Synchronizing local compiler cache.

.gitattributes

@@ -7307,3 +7307,6 @@ neuronxcc-2.23.6484.0+3b612583/MODULE_fa3c837be0618d501d18+84337dd9/wrapped_neff
 neuronxcc-2.23.6484.0+3b612583/MODULE_38e62965360cbacf1bd8+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.23.6484.0+3b612583/MODULE_5092f2052a543a2f5d04+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.23.6484.0+3b612583/MODULE_5092f2052a543a2f5d04+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_243af0abd9eb068822fe+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_243af0abd9eb068822fe+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.23.6484.0+3b612583/MODULE_8648a6d0cbd639733a91+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/8854ff8426cd13b49102.json

@@ -0,0 +1,83 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-0.5B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "continuous_batching": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "max_batch_size": 1,
+    "max_context_length": 8192,
+    "max_topk": 256,
+    "n_active_tokens": 8192,
+    "neuronxcc_version": "2.23.6484.0+3b612583",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.6.dev3",
+    "output_logits": false,
+    "pp_degree": 1,
+    "prefill_chunk_size": 1024,
+    "sequence_length": 8192,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "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": null,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.23.6484.0+3b612583/MODULE_243af0abd9eb068822fe+84337dd9/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.23.6484.0+3b612583/MODULE_243af0abd9eb068822fe+84337dd9/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff76e5d78d0904b62e5e139e8a802530fe14d7d2240933ed0c6c43db6248419
+size 2180086

neuronxcc-2.23.6484.0+3b612583/MODULE_243af0abd9eb068822fe+84337dd9/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a76dc74dc00337119876675e04a02c00e2d8fb511220e59c2e977ccd904649fd
+size 2089984

neuronxcc-2.23.6484.0+3b612583/MODULE_243af0abd9eb068822fe+84337dd9/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6ed3a5b0f427bf52110b3272ef7c73541e10a3669ec62c6a0ac77bc7d031e7
+size 2246292

neuronxcc-2.23.6484.0+3b612583/MODULE_8648a6d0cbd639733a91+12dd9119/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.23.6484.0+3b612583/MODULE_8648a6d0cbd639733a91+12dd9119/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f8dab5a12d82ebd71a695955d8e56a3edf342750069ba2faaec136360becf3
+size 2904205

neuronxcc-2.23.6484.0+3b612583/MODULE_8648a6d0cbd639733a91+12dd9119/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9bd53ba1fadd5b3af9ceaff480fc569822038e6964b037912bf0c128bb07fa
+size 16323584