diff --git a/.gitattributes b/.gitattributes index 486ce58bc6d455919185d14139253b61f39a2b6c..a5c46c1a9cdc74b1973e42fbbe0f2d24c6e36901 100644 --- a/.gitattributes +++ b/.gitattributes @@ -5082,3 +5082,31 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_f06c3b7135d9ee55cb8e+a9d440f5/wrapped_nef neuronxcc-2.21.18209.0+043b1bf7/MODULE_0858a4338346f514c1c3+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.18209.0+043b1bf7/MODULE_0858a4338346f514c1c3+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.18209.0+043b1bf7/MODULE_8368c27a60ca92409518+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_0d48bb2409b9fd56d719+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4293af2f997e6a59e530+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b10f7bb486873b498b4+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_88ba8ae419c66c430faa+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_b8bacfafd74d5ae5ba7b+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_c10b4f4702736f1b2f66+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/7bee60b8f8f792546a54.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/7bee60b8f8f792546a54.json new file mode 100644 index 0000000000000000000000000000000000000000..70b0dec5bd0daf61ba6181eff90efb96d270be10 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/7bee60b8f8f792546a54.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 128, + "max_topk": 256, + "n_active_tokens": 128, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 128, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "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 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/858f4e0d7893e2c9daf0.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/858f4e0d7893e2c9daf0.json new file mode 100644 index 0000000000000000000000000000000000000000..dc64909f05f2a1c52519b313d6aeecb3204ff0f6 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/858f4e0d7893e2c9daf0.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 512, + "max_topk": 256, + "n_active_tokens": 512, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 512, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "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 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/90868f09ac5f3109b4c0.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/90868f09ac5f3109b4c0.json new file mode 100644 index 0000000000000000000000000000000000000000..4dc6d15e3aa12a91b1a08c8daca59cba9ae8b625 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/90868f09ac5f3109b4c0.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 512, + "max_topk": 256, + "n_active_tokens": 512, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 512, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "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 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/c54eb40c84d4cd599524.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/c54eb40c84d4cd599524.json new file mode 100644 index 0000000000000000000000000000000000000000..99a6f6ba2521bca3d7655417ce7237e874643681 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/c54eb40c84d4cd599524.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 128, + "max_topk": 256, + "n_active_tokens": 128, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 128, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "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 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/35bbdc163c6f0f272ac5.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/35bbdc163c6f0f272ac5.json new file mode 100644 index 0000000000000000000000000000000000000000..1addddbf52010160b16098c27e710fb07a86c452 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/35bbdc163c6f0f272ac5.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "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": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "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": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/5971425e59d052eef4db.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/5971425e59d052eef4db.json new file mode 100644 index 0000000000000000000000000000000000000000..372c3101d140d343ce511d73f77627427c5461ba --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/5971425e59d052eef4db.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "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": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "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": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/8e82c1b287f80ac1c5c5.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/8e82c1b287f80ac1c5c5.json new file mode 100644 index 0000000000000000000000000000000000000000..d342ce9e156335df8b95899bf269d7bab9c88e3d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/8e82c1b287f80ac1c5c5.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 5, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "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": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/91d64006319bc202bb12.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/91d64006319bc202bb12.json new file mode 100644 index 0000000000000000000000000000000000000000..59357fca4d5b60e65ea9f80093671cd7def2234a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/91d64006319bc202bb12.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "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": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "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": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/b97c760ba759013a2971.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/b97c760ba759013a2971.json new file mode 100644 index 0000000000000000000000000000000000000000..d6fe21fb7b021f93f6b0226797cb93c6fad3e0a2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/b97c760ba759013a2971.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "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": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "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": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_04a651791e36c2cfd4d1+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_04a651791e36c2cfd4d1+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_04a651791e36c2cfd4d1+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"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_04a651791e36c2cfd4d1+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_04a651791e36c2cfd4d1+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ff9e04b7e444a65b6cba5c4aa29285ada7283922 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_04a651791e36c2cfd4d1+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:911e6e37d08b0e38efd539ec20caddc0e77d717bcaa800bcb88bacbd150d1e95 +size 691139 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0d48bb2409b9fd56d719+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0d48bb2409b9fd56d719+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0d48bb2409b9fd56d719+877608f3/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", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0d48bb2409b9fd56d719+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0d48bb2409b9fd56d719+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0d48bb2409b9fd56d719+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0d48bb2409b9fd56d719+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8ce59d8f760eb514afc4033c9695ab48cd87aa3f --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0d48bb2409b9fd56d719+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68e9e600acec93fb8d4fa9742de5648b0f2c7eeb24ba072fb3410f6f445bf47e +size 1284980 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0d48bb2409b9fd56d719+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0d48bb2409b9fd56d719+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3ea4a32dc5f7bbef17a65d18853830ec73db3b0e --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0d48bb2409b9fd56d719+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65d0969600f67a5bdf9d23c2323ace4ccf6edb77cd4330e2d90552ea98311423 +size 605184 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/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", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..78ba6500e751e5408906ce83bbffd27347c90b04 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c1f8405558ed131fe9548c773e9b915c6dc96f676107cedda65b6a9cf969fba +size 1501213 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..00679682142681a1f569f3d7c6f3f9b9dd3c06eb --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_144cc55e8b0792820aa7+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1162607b2a3d5bc5dc6618cdc90bc8fdf46ee7e6179cba7e020de64bec652957 +size 7363584 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4293af2f997e6a59e530+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4293af2f997e6a59e530+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4293af2f997e6a59e530+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"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4293af2f997e6a59e530+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4293af2f997e6a59e530+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4293af2f997e6a59e530+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4293af2f997e6a59e530+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..af1c085a965a0d966041bb76465bc2c7dd9f0ca7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4293af2f997e6a59e530+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:400c878c86e4fa6f5b5ae47c51668cf1bc947006e193d941e55b68316247ad63 +size 87854 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4293af2f997e6a59e530+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4293af2f997e6a59e530+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5a0493a6a49e0ff60c9356cbd2be075773b1cda3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4293af2f997e6a59e530+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31fad8ae71aab9ec9352f98b5c014f6608a43d6d828142ae2d5b79309f981303 +size 400384 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..22ca6832999250b08bdf8a4e64e05053ff384697 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/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=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d873faf2dfaa8b158baf749fc04d5bdfd1465b40 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6820471cc3742b4adf59a1b20142e67c937c1514499868f53f2b80d1077c6f62 +size 418223 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ffed977890c926592c8948d01d510d0eaabbd2a0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8710ff580957991adbd175d321e516ded7ea97cccfc5dcd75cb1a9b0e64d227 +size 3083264 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..04ce7f0292391ab0d5c220acada59aaa86fe3663 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cba6c2d85f5d93856b6+690e2d39/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6a556cd6fe4560e978200ecdd64beaa35ab3ee2614b2c5de61c387b997171e6 +size 3157508 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5667a85ed0b09b63fe2a07561e90a837789081d2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/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=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fa08feebcbcdc494c4c695395c1940a2b105990a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:114e6541a2ea809b0dfc0aef23148d2ac33eaf99d7fdca3c6d6336946926504c +size 509380 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b7305824a1159e7ce9400a30a216b496982306ae --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_596fadcd279603bd8b65+b6452646/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ceeb73e1d39f204f2d5b6fe1d0f5f5ecea5529ce10edde0bdb5ee788508fd80 +size 34100224 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b10f7bb486873b498b4+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b10f7bb486873b498b4+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b10f7bb486873b498b4+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"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b10f7bb486873b498b4+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b10f7bb486873b498b4+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b10f7bb486873b498b4+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b10f7bb486873b498b4+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5242556fbe13ab22b7c4e252dc2d208dacf75862 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b10f7bb486873b498b4+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b3cfd2da3b26f46400eedc55c66740742be739481d71c13d69f1a6c8a5caca +size 509380 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b10f7bb486873b498b4+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b10f7bb486873b498b4+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f940760f03075315f5c6a912372f2b39650ff6e9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5b10f7bb486873b498b4+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ebe59132f4cfa1e51306f00b90dd3e4d964c2b52799eaccfec5bbf0ae04c7ac +size 41585664 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/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", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..15af4bb002c6d66a20b2ba01c2ef85aab44034c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a89b81cdfd1f7ecc8ac622f9b63727994d156bcc48d3352e607e6e8e511cfd +size 1574268 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cea00c4effe8441b2e0c5c56b86f3ee5708dbe5b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0d066ef761ee9860297dad1e6d7e44f91927f243e87667f945a482e737f8c27 +size 779264 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b980eff96d1ff9ba7cdf59e9ef487f248add41f2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5e068a10d22bfaff89f6+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe197d03460730cc644166215fa75f68171db2f467c181e9d126a9d8bca3a33 +size 787211 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/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", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1e9dcecc803da6918c9dd4a0ddaa64cabc83e7a7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:581d703b845bd5403f4104e5e4e05a8b83c0664434bf290de96203b8d392bcbb +size 1284382 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b1f0ccad450ef5360cd5e676480d6d03dde8b11e --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4be13705b296fbd2c3e864682960468372ba221c9a9d0d63280894e8c96a0e2a +size 513024 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f08ce7b064cd21437cb57be7e531ce7f685990d9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_65712ebe0144fc2b3197+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3b5870b78a4bd9c000f9624508f3dc0c14ef9b907893634f93c3d0dcdf9fbab +size 520943 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/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", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1f4aee9dceb9f4fa27bd07c12c06682f91b3d1c1 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:317710548b5edeacc5f3f03a392a524bad93de31e8aad242ce4566c00177ff67 +size 2531606 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..272606af7ca6b4b9f71cd2c20bf8a2dd3b2ef4cc --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6dc5299e05011fcdce1afa03aa5c7d1c38f45282ece45e7975388a88ddc43cc +size 4547584 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b0528daff68482f823e54a82779417a57f15d15e --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6c6ffc55476bfb49f4a5+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a389802593017b1c13fddddd315f9e7f14c2831be8ff6772155e94a48d113879 +size 4622595 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+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"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5c62298d8a08d196e9705a2dd5985a702ec26668 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7b903d94040e120e0b411edbe0e71ac2ed6b07253e5156968451f84d12dd938 +size 380010 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3929eb189a062841f926c9cc4ae7a39b463341d0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1865a28f4106bb70c0c8867bb84c4ed9fe03ec5432b6fd53867f5571abf30d76 +size 1926144 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..5bee8c0c377711d08a0c5e6d634bafa168c6e4af --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7d2a5ede35410975fb54+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff7f1d06c99e7d50a6698a62716c7dded57561dda9a9425d02fb0dfa7979d270 +size 2019200 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_88ba8ae419c66c430faa+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_88ba8ae419c66c430faa+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_88ba8ae419c66c430faa+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"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_88ba8ae419c66c430faa+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_88ba8ae419c66c430faa+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_88ba8ae419c66c430faa+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_88ba8ae419c66c430faa+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4d03558d5b2155b0ae02f5d81c4139da10ec7f2c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_88ba8ae419c66c430faa+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c172b853d2ff9c45773838b48c9bcc55ea2a6fe543878be9924d7503c7d461a8 +size 392910 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_88ba8ae419c66c430faa+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_88ba8ae419c66c430faa+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..58a97f2ba3ad63d2f4b87dc8d87846d74e7abfae --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_88ba8ae419c66c430faa+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:180dfa8ac9f3efdd2f55b280964e746310ed4b77a02be00c7c2c060762cc4612 +size 41626624 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+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"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ccfd8df1567112b5d3b3ae737d3bc010acf601b0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac09fee9beef4356d5fa3b7db4c5cc47c086e3b3d0c0d3bd4b31eb45baf9c88a +size 82753 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..115c950c00d830de6b9377d0398538018395850e --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d49099afe9c7392b31d61a5140b6e42b45afd8b726150afb9a3fe5f70b03eb11 +size 277504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..369e8f85fc1f0b32d00c48e3c4a0ccdf13ceb9ae --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9af2a07cb223b67762e0+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d85114013d12b458f8c358bf85a711981ca2db2f9c1425c4675110dfb89efcf7 +size 285854 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/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", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f98c0c2cf0efa6e27d7ce43792401ccf49db0341 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d65c29e556d1756b32a9a888d1be21835118a660e141e6f7efca43108bdba2 +size 1384595 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3cc8f2d683cdd911fcc1a9ebe772b5b0847ac29e --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:482163e936f7b99b7173234fc131b8db0258373b4421e060c1dcf22c7e6bdfbb +size 1106944 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1699ccde1245cc302899bf5e1d6f7ee5cebc7fed --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a31ae0e56d2e6654c6f5+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0d068abefa46de9fcd99296b16cbf7079ed25143381f8aac52dba12c33ecd19 +size 1181044 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b8bacfafd74d5ae5ba7b+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b8bacfafd74d5ae5ba7b+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b8bacfafd74d5ae5ba7b+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"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b8bacfafd74d5ae5ba7b+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b8bacfafd74d5ae5ba7b+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b8bacfafd74d5ae5ba7b+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b8bacfafd74d5ae5ba7b+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..03b6d1aeca9552783ec95edeb7e7020cbda2fa3a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b8bacfafd74d5ae5ba7b+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5e1da5e93f79b64e70f717818554e3ead0257d95ffe1666d25d5c7f8e3b1323 +size 83504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b8bacfafd74d5ae5ba7b+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b8bacfafd74d5ae5ba7b+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..63f5870de857642a553025b555444e0553b17231 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_b8bacfafd74d5ae5ba7b+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ced32ee0c3ac229e70811c479afcc8fe8ef2180629402ff0b4d81789562bb90c +size 287744 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c10b4f4702736f1b2f66+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c10b4f4702736f1b2f66+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c10b4f4702736f1b2f66+877608f3/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", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c10b4f4702736f1b2f66+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c10b4f4702736f1b2f66+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c10b4f4702736f1b2f66+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c10b4f4702736f1b2f66+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bae3734bdf04a5e8501b35030c542d86fb906356 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c10b4f4702736f1b2f66+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8578f48dbf8d7b09f829fe0d95961b0eeaf60b58d29c5cf2556f9eb097f3d239 +size 1289358 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c10b4f4702736f1b2f66+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c10b4f4702736f1b2f66+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..686dcf5cca7f7c3b9cd0039561fbee3ab8c29a6b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c10b4f4702736f1b2f66+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa488b4b5e89ac90d459421f6fe158488b842e3c911b2860c7289b0e165d9655 +size 728064 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/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", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f21138f57214926ca1e6c9cf5a6a3bcc01e906c2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31cc4b21f5bf875f997fd77be46e7119d198bfad059866652176a4ceed7d8b2 +size 1772495 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..56f7e5d96789737df05e3a93628183c19acdae87 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c72e1741e3ec7f054e8f+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f6cd561c58f1f4c424601de7845e388dab89adf40439586477138e5c4eded64 +size 34612224 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+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"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d873faf2dfaa8b158baf749fc04d5bdfd1465b40 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6820471cc3742b4adf59a1b20142e67c937c1514499868f53f2b80d1077c6f62 +size 418223 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..614fc6ef33f1f28f5d3fdabfd9606750e5bdb3e2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89a3559714ce52d433ff4cfb9bb9f6d4dfc8137ae15db5460a7f89335dd8b185 +size 3093504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ad8948c15ff0ae3d9b75122b407fa5c6e868320d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c96c9145e08ca93adf22+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb356189ccb8228250235a6024bbd183a42be601f4a57ad68c6a6f587c594d0d +size 3167748 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ae7e0c6790082c43cd145aae8cc7e3cc89e15ca8 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/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/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d720ab66f166d266c2852b1eef13cd4d6f0638ca --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98adcbeedb5b17438eefb927f8aebce924ed0b4c178268ce4440981f5ff8b1c0 +size 415213 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2f0a366295f94d46f0d7d22fecac0bc892870fe8 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:990b07a9ec7b778b992c3d2a913f6a1a8372804d51c7d5a741477f6f4f24b010 +size 3666944 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec19a0b1324d847a76d1+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec19a0b1324d847a76d1+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec19a0b1324d847a76d1+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"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec19a0b1324d847a76d1+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec19a0b1324d847a76d1+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8524ba47992008770be12c915fd843914dc04a9e --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec19a0b1324d847a76d1+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e79e0864d9a0cb8832a5f87390ab3fde012b08a479e8a2e6c55b1d74844efb1 +size 417652 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+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"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c5961069c2c7295f9dd0c09c8926bbc9b13d4997 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5087d0418049fbd5b4475f55a760dababad1aa115486dc375bb55b04a0d634a5 +size 83369 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..65bbcad280b1c6f92207cd39edbb4f4d3d3907f3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:033d7cf4f88be613ee1b1bca7f45b64b6a35801853dcdd16db592987d14e5dd7 +size 287744 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..efef8963ab9cc727737a0737b310fbf6c40e4e5a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f06d7905d44beb2503e412c7131e325f0bf8cebee29e016241e5438fd07379a +size 296094