Synchronizing local compiler cache.

.gitattributes

@@ -18272,3 +18272,6 @@ neuronxcc-2.26.6360.0+6f180f47/MODULE_f7447941defc6f6c0342+665810b0/model.neff f
 neuronxcc-2.26.6360.0+6f180f47/MODULE_e090011e15ec2b236cbd+665810b0/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.26.6360.0+6f180f47/MODULE_e70e014e5ec2a1b4879d+4a27301b/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.26.6360.0+6f180f47/MODULE_e70e014e5ec2a1b4879d+4a27301b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.26.6360.0+6f180f47/MODULE_296d97c7da53bae0323d+4a27301b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.26.6360.0+6f180f47/MODULE_296d97c7da53bae0323d+4a27301b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.26.6360.0+6f180f47/MODULE_a3b4b27f33b64cd96ecf+665810b0/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3338d63843deff76593f3d84514682d027ea1b76f25961369968d0a698b30250/1e1295c1fde9cd6193ef.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": 32,
+    "capacity_factor": null,
+    "checkpoint_id": "meta-llama/Llama-3.3-70B-Instruct",
+    "checkpoint_revision": "6f6073b423013f6a7d4d9f39144961bfbfbc386b",
+    "continuous_batching": true,
+    "ep_degree": 1,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "local_ranks_size": 64,
+    "max_batch_size": 32,
+    "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_296d97c7da53bae0323d+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_296d97c7da53bae0323d+4a27301b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddac4879073bb59c9c894d1f0fc7026c8f4cb25ec9fd4c784cb11a7b82309093
+size 7040066

neuronxcc-2.26.6360.0+6f180f47/MODULE_296d97c7da53bae0323d+4a27301b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b6dcd0dc17c9700665f678652cf09f912e5b128c03383d8ff8acabeb016a637
+size 15533280

neuronxcc-2.26.6360.0+6f180f47/MODULE_296d97c7da53bae0323d+4a27301b/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd54c65afcfaabc53f2a5e01865d1c5abe6146ac38b299627c7e7920e2e00768
+size 15902383

neuronxcc-2.26.6360.0+6f180f47/MODULE_a3b4b27f33b64cd96ecf+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_a3b4b27f33b64cd96ecf+665810b0/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d3c5248a7954d3c9dc1622d85a21e3dc25eb424e2a631b7ea253d9652d3d41
+size 10129211

neuronxcc-2.26.6360.0+6f180f47/MODULE_a3b4b27f33b64cd96ecf+665810b0/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:460b550338d2b87747bc68c1f5d09ffdb393662243b47bf87effef6f0ffe92ef
+size 5270889