Synchronizing local compiler cache.

.gitattributes

@@ -18266,3 +18266,6 @@ neuronxcc-2.26.6360.0+6f180f47/MODULE_59e76bb4c209c3794292+4a27301b/wrapped_neff
 neuronxcc-2.26.6360.0+6f180f47/MODULE_30392b442a4f968fe98e+665810b0/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.26.6360.0+6f180f47/MODULE_8d0d6be159b7f241660b+4a27301b/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.26.6360.0+6f180f47/MODULE_8d0d6be159b7f241660b+4a27301b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.26.6360.0+6f180f47/MODULE_f4c45f346593438822e0+4a27301b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.26.6360.0+6f180f47/MODULE_f4c45f346593438822e0+4a27301b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.26.6360.0+6f180f47/MODULE_f7447941defc6f6c0342+665810b0/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3338d63843deff76593f3d84514682d027ea1b76f25961369968d0a698b30250/affc22aa5cd6a9bc0b92.json

@@ -0,0 +1,63 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-3.3-70B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "meta-llama/Llama-3.3-70B-Instruct",
+    "checkpoint_revision": "6f6073b423013f6a7d4d9f39144961bfbfbc386b",
+    "continuous_batching": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 64,
+    "max_batch_size": 1,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "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": 1024,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn2",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 64
+  },
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.26.6360.0+6f180f47/MODULE_f4c45f346593438822e0+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_f4c45f346593438822e0+4a27301b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e730b6be586c5fbf5885cb60f2324d24d0a6056e6c13fb377bb5a4409792104e
+size 7036692

neuronxcc-2.26.6360.0+6f180f47/MODULE_f4c45f346593438822e0+4a27301b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c87960396d92fa4162656360509d4c2d2382a5dfdc46adc94b14c808dafc96
+size 5126026

neuronxcc-2.26.6360.0+6f180f47/MODULE_f4c45f346593438822e0+4a27301b/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc028069976f6e98222ae6edfe9803f0ebd155e4711732b5233d49aa4a813cd
+size 5495129

neuronxcc-2.26.6360.0+6f180f47/MODULE_f7447941defc6f6c0342+665810b0/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.26.6360.0+6f180f47/MODULE_f7447941defc6f6c0342+665810b0/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b654ce43fb646f46a26608ccb4744ede57fda078aa486ae118438de6bea5dea
+size 9528000

neuronxcc-2.26.6360.0+6f180f47/MODULE_f7447941defc6f6c0342+665810b0/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029cfc163192366211e5a91b6ec8c358c23c1de50753bb5b69de7bd407a0ae85
+size 5549363