Synchronizing local compiler cache.

.gitattributes

@@ -3088,3 +3088,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_68f32804712d928f41bd+2c2d707e/model.neff fi
 neuronxcc-2.13.66.0+6dfecc895/MODULE_7ac05014b1f04215fc25+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.13.66.0+6dfecc895/MODULE_1d9faae79d6d8765bf40+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.13.66.0+6dfecc895/MODULE_91f9170c89096f11ee61+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.13.66.0+6dfecc895/MODULE_5207f7054fee18b4a110+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.13.66.0+6dfecc895/MODULE_b34e819f9371decdc13f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.22/inference/mistral/mistralai/Mistral-7B-Instruct-v0.3/d9d23b589ca43e531fa2.json

@@ -0,0 +1 @@
+{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.3", "checkpoint_revision": "83e9aa141f2e28c82232fea5325f54edf17c43de", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768}

neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/gpt2/gpt2/593328a77bb235f2a8c4.json

@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}

neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/gpt2/gpt2/797982a596fe5330c2fb.json

@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 128, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}

neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/d8ff5659ffc4c4f4120b.json

@@ -0,0 +1 @@
+{"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 128, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}

neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/HuggingFaceTB/cosmo-1b/75ff34e7d936ca49b6c2.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 2048, "model_type": "llama", "neuron": {"auto_cast_type": "f16", "batch_size": 4, "checkpoint_id": "HuggingFaceTB/cosmo-1b", "checkpoint_revision": "0d5e341cfe835dffc81b6186f9715c094889f8ce", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 32000}

neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23.dev0/inference/llama/NousResearch/Meta-Llama-3-8B-Instruct/e874499a8a7dcf0e3617.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "model_type": "llama", "neuron": {"auto_cast_type": "f16", "batch_size": 4, "checkpoint_id": "NousResearch/Meta-Llama-3-8B-Instruct", "checkpoint_revision": "3cf58932fb9b7257157a1a7e4b4cf0a469b069ba", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 4096, "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": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}

neuronxcc-2.13.66.0+6dfecc895/MODULE_040e95a3833cd064be24+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.13.66.0+6dfecc895/MODULE_040e95a3833cd064be24+2c2d707e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f39b4f1337a44bedff35cae35e4f0c156161406bf6aa704a089d3bd3fa131b
+size 11202

neuronxcc-2.13.66.0+6dfecc895/MODULE_0f94ff5123a6dd8df1ac+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.13.66.0+6dfecc895/MODULE_0f94ff5123a6dd8df1ac+2c2d707e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b883e7de3ce738655156b1af1c7cb5def382644d0d45137e9532abd70f59a5
+size 54937

neuronxcc-2.13.66.0+6dfecc895/MODULE_1e3ca0be1c8b4567292c+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.13.66.0+6dfecc895/MODULE_1e3ca0be1c8b4567292c+2c2d707e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681e0fbd2456f1adbd2e11043f85bd8e90e882b520b3fb258974d3858b1d0a1a
+size 131163

neuronxcc-2.13.66.0+6dfecc895/MODULE_5207f7054fee18b4a110+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.13.66.0+6dfecc895/MODULE_5207f7054fee18b4a110+2c2d707e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8bad343f1cbb367f000f4940e28deec58cdf82484866fe94079ecc5ad526b1
+size 345685

neuronxcc-2.13.66.0+6dfecc895/MODULE_5207f7054fee18b4a110+2c2d707e/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6928b4ff36c53de9203dce24e8d826b6f853a4b87dc1bda944a59df30ba4c5bd
+size 13067264

neuronxcc-2.13.66.0+6dfecc895/MODULE_63c629dba3b610468c4c+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.13.66.0+6dfecc895/MODULE_63c629dba3b610468c4c+2c2d707e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9254f744a5ee9bf344f78cd117cb7d98851808ed2b22d6c9b0e8a82c79f3f48
+size 40738

neuronxcc-2.13.66.0+6dfecc895/MODULE_668a5df4473eac64c504+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.13.66.0+6dfecc895/MODULE_668a5df4473eac64c504+2c2d707e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2628e7e8b43ac66b76064a664f5fc5640705dfcbae814c5512937dadb6720f8f
+size 131163

neuronxcc-2.13.66.0+6dfecc895/MODULE_6d0bacb99d31e57a1a59+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.13.66.0+6dfecc895/MODULE_6d0bacb99d31e57a1a59+2c2d707e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b363f4859bd1af694a0ef5f287292f4a1110f90de800b9d78ad129acf77c062
+size 131163

neuronxcc-2.13.66.0+6dfecc895/MODULE_9986d2fb9d865fb0b43c+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.13.66.0+6dfecc895/MODULE_9986d2fb9d865fb0b43c+2c2d707e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece991fef5dde6d76bc6dc7542bd62898df2f43b08d80dcd711e4ce2c8875f5b
+size 54726

neuronxcc-2.13.66.0+6dfecc895/MODULE_b34e819f9371decdc13f+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.13.66.0+6dfecc895/MODULE_b34e819f9371decdc13f+2c2d707e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc02b4ad82af243480132faf7efd618f5161d61e59671ba5349b9c6fcc94355
+size 399041

neuronxcc-2.13.66.0+6dfecc895/MODULE_b34e819f9371decdc13f+2c2d707e/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0a11140d47a1a15ad96d4783cc8587cc6474f40f704d56b932c7431337510a
+size 10578944

neuronxcc-2.13.66.0+6dfecc895/MODULE_b7c30479d185199a4d70+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.13.66.0+6dfecc895/MODULE_b7c30479d185199a4d70+2c2d707e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb4fb14f9cd6c30d4d508009311c6bff4db85d312a3e584422ad847d47a3147
+size 131163

neuronxcc-2.13.66.0+6dfecc895/MODULE_d40e7a4b1380a0cbc49a+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.13.66.0+6dfecc895/MODULE_d40e7a4b1380a0cbc49a+2c2d707e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a17fa41f998b710eb1cfc86508c35ab4903bf45f3920fb99eb1f6cebc6517fd1
+size 11024

neuronxcc-2.13.66.0+6dfecc895/MODULE_fdef7396523d3cb4a889+2c2d707e/compile_flags.txt

@@ -0,0 +1 @@
+--model-type=transformer --auto-cast=none

neuronxcc-2.13.66.0+6dfecc895/MODULE_fdef7396523d3cb4a889+2c2d707e/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ee4154531b15dcdb89c88677e3689adb2c813ef1747bf0e94d89ca158a1b76
+size 49228