diff --git a/.gitattributes b/.gitattributes index 22c5d5f4aea0442230880cdae0a6e9a30d3543e8..e70a472c9f7083e0faf959ac333e7056a12066c6 100644 --- a/.gitattributes +++ b/.gitattributes @@ -8296,3 +8296,72 @@ neuronxcc-2.26.6360.0+6f180f47/MODULE_1eff146175c8d58ac489+1d5aa319/wrapped_neff neuronxcc-2.26.6360.0+6f180f47/MODULE_d76067ed2e537c3aec65+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.26.6360.0+6f180f47/MODULE_d76067ed2e537c3aec65+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.26.6360.0+6f180f47/MODULE_e48a46eab0bc20001335+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_1283f6f31da959d41a79+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_1a557b2c80ce65011518+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_21bd7f101bf772193919+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_43a9ff96794aab5702ff+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_478ffa3f4b20dee50183+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_55d397ffb598606a9f74+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_613aff52871f55f15829+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_76c36cfb450c294eea96+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8172a8105d980618995c+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8ab4d2b4c4e73492c47d+a276e327/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8ffd7832a009c4667731+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_95c0740536c036e45e44+6aa1814a/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_be8a773fa44cd102fb0e+0788fa03/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c1a9f0fcf68d69705313+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_cc8875d5ba1caa64828e+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ce0f36dc6df4a699aa76+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ce4120480a980027dc50+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_d333fdfbebb9aac194c8+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e89d4411ae8f214d3e9f+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_fbab51725e51c7e1ba64+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_fee5fa3b97115a883ace+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3_text/unsloth/gemma-3-270m-it/9c9ee497483f6449ebfe.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3_text/unsloth/gemma-3-270m-it/9c9ee497483f6449ebfe.json new file mode 100644 index 0000000000000000000000000000000000000000..a91d1eb5b53b8ed42dae9257153ebc32aa9fbf4c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3_text/unsloth/gemma-3-270m-it/9c9ee497483f6449ebfe.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/gemma-3-270m-it", + "_sliding_window_pattern": 6, + "_task": "text-generation", + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/gemma-3-270m-it", + "checkpoint_revision": "23cf460f6bb16954176b3ddcc8d4f250501458a9", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "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": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 512, + "unsloth_fixed": true, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/idefics3/HuggingFaceTB/SmolVLM-256M-Instruct/7b7cbf8b550c8ee1a872.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/idefics3/HuggingFaceTB/SmolVLM-256M-Instruct/7b7cbf8b550c8ee1a872.json new file mode 100644 index 0000000000000000000000000000000000000000..8254f008bfaf9d443465e906c24895ae0393bc64 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/idefics3/HuggingFaceTB/SmolVLM-256M-Instruct/7b7cbf8b550c8ee1a872.json @@ -0,0 +1,189 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolVLM-256M-Instruct", + "_task": "image-text-to-text", + "architectures": [ + "Idefics3ForConditionalGeneration" + ], + "dtype": "bfloat16", + "image_token_id": 49190, + "model_type": "idefics3", + "neuron": { + "_serialized_key": "NxDVLMNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolVLM-256M-Instruct", + "checkpoint_revision": "7e3e67edbbed1bf9888184d9df282b700a323964", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "image_seq_len": 64, + "image_size": 512, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 2048, + "max_num_images": 17, + "max_topk": 256, + "n_active_tokens": 2048, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 2048, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "scale_factor": 4, + "text_config": { + "_attn_implementation_autoset": false, + "_flash_attn_2_enabled": true, + "_name_or_path": "None", + "architectures": [ + "VLlama3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 576, + "initializer_range": 0.041666666666666664, + "intermediate_size": 1536, + "is_llama_config": true, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "neftune_noise_alpha": 0.0, + "num_attention_heads": 9, + "num_hidden_layers": 30, + "num_key_value_heads": 3, + "pad_token_id": 2, + "perceiver_config": { + "_attn_implementation_autoset": false, + "_name_or_path": "", + "add_cross_attention": false, + "architectures": null, + "attention_dropout": 0.0, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "silu", + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "model_type": "vllama3", + "no_repeat_ngram_size": 0, + "num_beam_groups": 1, + "num_beams": 1, + "num_key_value_heads": 1, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "qk_layer_norms_perceiver": false, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "resampler_depth": 6, + "resampler_head_dim": 96, + "resampler_n_heads": 16, + "resampler_n_latents": 64, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": null, + "torchscript": false, + "transformers_version": "4.46.0", + "typical_p": 1.0, + "use_bfloat16": false + }, + "pixel_shuffle_factor": 4, + "pretraining_tp": 1, + "qk_layer_norms": false, + "rms_norm_eps": 1e-05, + "rope_interleaved": false, + "rope_scaling": null, + "rope_theta": 100000, + "transformers.js_config": { + "kv_cache_dtype": { + "fp16": "float16", + "q4f16": "float16" + } + }, + "use_cache": true, + "use_resampler": false, + "vocab_size": 49280 + }, + "tie_word_embeddings": false, + "transformers.js_config": { + "kv_cache_dtype": { + "fp16": "float16", + "q4f16": "float16" + } + }, + "use_cache": true, + "vision_config": { + "_attn_implementation_autoset": false, + "attention_dropout": 0.0, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 768, + "image_size": 512, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-06, + "max_image_size": { + "longest_edge": 512 + }, + "model_type": "idefics3_vision", + "num_attention_heads": 12, + "num_channels": 3, + "num_hidden_layers": 12, + "patch_size": 16, + "size": { + "longest_edge": 2048 + }, + "tie_word_embeddings": false, + "use_base_siglip": true + }, + "vocab_size": 49280 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/unsloth/Llama-3.2-1B-Instruct/d391df1950611ad2a02d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/unsloth/Llama-3.2-1B-Instruct/d391df1950611ad2a02d.json new file mode 100644 index 0000000000000000000000000000000000000000..5919a012c3b95b7e1a23942e8a3a482e3bdbbc5e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/unsloth/Llama-3.2-1B-Instruct/d391df1950611ad2a02d.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, + "dtype": "bfloat16", + "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, + "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": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 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-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/4a919ffcd2cabc839f97.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/4a919ffcd2cabc839f97.json new file mode 100644 index 0000000000000000000000000000000000000000..41cba1d99df5f6d845a23d6a65e85e14453d0d0b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/4a919ffcd2cabc839f97.json @@ -0,0 +1,135 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "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": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+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_1130d9f8be6166d81790+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9864d7601414612cc803d4248a5703dce9de5fc4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eb5148110d22dc53a14c3c8026dc89a70e4c52e3b2d83ce5f0e5024d7d10f8a +size 2912487 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ef0f3b3219ecbdcdcb7d21e8655a9ad4ce669e24 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d54efc07a921a96aae30760ee93ba3b3a306f1b1db48f3e602260c6543c65a20 +size 2212864 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c2729899516490fba194219f77cc336c48103e29 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1130d9f8be6166d81790+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c667c927206b667b4661c3d8495e1261952438b28112e67c8f33fe2deb93d5 +size 2323745 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1283f6f31da959d41a79+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1283f6f31da959d41a79+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1283f6f31da959d41a79+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_1283f6f31da959d41a79+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1283f6f31da959d41a79+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1283f6f31da959d41a79+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1283f6f31da959d41a79+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e45381ae345c9ce6e938a62fb3e17f7317b8319b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1283f6f31da959d41a79+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:071b63cae69c898ca12a59f203e63f64fa8fac2751ce44a33526189239271ac7 +size 284757 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1283f6f31da959d41a79+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1283f6f31da959d41a79+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..173e3422d607b512d703974847eddb3160c0550b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1283f6f31da959d41a79+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc056d4aefe787bc2e278b217242654e19d68c89a9c254bdb8abb11eed44bb2 +size 297984 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1a557b2c80ce65011518+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1a557b2c80ce65011518+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1a557b2c80ce65011518+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_1a557b2c80ce65011518+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1a557b2c80ce65011518+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1a557b2c80ce65011518+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1a557b2c80ce65011518+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b48f468d2066e90e0fd01aca93483d6b2810e21f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1a557b2c80ce65011518+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f68a36dc0e38524001b787c8ff708e7a842e0ba5d516917ff2cbc1cb8c554c76 +size 284320 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1a557b2c80ce65011518+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1a557b2c80ce65011518+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ede47863fa8b8c75cb26cde14607c8b13c7750ea --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1a557b2c80ce65011518+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d712302caec87510f85eebc43cf46d74ad099d03fdff5d73bc8247fd959e66 +size 297984 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21bd7f101bf772193919+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21bd7f101bf772193919+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21bd7f101bf772193919+12dd9119/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21bd7f101bf772193919+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21bd7f101bf772193919+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21bd7f101bf772193919+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21bd7f101bf772193919+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..caa8e123fd05baa51b348ab3362e2c614e140653 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21bd7f101bf772193919+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05318cacc7d1ee0a48bc69538c7c467c8cef4b2f2cd4dfa9f398ed35c01072b9 +size 3874213 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21bd7f101bf772193919+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21bd7f101bf772193919+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c384759f6dd1ba166ca896e32c1fb4324317075d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21bd7f101bf772193919+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3d768e1eaf3972a406fff5d95027581e2f30ad3118a99a6b6fe5be79bda9b90 +size 10609664 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9637a8418978fd74f1836f815e9bc6a9dbb32800 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/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/vision_encoder/_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_3256c2ed9d42c3220d87+1d5aa319/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bd02ed9fa918b545944ff8806531d81c92499004 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:506133c0eb90560b8702375d3aa0a87293f93f8ad370e3fece553b6b38ffd09a +size 755318 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..11d0252eeda9aa0bec0ad096fedaaf715ecdd88f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed35afc7217386c012d3f2bbba50388d346b28278c6a8ff5a981b59d690c0b2e +size 5520384 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ebe0c1915fcfbee968db1d9122469bb3d23a4c39 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3256c2ed9d42c3220d87+1d5aa319/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20085a48bdebdbace0786875c9257cb7ff07bb4630460a41f8842e4155c976d7 +size 5630549 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9637a8418978fd74f1836f815e9bc6a9dbb32800 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/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/vision_encoder/_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_34cd8d0ad669d6c33691+1d5aa319/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..04f156c7b7e67811adc497d2eb7f3c59c7eb5b19 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51da95ccb2598e4e3c0f743b33e44128e508dbd623d5b94fa198997584113d98 +size 757821 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c2a9a3542cc19c86133dbe3f6d46635a72c2d614 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f64c8cbc5674e0e375bdd6ccad864c9fc2e9ae3ddaba5e4f73ebedfc999b28a1 +size 5520384 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..08712c442553d401eee0a70c55df2ce97b10eec6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_34cd8d0ad669d6c33691+1d5aa319/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f171c8f6bdc712621b475d655f3c623c96d0806a79d8399f7760820b261ef6b4 +size 5630549 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_43a9ff96794aab5702ff+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_43a9ff96794aab5702ff+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_43a9ff96794aab5702ff+12dd9119/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_43a9ff96794aab5702ff+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_43a9ff96794aab5702ff+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_43a9ff96794aab5702ff+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_43a9ff96794aab5702ff+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2d3c7396d840b12510ae5ed77fdf63c1ed7361b9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_43a9ff96794aab5702ff+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0798876cdf00b2e9214c4d22e2c4dc9f6286adb11930c7955e29a1500d875648 +size 3866413 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_43a9ff96794aab5702ff+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_43a9ff96794aab5702ff+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0a6f41fa9777c0498b655fff2c731221947ed4dc --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_43a9ff96794aab5702ff+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2add3454841604d019b76b904c0f6e39c9724070043125b6bc54ae76afee23c +size 10609664 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_478ffa3f4b20dee50183+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_478ffa3f4b20dee50183+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_478ffa3f4b20dee50183+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_478ffa3f4b20dee50183+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_478ffa3f4b20dee50183+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_478ffa3f4b20dee50183+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_478ffa3f4b20dee50183+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7f53c55c660b4ad54aaf6c876b7abaf9aa874da2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_478ffa3f4b20dee50183+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eef5f8638d29cc818077f5f558be8245e0a9d92bda7307acc301c4878483796c +size 233296 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_478ffa3f4b20dee50183+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_478ffa3f4b20dee50183+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..490b242cc5e059454d54164655c1864502fce478 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_478ffa3f4b20dee50183+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6c20ad55c8d18f9287ba3c45d735eb61de057793c663e844da8dee58cda480 +size 287744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+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_49d38a4ae9db0081fa49+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..37c98ea2273267f1e15423eef49ba0fdc04910d0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0de6d54470c0bac97806dc6e507f60f25586d90303b22dd0e401af5b3bedab3 +size 2903569 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5e7d8cc9b98cff046381cb0f5d255a87c71015b2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19960222790d84cb25b08b8f0aa79b670b3158c3e22242f5777d0334972f433d +size 2212864 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..28eaceff08c8531fee76e7ac428f06e8b5068f46 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_49d38a4ae9db0081fa49+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6398db964d5d94e7dd2e2b9ad718ac25de7d45edf51485e3c8141cfff4bae7f +size 2323745 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d397ffb598606a9f74+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d397ffb598606a9f74+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d397ffb598606a9f74+12dd9119/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d397ffb598606a9f74+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d397ffb598606a9f74+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d397ffb598606a9f74+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d397ffb598606a9f74+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f8749ec6ff95c33fa8922fe005e4553f9fe90522 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d397ffb598606a9f74+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0040a61664afe67e4e85dccaa8966779e0be39e4ec2fad1f6f4d3cdf60f11738 +size 3862140 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d397ffb598606a9f74+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d397ffb598606a9f74+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ab4fb8123491224b1871f02ac66234f005fddc5d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d397ffb598606a9f74+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab07bec4c53237e0f78b1125461662574282d5c5f651b7da103644391857c444 +size 10609664 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9637a8418978fd74f1836f815e9bc6a9dbb32800 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/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/vision_encoder/_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_5b67293430dd8a20aa2b+1d5aa319/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c9d3a6382de5de5edc86bae0f078be7cb9c77208 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5fb805dc562a93d4e3043a957af5e37b8a238e94522a118c1c969e06764cb9d +size 757951 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7ee8afaf07904914179bf5b0fe472216db581bf4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b1b50a429489b33b8bcdba774f0261d7886e20d523dcfea326ce32212f38af +size 5520384 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9fc51896fd1b67ceacf898dfa04dc6b4fb24e4d3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5b67293430dd8a20aa2b+1d5aa319/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffdedcf9a0dd7a671195ad29e444c0927eb0caccbe91ec4b7e1df617ed10949d +size 5630549 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_613aff52871f55f15829+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_613aff52871f55f15829+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_613aff52871f55f15829+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_613aff52871f55f15829+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_613aff52871f55f15829+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_613aff52871f55f15829+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_613aff52871f55f15829+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e28cb8a3dd8ce95ca106741b6f2a75099574bf55 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_613aff52871f55f15829+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:897a4b4bdd4bf497275de2a30d8b91d063659b85f003aa562ba527dac26b8aa9 +size 327556 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_613aff52871f55f15829+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_613aff52871f55f15829+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5d1f56bb2e14298c455b86cb4cf66314b71adb06 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_613aff52871f55f15829+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f74293aae249b58308a220ead78c5a193d971234fee93b1866fb93e28cd5a3b5 +size 502784 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+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_6373d7ce2813ae7daced+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e4f64883fe23a5df36c529fd02df7399370c933a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66c562250abc4de55e1e4102950292c025cab22affed28eb4c2f05b914773bd6 +size 281703 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7e2b18869aebe23338b427f6551ce69d7bf2d80b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f9936881c104315d0eb4da7889fbc961692b2244f8579a48b71542734626903 +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..bd508f1eb4bd91a5620af54276250e66bacecf80 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6373d7ce2813ae7daced+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfb76fbb23cfebbe654f62b83a07e4ae1fd7f47ca849ceda5312040de8bc9c2f +size 234517 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9b8a42bc02b159a40cd05bf890cb9bcc32570a7a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/compile_flags.json @@ -0,0 +1 @@ +["--target=inf2", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--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_7268021147d2b157f429+8f3c2f7c/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9d1db62c621d251ea2d8f157afb0358efd63f714 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67ee317e16313b8890a529cc3780c47eb66f9e7b32fa88affcafbb138f0f124d +size 339122 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..55b159ab10bf63d2f3e2c7156e596be85e225526 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ee6a9c10c780a937d4dc1be5269872f3b88d91815cda12944ca075f568fc90 +size 277504 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..012bfece72e523648619978abcce9e01420e44c6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7268021147d2b157f429+8f3c2f7c/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90bcca32456e6205d5279244a164bee2715eea2483ca6a5a50fee25484abf7fb +size 289434 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+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_7654b2d615db6b942758+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..de6a17ffe650500e980edbfe879c801d3c5db7c1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b143eb57f8817aaa739b0b78ed2a5d0691d6bbfb00381cf5e65bbda5aa17d9f +size 257027 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..22801d2288935cd42e52a64f7cbfe8acbee9fcc6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b9ef1b1266c3bbbd3845eaeed962f0eb5665832b223023b1d32762cfcf9d35 +size 236544 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9da3452db8d10966ce90a4d40a28f9df00ab996a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7654b2d615db6b942758+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1dd2a3071a9be0bc2ad3a2d9ab8d993d571de81d0dfca5473d12e4b9cc88977 +size 244757 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_76c36cfb450c294eea96+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_76c36cfb450c294eea96+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_76c36cfb450c294eea96+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_76c36cfb450c294eea96+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_76c36cfb450c294eea96+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_76c36cfb450c294eea96+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_76c36cfb450c294eea96+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e7f3a3d4628da7c1b994dd3b2fe5d94567c7be5a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_76c36cfb450c294eea96+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5898599f7769a5febe7563dd4d8c20ae79ee5a88cd3d2bcd93e0e43ccbf8619 +size 284531 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_76c36cfb450c294eea96+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_76c36cfb450c294eea96+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..298b5a05f48918ffd0e5accdb014d008051688b1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_76c36cfb450c294eea96+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92b5c26a6f4d4c0e98dca3a512878f3f78d88a8ef4bab6b68bf307aa6b3e710a +size 297984 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+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_7a1d90e77dea4f349276+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3debafba951ca4b24e889fa056415fa76f00faf3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52c051cddc5242f74fe61e2a6069ab15a0a0e2f1bee6c29b3b08a0db7b1eecd5 +size 3604280 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ba18cb2470ef18e325dbc89621362777585a177f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43a01c78e707d41fa19002e8d7058e7e09cb7515dfcdf272bd803bb0ce92e1e3 +size 4639744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..56e0d3eeb3a09d854bf4e9adc0fd54dd44c4b129 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a1d90e77dea4f349276+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71d73376bfeb72df5f6ef19e680aefcd359c6eee5ec323e315c25129156f2a55 +size 4806268 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8172a8105d980618995c+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8172a8105d980618995c+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8172a8105d980618995c+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_8172a8105d980618995c+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8172a8105d980618995c+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8172a8105d980618995c+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8172a8105d980618995c+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..34385e215a96f2d7399087c32646e8a532bd2e5f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8172a8105d980618995c+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b863b0ca706ad36eefc7f12d52aa8074f51d960d77ad16482a78c70528949c05 +size 1133214 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8172a8105d980618995c+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8172a8105d980618995c+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f2bec35df91bdb045491d19061dcad007c82e0f6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8172a8105d980618995c+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:882f1502c6de93099899b88ba4f9c307c9682348337ed7cf140ca438f6dc6586 +size 5633024 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ab4d2b4c4e73492c47d+a276e327/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ab4d2b4c4e73492c47d+a276e327/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..6b81fc2a42509b323f43b1bf0b3e116d298f873b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ab4d2b4c4e73492c47d+a276e327/compile_flags.json @@ -0,0 +1 @@ +["--target=inf2", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--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_8ab4d2b4c4e73492c47d+a276e327/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ab4d2b4c4e73492c47d+a276e327/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ab4d2b4c4e73492c47d+a276e327/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ab4d2b4c4e73492c47d+a276e327/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cd1521b5a406e24a7d83652008ead932d74bf749 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ab4d2b4c4e73492c47d+a276e327/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b37acdc0821cd7bdb9cc7654998d655f246f71b9a5148c3f4cd871ddc9a09aa +size 317521 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ab4d2b4c4e73492c47d+a276e327/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ab4d2b4c4e73492c47d+a276e327/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7d005d117f242231efad97236455a7ed24c460b7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ab4d2b4c4e73492c47d+a276e327/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ec13f9b36e33c51efe80f8998de10f982154517701e33e920f359e6fa2e09ad +size 328704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+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_8af326880d5b097b2d24+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..777fe6c92f8f0cff7f8e3008e16d4b2ca383389e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1fd2ed05890c13022045b19448b9996fa21fec46c5c4e61d1f62f8806b17f79 +size 1634228 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3aa7ae5e55b684b5569432a431d29f2e0c91dce7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82e247bb455f1a6812308e0a9af5c6c92b28efbdb0f38a0ae978d148c9a20895 +size 1946624 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..12f2ca1c2dada0830b464f297cc043fa4e5abac0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8af326880d5b097b2d24+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13bd7c2272deb56456967c79be2a454702ca8e1dbece99c2ee03169e499eff14 +size 2039537 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+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_8bf2ad61725c80881af5+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..be4c33e49fc610a6797584ff32e9e5c208a92a0c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad105131770fc35c048dfa9840b841a3775dd07c0d4fb309f3cfcdf094a63732 +size 311363 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bbae150ecf1b05ee7f0436df48f93af63720b056 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7d061e8f0919ac8797297f4ec4058c3822826826d5037f6e5f5160772cdbfe0 +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..988fc588e1f098d9e6e0d9a75cfb6ab6b55a8a40 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8bf2ad61725c80881af5+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18276090a1233a9537e040f4083d4bdd40bbe2aed73f5d4190d4f825d62c406d +size 237695 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+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_8f5aa5a37d6faa81d598+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5e7f0d311c1252737575c325d88bb9bf01cf331f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed9bd02107177ec56e1bc4f608a7da2fe8f67a199f4131d9304ab892676ca19f +size 355477 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4df5142d52f4eeb4e0e7baa21281ea151e3cfb44 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:589d354202adcd23fa4196ed8ba75c22834b4e1b728655fee603632bef82ca2e +size 349184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..163a600b7573a6a9a8a20d847d8c89f359a71624 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8f5aa5a37d6faa81d598+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b3d95ebf55f595053b7e067f08207f00fe4e1afb9be64e964c8f48f96ad215a +size 359709 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ffd7832a009c4667731+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ffd7832a009c4667731+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ffd7832a009c4667731+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_8ffd7832a009c4667731+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ffd7832a009c4667731+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ffd7832a009c4667731+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ffd7832a009c4667731+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f902e6202ef9d9e4cb8ca22432280570265bd101 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ffd7832a009c4667731+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ca4a26d1f8ff1dc6e78b7252e4ba9731e76b26c3978ff215dc4ddfdd6cf9cd8 +size 252880 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ffd7832a009c4667731+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ffd7832a009c4667731+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..18ddb48d1b1d1a7fd9f00cf8c49e35a4abb519cb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8ffd7832a009c4667731+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f1ff33e8ebbf691fbc3b7a760d97c74974ef449caf949adfe4c42ac0c7f35c5 +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..edc6c55fae4af05e7de32b3ea3cae60f038c8428 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/compile_flags.json @@ -0,0 +1 @@ +["--target=inf2", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--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_916244c5ab32cdc00ebc+dbd8466c/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b56db38ae3a6fc1ca94a9f61497a48126b70d6f2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4d2603defdea89a027aa5c0d008d8406b95b2d94c1801c0905225ba70b12f45 +size 304422 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4e336a13b3e009cfe8fc6559e8e98e53aa839c85 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baac875147ff147d976f9016d59acf532344dcd5c40fa4c547bd7c3f120d4333 +size 287744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f323411409313988e092237600cbe04edec80c07 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_916244c5ab32cdc00ebc+dbd8466c/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ec6fbdd02c5533ab271c6c08ca64cdece55a96b5397bf45947cbd95d3359e71 +size 297305 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_95c0740536c036e45e44+6aa1814a/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95c0740536c036e45e44+6aa1814a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..535be2b7d778927ffda65bfa3d7d241acf79080a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95c0740536c036e45e44+6aa1814a/compile_flags.json @@ -0,0 +1 @@ +["--target=inf2", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--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_95c0740536c036e45e44+6aa1814a/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95c0740536c036e45e44+6aa1814a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_95c0740536c036e45e44+6aa1814a/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95c0740536c036e45e44+6aa1814a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7d3633428613e947aacdf9c51c697b8f3aff0a64 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95c0740536c036e45e44+6aa1814a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4452d6a61a0a67450ca249ac49a254986c46e7bfe59e5a8a7fb90f676e75ba25 +size 384531 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_95c0740536c036e45e44+6aa1814a/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95c0740536c036e45e44+6aa1814a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3b40989a95a04e3a4610b6fa10399e65c373f88a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95c0740536c036e45e44+6aa1814a/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e379b894ece8ea8ce29c864d07e0e08bd2eb3c2994f9e40cc296ebde9b5db604 +size 809984 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9637a8418978fd74f1836f815e9bc6a9dbb32800 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/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/vision_encoder/_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_9e82659feadf7855d6ba+1d5aa319/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d148ca4a15985bf3f5b10267c0b3f98c4dd1af56 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba6129a78c493b404d1f28036cc02162358200d7cd50ae229b2ccba1035f7e8d +size 186601 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ac9d8f7cdf7d93f6ac88fbed3b7d3c138053e368 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c9cd03f936bb22166198fe26826a5b8218a00f5462d704078a1c5c06ad6f670 +size 1670144 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..73f841d39faf6f1ece6877e8afd18f23600a7263 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e82659feadf7855d6ba+1d5aa319/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826708cdee1ed260274a71ba1e43e604ab7801475732160502aff76c01aa9b38 +size 1680998 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+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_a3cddc301537545539bf+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2b10812d7372fc4f1842df9b85a544184cef6262 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2475b036e241c0d6356a934946d50f775b880bc8e110609b66d7d7193f44c518 +size 1154418 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c350cbae4979ad3f415700dfbf3d202b84e9c25b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee4c3d77b1ac0a09ebaa187b02ad3d16bdea066dddf549337e773b0e76d93997 +size 482304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..abfec91a9d2baf5f5f149d54aea8bbf4fe376234 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a3cddc301537545539bf+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6b0a294f22326dcb87e760d370553c2c4c69f45517d9f35b51d1e1da0d244a3 +size 501805 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+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_a68b2f8bf7dfcd5816a9+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d99bba7e951f1d065bf4119df6b230b7caae9d73 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f07a7a0fd59b2008074055b3e66d11656ee4c4bfa6bd9e86cf1a8ad8207f9953 +size 2141019 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d13feffe2a2ac6d31014583fa7cb035d04e8a4b1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39746bb4fcf4ab943c758505ce2227a163324ee4ea591b7ad0b6fe0f2dbf5c75 +size 953344 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fa802e55c451e50addf250693faf5b856c1bdf38 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a68b2f8bf7dfcd5816a9+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b09a723ad374bbf250c9cc367fe1cddeaab7674d19ad422f617467b62a59b002 +size 1075733 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+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_a91b70c73159815e9151+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..569c451ae4f30595a3560914d388254a6a2b05e8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d7e252476ca6eec0fee4673a351792962d5328ecad1327ed077dcaf59866469 +size 267998 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7fe43da01c2e9ce2fbe8ce6d8372d13523be7300 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a73668433e9d0af055b34b72cdb78996a6c337a934371ad2262274d9518fb2d9 +size 205824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f91ed52bd33f278444716c50f893d84f05a43126 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a91b70c73159815e9151+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d38db32d4a2852968c82b81bb2e4cfcd32a703a93a6fe6af229b654f081752c +size 214035 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+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_bac132fe85578151d292+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b9995bc1f483b9e1fc970f42b3395aeaddee9a12 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a790da04c28bcfa26fa2663ddc48798921a35b69e39f453a1cfa8a5f98b54f +size 281761 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..24366ae08009577f041bf24d809180ba6a044e9f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d79ab63dfebc8c0978fb569626fc540b9883581729f3e9134f997a27ce502d17 +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..8edffb85b96c55baa6b91db03476a82c9200b932 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bac132fe85578151d292+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4bbcb8bac7896c4d71c1e2425ed062dfed5bdfb5e6f9c6bac61404c54e30d84 +size 234517 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_be8a773fa44cd102fb0e+0788fa03/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be8a773fa44cd102fb0e+0788fa03/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..c27e6c39a7a4c3b736e614d7725e8bfa29486eb1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be8a773fa44cd102fb0e+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_be8a773fa44cd102fb0e+0788fa03/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be8a773fa44cd102fb0e+0788fa03/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_be8a773fa44cd102fb0e+0788fa03/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be8a773fa44cd102fb0e+0788fa03/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0b56636d0b7ec01d90fcfe9de684767e856f745e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be8a773fa44cd102fb0e+0788fa03/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a44c2ab3f310ee756fcd9e95959814ff46140fa343545929f50b35ec31824b3 +size 1842768 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_be8a773fa44cd102fb0e+0788fa03/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be8a773fa44cd102fb0e+0788fa03/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7decdd61ef086a8feeae55abafcb5c971b5b9b8b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be8a773fa44cd102fb0e+0788fa03/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c501008259a0469aa0919f2747463b2664ad00f7ae058d497c5a709b38cf479c +size 3656704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c1a9f0fcf68d69705313+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c1a9f0fcf68d69705313+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c1a9f0fcf68d69705313+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_c1a9f0fcf68d69705313+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c1a9f0fcf68d69705313+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c1a9f0fcf68d69705313+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c1a9f0fcf68d69705313+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6b2320df8f01635d25a19aba71d402870ffc0355 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c1a9f0fcf68d69705313+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944e8ae4edc9fafca3b9cc8f3a1d7b0258ed830a14c414ca55da652c703dc278 +size 1878858 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c1a9f0fcf68d69705313+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c1a9f0fcf68d69705313+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5cef62b5e5453c4a3e422d5b7861ca64bb4e809a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c1a9f0fcf68d69705313+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65d09e98e263e76252b69c66478ad1c45fea4ebf32fb5157654ee327fbfc5790 +size 1618944 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+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_c32da82bfab74976bcfb+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bf7879e88317f131e2b4bf33be22b22145ca43f6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cd1e0329d6b191ddd2bb078644e63b221685e0fa1ce9c1cbde0c55f2f7bf9b7 +size 312482 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9518ff307aed171548c128e446938a0624be6d7a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cadfa09df4d464f75f27c61e7fe48e3034a687ff72064ae7eddbd6f629435623 +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9c9bdebbff208f61f3c19b1f57c2b73b289f81d0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c32da82bfab74976bcfb+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d29157af82927f8da3bfc05281288f2204307d3a4fbc4d06e48bd0780e7ae229 +size 237695 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+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_c8c372281996e6b14834+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d708eddcfee5d109b3670877947e2fb0071cec19 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a314dcf678d0e99852aeb35b3bbe11b92d1aec5d3941eb1e32078b926aceb6e3 +size 311838 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5abecc1b9ad5f60510ece0ba5281b751c594901e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82fd08963cfcf5522b4514c14fd1df197253c3412870a3b5042a70f384e85461 +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7761c70dd0cda455fb26e5a36d50dc8a92b18c43 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c8c372281996e6b14834+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:733110d4041b531fd9797178dd20257a907011dfd6090f8875ffeb70d1256bb4 +size 237695 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_cc8875d5ba1caa64828e+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cc8875d5ba1caa64828e+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cc8875d5ba1caa64828e+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_cc8875d5ba1caa64828e+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cc8875d5ba1caa64828e+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_cc8875d5ba1caa64828e+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cc8875d5ba1caa64828e+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..02b09189334166d05133f3476adfce0833c6680e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cc8875d5ba1caa64828e+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d3e7ccb46b508199f3d6dd7cf8104b23354a0dd58ef807b20ac2953866ebdd +size 253741 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_cc8875d5ba1caa64828e+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cc8875d5ba1caa64828e+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..92a8c069eef4dc5ac4e9c52671751e0809bba226 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cc8875d5ba1caa64828e+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae4a9194158b1d61beb2dad99536bf0421790e4e2e17ff7a8d048dd6378ba2fe +size 267264 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce0f36dc6df4a699aa76+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce0f36dc6df4a699aa76+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce0f36dc6df4a699aa76+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_ce0f36dc6df4a699aa76+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce0f36dc6df4a699aa76+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce0f36dc6df4a699aa76+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce0f36dc6df4a699aa76+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..89f3bdb26311ceab1b1160f449fbcfd1bafb4cad --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce0f36dc6df4a699aa76+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b65eb8d3e9557a29831d5a631609ee48f8c988d9f2261e7a4ce60e84d26902ea +size 253668 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce0f36dc6df4a699aa76+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce0f36dc6df4a699aa76+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9db5f4c726edd533a4a5fc5118f1786db65234fd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce0f36dc6df4a699aa76+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd55e33ca7deebaa4a1925936545b3d9540c2bd14784c7d79a050a620586ccdf +size 267264 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce4120480a980027dc50+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce4120480a980027dc50+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce4120480a980027dc50+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_ce4120480a980027dc50+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce4120480a980027dc50+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce4120480a980027dc50+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce4120480a980027dc50+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..45bb4c50ffea093a20d98973c41ef502c1e40c58 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce4120480a980027dc50+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd4a56f7b16dcfa8796074dd0d7aa2a27f6d50e8035b7ede811fdd4d8a7e423 +size 243880 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce4120480a980027dc50+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce4120480a980027dc50+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..52c00bb4e9702e19e38dd00d71103a5dd97bd618 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ce4120480a980027dc50+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba3f5e2f4f3ee3ceb5e1ac7043e753523d25178c4e7c6ebe52aac959b03fca8f +size 246784 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+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_cfe4fb02ad353919ecb5+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5b6e605521c2bbeec491956ccd3fdf7c84dfb4ff --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69bc36b3841d3477b721224b51e04017640bafcf135ddf7ece5b28e21632a08a +size 2913394 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ece730c3b22fa001ed301e7c0b03600244e20501 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b14b8749db2629b809bd5833cb339fc4b77bb820d4d88167031d32c8b4105b4 +size 2212864 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d0bab3d57cfa46682a7438c098f6b13011b2a33a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cfe4fb02ad353919ecb5+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e34ff02c96844daba21f59ef4c09e82aae74f93243a77fa851393d6bb735f5e0 +size 2323745 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_d333fdfbebb9aac194c8+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_d333fdfbebb9aac194c8+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_d333fdfbebb9aac194c8+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_d333fdfbebb9aac194c8+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_d333fdfbebb9aac194c8+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_d333fdfbebb9aac194c8+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_d333fdfbebb9aac194c8+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..85bf1dc61d6f6f02058e9db1bbbaebb08117555a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_d333fdfbebb9aac194c8+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4649e44229b1595b944cf9a0e1c285c11784d188c6f9b603dd6a0781f4044c7 +size 1197721 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_d333fdfbebb9aac194c8+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_d333fdfbebb9aac194c8+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..919a1e10d27fcffd30245633a44a390f0b486212 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_d333fdfbebb9aac194c8+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bbbbce40d2d07e175740512d69e86591ad6c32bcb77b3863569e7abc71c4ee8 +size 543744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+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_dfd8f9902513613df342+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..dc6fcf1493a501395a82eecf5f3210cc19507d64 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0d400ffd3ea42f9b391dd77ec3a21bc420b632b7b59ae45b0e03b04bf039538 +size 274665 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c9ee61682945cbddb333999a1cbacad254c096fa --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9682f7537e7f5ce18f6fb760922994e25000c8728c3300c8a67e850270a7acc +size 216064 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..73522502f83989e710f191c0452272294cd4a4a2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dfd8f9902513613df342+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:231e7815afe30091994e64b9fb43bf4509341a10baf95aef78583cd55b19dbd1 +size 224247 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e89d4411ae8f214d3e9f+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e89d4411ae8f214d3e9f+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e89d4411ae8f214d3e9f+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_e89d4411ae8f214d3e9f+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e89d4411ae8f214d3e9f+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e89d4411ae8f214d3e9f+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e89d4411ae8f214d3e9f+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fd4e172ed2d5bdace6311b4d227f03dcb3e2ac58 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e89d4411ae8f214d3e9f+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6024d009cf5ef6b75efabae005f4d45e1ff9b11436d2fe2c306275f067444266 +size 284757 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e89d4411ae8f214d3e9f+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e89d4411ae8f214d3e9f+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c968b7cfea06e3e1ed7df6c78e1a4fd12ae062f4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e89d4411ae8f214d3e9f+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:053054819a86553a2562a1dcde3e166d1831f7a7a619cf37f6177269428abb9d +size 297984 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+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_f46455aed70798f290bb+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fe3c5c4595c51f5911cfcf08c2789a26ee4eaea8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf557869e209277347c954e1e889e1745ed3a354721b3070dffd420fb5312bf +size 311838 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..884ed65478546f555d3b23ff38e8997db51aa38a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78c957f8ffcde665ab38abbaf07bce046d1123ec57090cf56cd1c274b7af3b0 +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ad1523b8867fa347b38068dfc5c516a7cb55d92b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f46455aed70798f290bb+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:316c77c1f87df6d5e5be48bba6fc6662a225d252ce16adca1bae1c30e2be8d57 +size 237695 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+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_f8c2c1b86a23ba70b71f+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a862723c66849b71630e43dcf549b060b6dc51ed --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7175dd9d91de6877ebfd0324c27c03a162fe38a7ece9c0fcf7287c9c2c3f2aa +size 310556 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c2893fa18925582abb3c2756264bb02fb16c0ec5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2713002fec1424d0168fb78805d0b6f49b3b984da5a5ae50f47c183b65326a45 +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ed7f97e3e883b29edb013e70cf3464fc8bfb12fe --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f8c2c1b86a23ba70b71f+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:114d8c2047fe37db3bbae768c3252504f27db12e32ec0c49e33270de390f32bd +size 237695 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fbab51725e51c7e1ba64+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fbab51725e51c7e1ba64+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fbab51725e51c7e1ba64+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_fbab51725e51c7e1ba64+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fbab51725e51c7e1ba64+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fbab51725e51c7e1ba64+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fbab51725e51c7e1ba64+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..aea4661bf0f06f118f6e369153cc1cf60d15bcb6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fbab51725e51c7e1ba64+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb53e5a04e2bd21205fea14afc8f242b234342844ec88dec7d48f58e0b3c3680 +size 2863023 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fbab51725e51c7e1ba64+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fbab51725e51c7e1ba64+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0a61cb4f2e01644395990b1b7a66d3f1fc6ae18e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fbab51725e51c7e1ba64+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb600795f9bf1c22ef83f042f8712588cc12944dd28d493dba2b9f8d0031bf38 +size 2837504 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fee5fa3b97115a883ace+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fee5fa3b97115a883ace+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fee5fa3b97115a883ace+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_fee5fa3b97115a883ace+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fee5fa3b97115a883ace+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fee5fa3b97115a883ace+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fee5fa3b97115a883ace+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cd9c2d920e33cec46f9034f02b0fc7a937589eda --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fee5fa3b97115a883ace+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6c84e547c0c11ecc996efe3289c98bb53cbcb5238152bb3d7e8c81278e470e +size 283492 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fee5fa3b97115a883ace+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fee5fa3b97115a883ace+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4f089eb70a75ed1b7e75da095c6ed39dc875a1ab --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fee5fa3b97115a883ace+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aaf6f562ea62b1941ce8d58b5fae6ffea1c849621c08a9f5886013d75683b77 +size 297984