Synchronizing local compiler cache.

.gitattributes

@@ -8404,3 +8404,6 @@ neuronxcc-2.26.6360.0+6f180f47/MODULE_d6648ef17ad6a5b086bb+4a27301b/wrapped_neff
 neuronxcc-2.26.6360.0+6f180f47/MODULE_38813cc328d13a3d1cdd+4a27301b/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.26.6360.0+6f180f47/MODULE_38813cc328d13a3d1cdd+4a27301b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.26.6360.0+6f180f47/MODULE_4439375f8e706263d170+665810b0/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.26.6360.0+6f180f47/MODULE_0fc60c325d23030012df+4a27301b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.26.6360.0+6f180f47/MODULE_0fc60c325d23030012df+4a27301b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.26.6360.0+6f180f47/MODULE_496ba1d3708358fbe356+e457fe88/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/29ec25a4b7a96168f6a7.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": 4,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "continuous_batching": true,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 4,
+    "max_batch_size": 4,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "neuronxcc_version": "2.26.6360.0+6f180f47",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.7.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "prefill_chunk_size": 0,
+    "sequence_length": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn2",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 4
+  },
+  "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-2.26.6360.0+6f180f47/MODULE_0fc60c325d23030012df+4a27301b/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.26.6360.0+6f180f47/MODULE_0fc60c325d23030012df+4a27301b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4122876cae0e201cd4075bcc682f3b98211b7ccee41a4dfc04159b4fb02c74cb
+size 620103

neuronxcc-2.26.6360.0+6f180f47/MODULE_0fc60c325d23030012df+4a27301b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd38bad2986952365525b89263e2d46b5f2041c3bb686789c828adf3a5000ef6
+size 1452828

neuronxcc-2.26.6360.0+6f180f47/MODULE_0fc60c325d23030012df+4a27301b/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20790d2de4f550775c3d1564d3f171f4399b633ca09f4740cffc56946cca1507
+size 1609638

neuronxcc-2.26.6360.0+6f180f47/MODULE_496ba1d3708358fbe356+e457fe88/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.26.6360.0+6f180f47/MODULE_496ba1d3708358fbe356+e457fe88/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69365e364db876384b765b3ef2a135a93af080d642521e4d202547d72aab646d
+size 854251

neuronxcc-2.26.6360.0+6f180f47/MODULE_496ba1d3708358fbe356+e457fe88/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be80307a7670bb9391a1eb9c4485552b9b18b80151fa059fdef25aba1bf2809
+size 2741483