Synchronizing local compiler cache.

.gitattributes

@@ -12191,3 +12191,6 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_e074e1154d68365e3dff+747527b0/wrapped_nef
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_00b4a0e14fb97004e70e+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_00b4a0e14fb97004e70e+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_072b79f1482ad9ff6f00+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_1d0c24de5fb2fe347241+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_1d0c24de5fb2fe347241+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_2afc62a361935e9ff8c5+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/meta-llama/Llama-3.3-70B-Instruct/7467e08371b9c7b1b1a7.json

@@ -0,0 +1,62 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-3.3-70B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "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": 8,
+    "capacity_factor": null,
+    "checkpoint_id": "meta-llama/Llama-3.3-70B-Instruct",
+    "checkpoint_revision": "6f6073b423013f6a7d4d9f39144961bfbfbc386b",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 24,
+    "max_batch_size": 8,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 24
+  },
+  "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-2.21.18209.0+043b1bf7/MODULE_1d0c24de5fb2fe347241+a9d440f5/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", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_1d0c24de5fb2fe347241+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77177d1ae5e005b469dc2ebb3ebcbfe4e754d3bda54e0a2f9eade969c2286fe3
+size 1956181

neuronxcc-2.21.18209.0+043b1bf7/MODULE_1d0c24de5fb2fe347241+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6ebad56fb76d2973b9c3613a423f3606cc3f75ae1d0c8a4ac5281981fc06c0
+size 13906944

neuronxcc-2.21.18209.0+043b1bf7/MODULE_1d0c24de5fb2fe347241+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa33b9d9a6f128ec7182bcf7034d64f7a668975ca2ae2e5c83d8a1ea1a36172f
+size 14274929

neuronxcc-2.21.18209.0+043b1bf7/MODULE_2afc62a361935e9ff8c5+ed72d204/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", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_2afc62a361935e9ff8c5+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aecc190cd3a8a71ddd3cd0aa49f1cc0525b2f715ad94f4f9b9aa41d108c3fa9e
+size 2397394

neuronxcc-2.21.18209.0+043b1bf7/MODULE_2afc62a361935e9ff8c5+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09cbe76a30b609b25a7777c96a5ba23bf096697387dc8387fd228156269e0f4e
+size 3073024