diff --git a/.gitattributes b/.gitattributes index 9f32ef7450d1f87502937fa64749b731a4fde559..cbf0724ee28697cc0264a4c6af98c539d3bac497 100644 --- a/.gitattributes +++ b/.gitattributes @@ -8076,3 +8076,33 @@ neuronxcc-2.26.6360.0+6f180f47/MODULE_fe2cfc6d41d8e092fd79+12dd9119/model.neff f neuronxcc-2.26.6360.0+6f180f47/MODULE_3ddd9af1728ebbf92806+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.26.6360.0+6f180f47/MODULE_f937ae28aac80376b700+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.26.6360.0+6f180f47/MODULE_f937ae28aac80376b700+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/04e22cfac37c408caa51d61b493ee185fc351c2f9db86171e024b5d0ad5b25c1/c56a8bce0577ce31a594.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/04e22cfac37c408caa51d61b493ee185fc351c2f9db86171e024b5d0ad5b25c1/c56a8bce0577ce31a594.json new file mode 100644 index 0000000000000000000000000000000000000000..84c8a9548b1d66209f8318273b54d0621c516a9e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/04e22cfac37c408caa51d61b493ee185fc351c2f9db86171e024b5d0ad5b25c1/c56a8bce0577ce31a594.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-qwen3", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 36, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-qwen3", + "checkpoint_revision": "81d6f5f5e05ed53ea8a1d19431266a486e46bbd8", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "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, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/dedf7a5ae53bb6e1b3fc.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/dedf7a5ae53bb6e1b3fc.json new file mode 100644 index 0000000000000000000000000000000000000000..1d8bbd0d364536a1e660d2fb1cf3c064abfae13a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/dedf7a5ae53bb6e1b3fc.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "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, + "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": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 128, + "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-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/df8b960809b8e9d97bd2.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/df8b960809b8e9d97bd2.json new file mode 100644 index 0000000000000000000000000000000000000000..1d3fef01c2f9f494c0c66183db598cee214041f0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/df8b960809b8e9d97bd2.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "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, + "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": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "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-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3/llamafactory/tiny-random-qwen3/c56a8bce0577ce31a594.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3/llamafactory/tiny-random-qwen3/c56a8bce0577ce31a594.json new file mode 100644 index 0000000000000000000000000000000000000000..84c8a9548b1d66209f8318273b54d0621c516a9e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3/llamafactory/tiny-random-qwen3/c56a8bce0577ce31a594.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-qwen3", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 36, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-qwen3", + "checkpoint_revision": "81d6f5f5e05ed53ea8a1d19431266a486e46bbd8", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "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, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..82ffb7cbbb811418fe322fcf3dc95f77584d86f5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b0c54fd448d01bfaca6a8c8f89d6d230b2a35479ba7329ab752b71d93572c8 +size 1384895 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f115860bc1075f4a4831bea3c2d79772f5afa5ff --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f6011b6eedff21ecc70740a16b05e428af899706eea5343eb529417a0fbe13 +size 1946624 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1a2f02d18c7dc862370dda291e294d44e0c7efb1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c21a269073f2ec6aba8a67d542e7016e29fed9b50c611071237bc66e825b240 +size 2039537 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a9790cd58bfb20d885359d0bbc4f900926b03dd8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfc6c8d490cd17282445a8c5a7d48c44c5f8cd6d01f4a08c5c056ba21bba3877 +size 157192 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..912531c26666945cdefe02d3a7b02f223b781f1e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:583492cdbc8011c3e8a7399a57c2c901033f842fce27158ff8b4daa346f3f63a +size 205824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fcbd98b51bbe727fd849ac60bafddfcb021bd8da --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b6a309368147634336d212f7d5abf1a5344b9e7a837146f800f7d42944a819e +size 211973 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e28e4a3637aa7e0c96c56c30b4e73416fa25cf28 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+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"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0458f6e84149c42760428fb3c55cb7b6832ddab3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a6fc533269b6f9653c44f680c4b8f506809c81e8d005f6e265b1bc9cfb5479 +size 272044 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fd8edeac07ca632812b656d8ee93fda2b15c576e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04da6b75740e8a9aa4b37c10e0b977f8c824103a8fa62b85d38edfdc467cd577 +size 374414 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..cd1cafeadb38443e8ddd66d1412976bfe543cfd7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece6379f14596fe315bc86a7e322ffb211fd5a2e45b959e74768d1b0ae20df62 +size 382210 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e5c829238cb266352287645955b1f074de42c58a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2627dce527832dbdb1497c61a5cdaee1d0f7b02140ac543a93f66510f1357957 +size 195287 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..df73324247f835b6a393f02119ce54e9d8c2176f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f32e1ad61ad1f8da22fd44a647d3df3f1dcc4b4bb9b9d17f88e421651340b05c +size 318464 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..10880a1a48a6d3e324e2d2b947237965bfe7029a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eadac5b46718f86a1caf26c09bbfa58f3791fcf575865ac88d104cb0b566ba4 +size 1003294 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b72c229a5266bc5d6fe92c3b23f0168e4a356f39 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6bea7eaf64552d3fea1f24e3b2c1ef85d13b90ce49c8b00e9a084bca384c5a4 +size 5633024 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..dbc1e20c6e979343e16bdb54705634b17d501955 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cbb70674d43a79e877fa0e937f7247ee31b03e864e8797460dc911ef21153d5 +size 204291 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..efa382a79d24d2c85afaf583f944c88737eedaac --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c01053853e045806e2855ef7791f3d955bd07797bdc4e94fb6274d3a166fec5 +size 287744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..23333f396509c6f3747252892313dc013437409a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/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/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..538d24eb4bd67a8ba760add803dd9d464de06707 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b224244b6ba07f7aec2feffbdc1e1ce476bcb327e579e676e39321787b0f69a +size 258494 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9d880b92420c7a7fd9eb0c4f0f75c4567cbb0ccf --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e6e047b663fac0ba12512caed6d51e32de3b3c9aeb1f0200abd6f0e33ad227 +size 318601 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4bf48cedebf320b0c5081c9342d4238acb70fdfd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87551c425d5a4545bedd0afacddec45628d5eb93d3733f6b3b09bc48b411558e +size 220920 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f559e728fcaf36648fdd1a831c37af68eedda81d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90bc5ec65ac5275b84c82d6342a170e6ea1dc1172b7e496f0d7c3e2272d4394a +size 246784 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..789667eb41ab8c8f609b3b7a0c8a7f08d727e2d4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:376d6c47055c7a84fc8865ddef4c63c9e23aae2eaecee00e437a75966b727c39 +size 254997 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..88b44446245646668212f7f5490735f1b32e5842 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e647593ac79f1aad7b98176515c1c2b6e589d704e2f2dc48c51bebfaa4c43f56 +size 1437353 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8373d36db7a073591b3447b8655cef0494c9a433 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf7ab149507a1959fee6bb162328ec57acece883c6e20806d513b862054a62c +size 2253824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fcfbc65eded9426b298ffe1b13bbbc1d3252bd89 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9651465fb64d85368fdbc48eb2c00af128668c2dabff4b50560a805bec46fa67 +size 2328023 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d84fb4f20a6b4ba739533518b2bc90aaf1d82312 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d44c889a3753fa7589ac216ad9a2df194384f05a7de7be8c250c86e35fb50a +size 156253 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..dffd62a90c9ecf0d5b26e97fe02cdb4ced4448d9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb850d50a75f52890e4262c645a6424c79da8881051a2e092547f2d027a28364 +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3ed7cdba5ef44a455bcc300e2c72fa63043aa03b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020b3226eeb42ce0aadfedf83c76542ad97fb7a8f5882e2be787a2649be5d30b +size 1281258 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3814ac4a9f79413917e0307bbf6a5e3503d86ff5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96bf1a392ca04ea1f24b0970acebf4ab3da4d1e7e5407864a6c44f6c62b23507 +size 3267584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5d5f55d8a61ad692c8a9905e7ac124cc76a636ad --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453d181e4e02fea281f7d7e96354b5790dcd122da1af0c0f9cd671d9d2dea6e7 +size 246664 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..044a693b854d7f078629a15087c865cdcd44453b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a245efb43e0bc49d3d9e1e20e286ece9c227cbe1f5e9cae281191edd1c14c5 +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bc8ac477df36cb96322c190748055a3557dd0f46 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00fb9406bd2cdfef4eac1be94b62473abab868ed548085d5a79cd64b3e063318 +size 269001 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d7547bbd31ff750e8e73a0e905530dfcd8af696e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378748ea944cd50b5741529a83703bc140ef42cf971a64ba5ea92c801b2e06ab +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a6f0ef17f922c259a11f3c64d81e69d702194e1d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a131d1d80f04b6b1e1870ac33de53df8a4acad2c610a105312e02e6f7e2268 +size 234517 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b6c20b995ba5a1d8db7f11da26b7b5567c9bd05c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad0c6944a2643e4157a2c4a94659a84fe9f6e76ac9c30ac67148f842e8ee8cf1 +size 1440206 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..55d5627ec8a9e29dd273128a183ba4d2f340691a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d6fbe10adcb6dba5be99816fd79a15c815398d4c134c65ad3ecf8b9cbbe6e0 +size 2253824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..30196375f8b523e229cf29406f4594c7135a6464 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd94a17f7434507428cbb4a5288051b07fd38e2e974d0e255d29010c334170e +size 2328023 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c5408e82de9ffc6a691997e9ac38d9e72111fc45 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae4f7766dfa6d1ef493c782841c199569d912b36c41f20fcbe6d913d2c2a182e +size 1284078 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3abca73e0a863f3aabc9f360243e863ebefc5a70 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22d1fa6bf378311574a7d4ae4a2c3a72253f21de2dfbfe2a70589c2ed5ed2a7 +size 3267584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..95196af4946ea37f863ed8de3258d824cec9fea9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a116a020066fc50e307b10bdde4e9ffb0d1a2e9c7191237e62497a15e4c90ae +size 221634 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bb536bc29b4302532b81db5c522f962eb9980c03 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78549d0495f698a88a0f60c13d9a230366b36e1c38567b48fde708b1b0af5ec9 +size 267264 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..53716fd5f3f619b673e294ab2b617799624f5682 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e252918450884c004fe2164e046d901b30ab14e0b321dea8a69c3991061bf218 +size 1436432 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3e23cc4276f01a2455f4bb3468dacec07da9498a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7bdd221f815c567c9c3c4039706974b83d0987612ed2208e25cf5b94914c48f +size 2253824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..647fe86df645292d1cf7cac9355caf306904d757 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ba931a2848b10dcb36ce6acb99ce7d8317edd5713a2a8d7233b87874e7c3f97 +size 2328023 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..50d949def2ddfcf70e1fc7b0915bf68c974e28f9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b024a86abbbb08a23506216820912402ebc18b09a457a5f30bc7eadb0c9ad378 +size 241800 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0e1b65b4f679394fe26291f5505a7e206d708333 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a5c19c3c44dc5f0a7bada64a098b226666b06dfb84cd66e57406e899064b5ae +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7ae60f7b91448bf8adfbc73703c2a70d45ab8a3f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e80adcbd149a6cc88cdf46dada3180b46a9885cadb7a6c4645b99e2ede8ff3 +size 234517 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..c27e6c39a7a4c3b736e614d7725e8bfa29486eb1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/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", "--verbose=35", "--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-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5902ae6960596566a5e4df05a31e7c0fa2b4790d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e98b223113ebe071c2c8d74b1b66d1ab79ac18c699ec69b869b95462251284 +size 1559140 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4e9dd31214eaa9e6962f32083af029c429bc7683 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4de3dcf7b5774e6bd371bc253c48cd2eda21fbce680be38d55dc604a4ff21a82 +size 3656704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..27adb4c0539151876bd1516cf4401a96c158a707 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2174fa839ce5e178289e91216b4d433a8bfabbaa8816752ec6d9b3a45de2e4bd +size 209487 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..284c715d42d839d6131216915444ef78a2a860d8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd0e4841d782d22bd918e7c6a301ac555ed6cb87ce1663845cce3ce8fab946d +size 297984 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1ef82fdbafd16dbbe9767552f8a06b4cb5ba07c9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd1b71919afbf955a2c39dc4adfc803c920a48d2c0cff43efcc2e41ff9d1fad +size 306129