20:43,432 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /conv_last/Conv ...
2025-07-07 02:20:43,432 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_81 ...
2025-07-07 02:20:43,432 onnxruntime.quantization.matmul_4bits_quantizer [INFO] - skip to quantize /Slice_82 ...
/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:73: UserWarning: the float32 number 2.9133301993056193e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.5454426122450968e-08 will be truncated to 1e-07
warnings.warn(
- Quantizing to q4f16: 0%| | 0/1 [00:00<?, ?it/s]
Processing /tmp/tmpjajl2j8i/model.onnx: 0%| | 0/1 [00:00<?, ?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-v0/7hYcxZ8pwavXeKpAYRaHY/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:Div, node name: /layers.0/blocks.0/attn/stripe_attn/Div_8): B has inconsistent type tensor(float16)
β
Based on model.onnx
without slimming
β³ β
q4f16
: model_q4f16.onnx
(added)
Xenova
changed pull request status to
merged