Synchronizing local compiler cache.

.gitattributes

@@ -8477,3 +8477,7 @@ neuronxcc-2.17.194.0+d312836f/MODULE_e6999889c1aa48a9a2bd+165e9558/wrapped_neff.
 neuronxcc-2.17.194.0+d312836f/MODULE_8721c425db97335607af+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_b53ded824fa587d49391+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_b53ded824fa587d49391+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_0bf7b69b289842d41ae8+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_6937ec25fae3c7ef5164+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_6937ec25fae3c7ef5164+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_74bd441e7f0dbdf5d121+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/Qwen/Qwen2.5-0.5B/e1226cd19c109531ddcf.json

@@ -0,0 +1,71 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-0.5B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "Qwen/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.0.dev0",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 4096,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.17.194.0+d312836f/MODULE_0bf7b69b289842d41ae8+bfe5714b/compile_flags.json

@@ -0,0 +1 @@
+"--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2  --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"

neuronxcc-2.17.194.0+d312836f/MODULE_0bf7b69b289842d41ae8+bfe5714b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e670f2a3a24d155ee645b07ea70759a8f2f6ef97dd6d15dbcb1f4da28bb82f
+size 752845

neuronxcc-2.17.194.0+d312836f/MODULE_0bf7b69b289842d41ae8+bfe5714b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2495cad9895fbe5ce5939e59c94dbd97ab1b8504abb36e9d84601d9b96da29
+size 19600384

neuronxcc-2.17.194.0+d312836f/MODULE_6937ec25fae3c7ef5164+165e9558/compile_flags.json

@@ -0,0 +1 @@
+"--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2  --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper"

neuronxcc-2.17.194.0+d312836f/MODULE_6937ec25fae3c7ef5164+165e9558/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f2d05f9e42489fa5e84a3984f5dd65fa218e874af3cfd727a92ae4bc31d7651
+size 681084

neuronxcc-2.17.194.0+d312836f/MODULE_6937ec25fae3c7ef5164+165e9558/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf3000ed6794c2957483f02a30fd74b5f290a9d66dcfb7294bbe2c99fc1cea4c
+size 1178624

neuronxcc-2.17.194.0+d312836f/MODULE_6937ec25fae3c7ef5164+165e9558/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7098ea5f61932ed7047cd903528bb6c102166dd1325d18452240352ede7095d1
+size 1323650

neuronxcc-2.17.194.0+d312836f/MODULE_74bd441e7f0dbdf5d121+431f5505/compile_flags.json

@@ -0,0 +1 @@
+"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"

neuronxcc-2.17.194.0+d312836f/MODULE_74bd441e7f0dbdf5d121+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8327b531c0dc4e7d0709cad817676195a514358ee59fdf338aae5488d9521e1c
+size 149919

neuronxcc-2.17.194.0+d312836f/MODULE_74bd441e7f0dbdf5d121+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1e6bc659b8c242a90cff3cc5dcc064332e4e8b4119329dacc5312af85e9dbc
+size 594944