Synchronizing local compiler cache.

.gitattributes

@@ -8294,3 +8294,7 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_284cb3ffef586348809d+613edded/model.neff fi
 neuronxcc-2.16.372.0+4a9b2326/MODULE_629b0269219133666d97+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.16.372.0+4a9b2326/MODULE_841dfee8bfd94697be95+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.16.372.0+4a9b2326/MODULE_cf84f1c0bff507b086e0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_1ec970130638677f3187+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_767aaffd027b9e3b85b0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_8d85280a9a94b88c7245+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.16.372.0+4a9b2326/MODULE_b306ecc47e279296f3d4+613edded/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/4f56f0236d31f8831a36.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 10240, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "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, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/llama/meta-llama/Meta-Llama-3.1-8B-Instruct/d4c09c8f8e6120b43b61.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 4, "sequence_length": 10240, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "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, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.16.372.0+4a9b2326/MODULE_1ec970130638677f3187+613edded/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]

neuronxcc-2.16.372.0+4a9b2326/MODULE_1ec970130638677f3187+613edded/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ac9e70dc2a9e02e2ff1dbab801e5fed9bbc34e5dc4143700eaa36f48ad2892
+size 363704

neuronxcc-2.16.372.0+4a9b2326/MODULE_1ec970130638677f3187+613edded/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b148886d403a86936550cdd4b2224b57e834a0ac226f7cead3ab9718e3a018
+size 16036864

neuronxcc-2.16.372.0+4a9b2326/MODULE_767aaffd027b9e3b85b0+613edded/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]

neuronxcc-2.16.372.0+4a9b2326/MODULE_767aaffd027b9e3b85b0+613edded/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61377b0921d1cddff79bb6ceecdcb05152178a1dc1d4706b96fd21e8647f9399
+size 446738

neuronxcc-2.16.372.0+4a9b2326/MODULE_767aaffd027b9e3b85b0+613edded/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:928ea7ffd81cc36ebd187c9b9618b0dbd9c91f7d618962180f43fb0f1a8b526f
+size 10466304

neuronxcc-2.16.372.0+4a9b2326/MODULE_8d85280a9a94b88c7245+613edded/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]

neuronxcc-2.16.372.0+4a9b2326/MODULE_8d85280a9a94b88c7245+613edded/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63178548145c3c59115eadbbf3bc0c74f3a2c1a53e36e55f64ce7689d9ea4a43
+size 363832

neuronxcc-2.16.372.0+4a9b2326/MODULE_8d85280a9a94b88c7245+613edded/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c150d4403b16c84fca3e64e4d2c1ff84e719786c81ad0746e8e33f8fab54e89
+size 29819904

neuronxcc-2.16.372.0+4a9b2326/MODULE_b306ecc47e279296f3d4+613edded/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]

neuronxcc-2.16.372.0+4a9b2326/MODULE_b306ecc47e279296f3d4+613edded/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf869eef71e92a6260210ed05cd3f322326aa849b5cd0c8ff337f27987e31ed5
+size 447122

neuronxcc-2.16.372.0+4a9b2326/MODULE_b306ecc47e279296f3d4+613edded/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:686619450548bc63696bd1588568ece25991f98171a3ca3396a0b66f65101b05
+size 19846144