diff --git a/.gitattributes b/.gitattributes index f803817e8f2bc9d2f13ad7ed3653ea37acde9529..ddd5c4979cede695ad64597ca4dd09584295115c 100644 --- a/.gitattributes +++ b/.gitattributes @@ -2733,3 +2733,50 @@ neuronxcc-2.17.194.0+d312836f/MODULE_0191a5f7284b00665cc0+613edded/model.neff fi neuronxcc-2.17.194.0+d312836f/MODULE_15ff576e3081c9564b48+613edded/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_9c8fcd1797ad84745497+613edded/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_ea55ff0c585401f8acb5+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/04f1740b7a0d1c756d80.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/04f1740b7a0d1c756d80.json new file mode 100644 index 0000000000000000000000000000000000000000..6844e4546445178e5a33a3181c4392c7d8790509 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/04f1740b7a0d1c756d80.json @@ -0,0 +1,51 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "bf16", + "batch_size": 1, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/6ae95ac44a666f05c6ac.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/6ae95ac44a666f05c6ac.json new file mode 100644 index 0000000000000000000000000000000000000000..b9d44b131d252ee9c3ffc5e103802d094776cba7 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/6ae95ac44a666f05c6ac.json @@ -0,0 +1,51 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 1, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/d89e7bb9ce60e060a05a.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/d89e7bb9ce60e060a05a.json new file mode 100644 index 0000000000000000000000000000000000000000..e798fa705b35fc4d47f20a432269184cb1f5290f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/d89e7bb9ce60e060a05a.json @@ -0,0 +1,51 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/0a43825be7b7281911e9.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/0a43825be7b7281911e9.json new file mode 100644 index 0000000000000000000000000000000000000000..8bb4bd9d5eedee6ff0fa2dceb424e7d5651db1e7 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/0a43825be7b7281911e9.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.2.0.dev7", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/22733839dacb6e5015cd.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/22733839dacb6e5015cd.json new file mode 100644 index 0000000000000000000000000000000000000000..99e1b7741c6fbb344191edaca7a52ef16403fb0b --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/22733839dacb6e5015cd.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.2.0.dev7", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/7e0883804eb67213ba2d.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/7e0883804eb67213ba2d.json new file mode 100644 index 0000000000000000000000000000000000000000..a5ceebe7468fdef90047e44ef403ff9748c47aa4 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/7e0883804eb67213ba2d.json @@ -0,0 +1,55 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "bf16", + "batch_size": 1, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/8092f01dcffbf2d4dd15.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/8092f01dcffbf2d4dd15.json new file mode 100644 index 0000000000000000000000000000000000000000..a64512d31281b9ffb35af6e4dacd1eb1e5646803 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/8092f01dcffbf2d4dd15.json @@ -0,0 +1,55 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 1, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/ee3839ec4d870a814ca2.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/ee3839ec4d870a814ca2.json new file mode 100644 index 0000000000000000000000000000000000000000..96950fbb001d3766e114a8ae8d4c858a8136d0c5 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/ee3839ec4d870a814ca2.json @@ -0,0 +1,55 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/f703f2db24b888540de0.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/f703f2db24b888540de0.json new file mode 100644 index 0000000000000000000000000000000000000000..f8229955b1f69c6ff4fcafc063eed584057a2ed4 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/f703f2db24b888540de0.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.2.0.dev7", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/unsloth/Llama-3.2-1B-Instruct/ba8db5c1f8497571a448.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/unsloth/Llama-3.2-1B-Instruct/ba8db5c1f8497571a448.json new file mode 100644 index 0000000000000000000000000000000000000000..0339597f011249fcf3080665b9c46e14c43055ff --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/unsloth/Llama-3.2-1B-Instruct/ba8db5c1f8497571a448.json @@ -0,0 +1,56 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 4, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 4096, + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/9dc90635cfa8c5b914cc.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/9dc90635cfa8c5b914cc.json new file mode 100644 index 0000000000000000000000000000000000000000..cc6f1f4c8fb3f7fe129a554d7157734b00a9ec8b --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/9dc90635cfa8c5b914cc.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.2.0.dev7", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/adc2150036a52ffc6af5.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/adc2150036a52ffc6af5.json new file mode 100644 index 0000000000000000000000000000000000000000..a876b494969e275e1653ddd2f7d9f9dc77986e2a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/adc2150036a52ffc6af5.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.2.0.dev7", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/b05741f94b766070c26a.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/b05741f94b766070c26a.json new file mode 100644 index 0000000000000000000000000000000000000000..8fd311b7102643ef275a7389d7ef3c3644bfd9ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/b05741f94b766070c26a.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.2.0.dev7", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/93d1c70697961dfb4051.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/93d1c70697961dfb4051.json new file mode 100644 index 0000000000000000000000000000000000000000..44ee47595648be8355f99a2c9f4801301c9afe85 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/93d1c70697961dfb4051.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": false, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": "replicated-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/dd7372422bdfe51f7483.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/dd7372422bdfe51f7483.json new file mode 100644 index 0000000000000000000000000000000000000000..11c33304d8d844cae94afce57fdf35928c1dc4fc --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/dd7372422bdfe51f7483.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": false, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 1, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": "replicated-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/f40bbae82fb4cfd892b6.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/f40bbae82fb4cfd892b6.json new file mode 100644 index 0000000000000000000000000000000000000000..7e6786ce7728676e9f172ec4f0551800b92e4d96 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/f40bbae82fb4cfd892b6.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": false, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "bf16", + "batch_size": 1, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": "replicated-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/21462d921fe00fab6cf6.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/21462d921fe00fab6cf6.json new file mode 100644 index 0000000000000000000000000000000000000000..18fe96d8c2036136cf5c1240536030065805097f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/21462d921fe00fab6cf6.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 1, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/5ec3ea4c38639645de5e.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/5ec3ea4c38639645de5e.json new file mode 100644 index 0000000000000000000000000000000000000000..abd151c28704b132af6e1dd0384b131c22a30396 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/5ec3ea4c38639645de5e.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "bf16", + "batch_size": 1, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/ad4d2aee22289a920d76.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/ad4d2aee22289a920d76.json new file mode 100644 index 0000000000000000000000000000000000000000..8b72154eb5d57bbf2827783c0ae64d8d94e211bd --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/ad4d2aee22289a920d76.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "HloNeuronConfig", + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "batch_size": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "optimum_neuron_version": "0.2.0.dev7", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3bad8a326e2a2910cf7cfa0e4598374dbf4d631d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:812e7533a893b01d4889fd56aed08a4d04c176a543db1294b6993942845906cc +size 7106 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..21c60b4720853f811ca22359d49a8d3aa026ad04 Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1053224520467247466420abf84d766d540de5dd --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb43375f225e75f29624572006b6531f223eb07afc06f0f084b46ef315750fc +size 7106 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f4bda58d62ea6f78fadeedabd6a22df91cb8ef1d Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..102b561ed6fd99c34f0202f7860b1ca2795ce432 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ee8ff96a09e7f8b2d0e01617ec7d0fb75c815a76a68ec40016def33bf974af7 +size 80428 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6762f6c505af152cd6c666336fb96799da7bf2aa --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bdbcb91e1b29691ae1ec050e5a4fd31fc9ba2475ffeea46b71b571b880a994d +size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2b973429f78d2d412062808dd9377968e196a9d9 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:137567311745b944d4e98177aec0d5d879f138f88e9298aa007003bce0d3734a +size 244319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..877709820f06e422d43bd537a32e37af4c1cd27a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee9957eb134e14bbaa4c3c7b989176a02ef262107f354f444b1a2bd85e3c438 +size 80388 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e13b566e6ea860da7f8b1718c186a372034a749b --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6654cb47676a5dda37938e1c3b91dfabe8a6445dd8a1d9ae0f7e5b66a2cca6a1 +size 226304 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0137bc9ba0bb8adf071ca54f7c316c2fe64fd047 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:206a7ad89370cff8d2b2322c1ac670c89f032f09dacf78c1919f6862a5f988f8 +size 20204 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a00c53eced5dd4773729980b6636158e9d2a15b0 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1097368aaa1ce8526d2e6e5468918bec01b472641e3929c5ef405dce6a8a9625 +size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d26d776615893c63f9487ce93dab0bf854a7ebad --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54bcdec06d89d654845d062183036a3a4b545c119ab7f8bfcfcf806a54b9b35d +size 11183 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..63a34bc1b18d3a66ad396f4cfa267648858b31a8 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15bf257da8d2ac9c165a0f254170c9fcf42921fe07da2394a99317acf58d9a53 +size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a6e893a25329ac961b2d4fa2caf8cafe1d96623c --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3978ae0dae4598ee8e9bbe8392fc2e7e13757206db58da945eeacc59ca5ff3de +size 21402 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6ba0b1afe858747bdbb75556d6eff22b13e2035a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fb0f3d36d810f920a63f120e7d5fd467d839408f2db5720ef1c3a224807664f +size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..64b088be808a82d8c95848c4dcf500d4dc8de3ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89450bb664c81cdf16fe49daafa237c12c1cd71f5d8ddae84827db4a2eee340a +size 17475 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b192093e5946efcc43b854154a8a1c5ef1ddd20a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad30203c52a624daeb27b0f28a6b498abc578fe67e29f34fb7573ba3f6f52b4d +size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b491b19b467c4149e11536659bb757f969d67813 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bffb7434bff71e7ba712292397b2ad4ee6448cc362b3669d6140ae7eda9fed6f +size 21402 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..578f58d0f3cedbe2bc753c6c618c2431b8f147f8 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73e21d16ad0a296c04ecba8f94402851327957df08243931da3e03ab8333a838 +size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4abc5a906cf2a130afce0e73fabeba74609db934 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d94fe1a947149b651a7c79c80adadadad51f361bcfe470c5c63c2e0ab0550ba6 +size 16718 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1ae8f0f1af09b5e5e584989482f77cea13585f22 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f99961fa79c12989f104329bc33fc808a0f2c223563e04ce4dc51501c4bb921e +size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dc442f1bb29b1c95d459413ebe0d1229340f95b1 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e77d8983879f0776517469162cae6dcb38f8fc12 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:806a1385f651192b0303c2a58bef90450f99c6cfaae981eaa0ddba44f4a681c4 +size 68277 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..057caf7ed088c3c6f92070778b8e9d74fdbd660c --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f9790a8375874acff67f2d5f2db4431516eada2f666bc7a658860b931121a0d +size 257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4cfb8a2d77484c0b25caf4469c0b5e61723aec53 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f49121fc35c1edf827ed2858e4c1df2122e9f117fdc4355469802d37a752a89f +size 268322 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e6e3e749231167973be1e74d4fac2cd7ad2ee71a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14f3f25ac84183e3e0fbaea932e3c43b3d7df2d165a2f3fd8d17bbb0d9b67100 +size 17475 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ca57b192dad00d1432cb0be0843402ac20c1936b --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f05cb8d4c36e8469d2e4c9190e8964e21b68297a5b7ad4dfaf112b9b203750a7 +size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fdff7d538dbc95c3ca3559436742fe386eb1b1f0 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae80c5021d8426bbcb8d44cb4eb336af3357f7559620811a34c60913211a1326 +size 22194 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1b38de2bfd7c3c7b9f64092bb170cec3c6a955cc --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:838dd1cee35c03d91bd39bbdeb1b678d327d2db145752e2c203a5dcd5ddcad42 +size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..336dd20dbbfca606c5506b057eb0c7f9827de046 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38184c632616d2476fe6e7794270c8a51ed09eccce54dfc80c4ee171068da566 +size 20501 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0e3d70b18a9bc8d6003f16313da845219af41bd3 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e52a87210abd86a86feacc71c423a2494a5415d3e1199932dcad32363604379 +size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..235d59ffb22eac4d38831202f2394cf20f120cfa --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffcc61769d8fb9bea5e15c42d960c69b9df6f97061385d0bd0a21d0ce6906af6 +size 26028 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..013582071e6448a940b181e861f930067ed46e98 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7934f54ebadf6962796f723dfd7c9fff4ac70164f435ea7c681a5c699eb1be45 +size 154624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..38848a4e329ca7a1a5eb11691a487721c2e0b9a8 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3576120c6eac84be8c5cc6155994228f8330fa2472c297e73729e2a817783e9 +size 80388 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bea03f59404562dbf330674f8767299775e9b67c --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9d9454c6a6b08695e0c8360a725dd97d4c34d2b130324450413ef0f162436a7 +size 226304 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..25004c872e032ad759a0e534e8728ec30c8027cc --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0df5d765518a8a37e232a30badf00c24949b6001eda6acdb60c55bbf974e1df +size 20644 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..abb94cfc3d5be421fa68810f7b2b9868954ade3d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d0d86a53eeef2f5374a6fc7235c8423a7a818db5f00e1d36a3ee0020f456eb +size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6dcfa64daf274b7949b2fef1fa41ac04dd50d3af --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f15a46bf48ef719945d1be5c931da1ae753a2a0511e68e8bc5d12755ee6c1d66 +size 22098 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8d3c98b5ae3995730390f578db7e63ab3d454e4d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a40ba8dfc59ee78ce6d463d16b3ea3b9552f8a300cff25b2ac895f01cf98894 +size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8b1f7d7aab0bc821983bd1d38df4faf672d933bb --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f2fb1e13c30d14bdf2a36c1c0b2efeca926d064a4e7ee7e668c6708a0d0e0ee +size 16631 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..12ef8b03a791a9403987599d439b815856b4e3cf --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0708b47efdbc2b971c3c10a556907e75de7996a7967adb57d4b7d23adfc70f66 +size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2549e3fbf2b5e2d297902cc0effa0ffd5f90d748 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edded5e41c2f708ffac026780e8c02ae993f0f60d0c40b7e256aca2644ce77d9 +size 47194 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3d5916e2a87cf3fb49e73e7827bfa94719c9c31f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f9ed508f414b6ce2c7a50a0a7343301d1e96e95361c7f06eca9fd76ce8b8b6 +size 246784 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ea9c0698c33b7a36a05c893d3926cf3ecc909a30 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..723224eaf1aaee46f87791a9e110abaf3277d471 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f608e53b35e833af3454442e9938fcd0c8904cf7488fca7396d606e2f630334 +size 81317 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d28e808ff1f5be9018cf4bb9f47370e889d7d407 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:559e33729b53b103f9c1f1c71aa37bde9e394daf9a34d6293fdcb52f019fbe7d +size 359424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ea9c0698c33b7a36a05c893d3926cf3ecc909a30 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3533c6a9a6339255ecb7af61a6040af1f68afbd6 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dabce0fd6044e00784cc15ec5325ab2531587d98da2907e3af4771eb4e745d3 +size 81319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..61154aa1d52c1769542539893dd0fb09e1b0b06e --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd40201d22c8305b51e7a9bdb8a4c69ccbcab75806f1a58833753d720170de07 +size 359424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6487ce1aea969e164a5236e00d3dd4a40638ab0d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb26bd2e91a5e5ab1f04ea28be82476f19575f897cc01c75e92caa404f6619cf +size 80428 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..21e69cccacfdc58d8d08628a8839daa02cf9af65 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1124d42350488e4041de9d58e09153de8af597a3084681bddbfae296c06f2f7a +size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..19dcb1427abac1997c1a980649be7295cb67b8f7 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2a451e8366682f6031d3802969bf81a99c5f9694c76a810385784bf4b281fbc +size 244319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ea9c0698c33b7a36a05c893d3926cf3ecc909a30 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9de7745abb7d2fcd51ceaf3c20bf705740af264b --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb95ab74c61dc5beb12a642e93e6b6df274f24cc0c1b199185c968f39ccbc3fa +size 82168 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..42f192091da984bb845ee6d383ff6bc36579f28f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddaf92e8b65ef9a9ba724647f18c64ea0185badf5a630d334589d52d5e2ab331 +size 420864 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c796cbd1d8cc49ba62a32a0936e850e82f6a8738 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd0fb0da05aac81e18b930efa0fa57ea6b400f7eb3a7ab702fb7626eddde8ee3 +size 48045 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b60d9483c9b2424b41cf846387e141e4201eb2ee --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:960e4dbed38e79af98529234a0a5dc58c85c5cee20969762542852e827fd25b8 +size 2386944 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..681e4eb2cecdf1b06e0fb3584883f7285f52e073 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe5eff2ee6351a89412d6d02fbfc2439dd073145ac2b905f3d8b068cc25e626b +size 2394734 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3243b062d2441b214dc8d748c458789c263c0057 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e52a98532ea1f8a083fab1010a6306ad96c1d3ca06b558e84feed3fdaf8b7e6 +size 236301 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e643dc0a5fdf1a7dcd9d08c8f6d072fc7542e0bc --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b22f2f015150c7728329e90ee4e682235e5e17d41d922f98a8bfa27c88af1d0 +size 29471744 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..672f837d60308b6f194264f9372d1360eaf83702 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:635a56ee4821e472900e2f45aff06fca7b6436d644a90095b9c830f6deae7d18 +size 19832 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1f5a11a575f9ecb9a3bedc38ae983f64091a5ec8 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20f45095a50a31fd158578df588cdaa5927442dd4debf03ce4ee823a0fd5a33 +size 154624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..561d229e401204468f750c517bd8496a6ab1ea00 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e7b848fd50ed1cc32978f64e4698cd1f10eaa9221bc9dc60316760a651d212 +size 24382 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..da5b785cdf8595fe32181f3be338f5a182bb2fe2 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:329376b735ae3d25ad9ae1066e3e9885813050092450c536e31d43bc664b18f2 +size 154624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bcfde6e20c66b07f24c853a5f28354fe76bc7f1d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c401c20ee313a4fda311fdf8ebd910b84f627ded8f6f3a17abb78ec208ffda +size 24382 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c47478fbb1089b3b6b58106697460ecb0241ce50 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69ca5f3b36534b36b8b54a0dd5608131096b5c9a010f4f053a9598f4caa96ff7 +size 154624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a24c309fb72d4a6c3fc2b48f2e4b330f98945077 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a0f2b2fb89aada76f426182e61cc4b3fc5274ecde4665f7745a7b2742418492 +size 7106 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8934fdee2bc09e1cb1fe0384c630d22368d63728 Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ddedf8047e3cc2dfea1add455687ec2e59136ffd --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a18136a0c5ee2b3f80ccfefce5e2065c2a75c972cf3c7ab7a73d27f9f378cf2 +size 11183 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c026c2e0c259edfc6aa1fb76c4c6c778f4588907 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ea270c7f49444248c474c5185893d591c257084461d2f8fb15b19fb642138cc +size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..15dcb7c0155a50c6952b470945364207a9dba6c8 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f8f9e3c0a49ed92e6325ffd642090a9d65dcbd565c812acb8bcc98d12204e08 +size 20644 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f575b4f4c3d4ebf974045c6e454e81f9528d050f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50735ded7702c4d655b264b6ea4d0cd1b96a149529121c7be7547a1ae4a0721a +size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..37ffc6b6f7d787417f6b1c1452725a98299258dd --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:331132547003b9874793b3c551a55417efc4c95974c7795210b56ac6bf49150a +size 19360 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..de395ff1ad244a3d5a58c5bd6c1151bf04b06fe1 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c6b19b692a85df6b1461b4b1aeec1fce3ac1ae8d361e65a9f33906c45688f12 +size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..344d99d0624ebe8e1c04d8fd053d32bb8b18efcb --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97a3ff299b77d41425f3ddbf6b205847b1158cc20d89f1aea55c0f2d50e49dc0 +size 11183 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3a8f9f43c38be221ff8b4601a755c03c2b858ad2 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e84ef54ac327c9dcbbaf76397c13a34127f92b41e260d1a26af9a20f8e1443ba +size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a0369b589a88935d375ceae1e5505d6307ae21d4 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c1716e6ab08c7d8828b58c7a4ac4fbd4cc7a6574e6db4932ffc53020aa28bb0 +size 19832 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b16d93221a0ae9f1ff16f73fdb66921dcaf87d4a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a486b97611c9e33bfaaccbce72878a2d714edfe80242adb4542778c3c957f0e +size 154624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dc442f1bb29b1c95d459413ebe0d1229340f95b1 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b6cfd1722ede57a0f9f38c450f8b71f0813eb6c0 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6edbc1f61aebd2bcfc907bf4a74354906dcc25824e201291622b0f1c912d4d +size 79431 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f846b013e2a5b97690c94a14d6276e6bae3303ec --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d4a804e10612972a19e17b18e96b6f4c3b37ae2b7cea510b747cc3baae42502 +size 318464 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3dc4d8ed68960c1b9556c09ccbca700012e60614 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2782e016d055943b7a89d74e1d65a5f2adc3e59e83257bb8412ee9236d38040 +size 329762 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9e16c5738b2c3a77e7b8a03523c50d5c09e13471 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c329043e0317bf828d20d346b60debcff57580515609f6b5ffc06091922ca4a6 +size 20501 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..234993bfc7ab491893e322c2043b609b39714843 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c260463ae9d71e01a6fa65f48a5caf9ff6e1eda6d76840ad83c838236b3547a0 +size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6dbb25dabbb87c729eeca1a4e31ff4baf52a09b4 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:905a7378ccf2c97e45de51a848471829b62b6943fcd2bb223f09bc2664a772c0 +size 19321 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1500ffd83a5e6e09130e0bc407170d6e9faa6b21 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7386f37c74a70902f2bdd5f32bc61851ea0fa8c73eaa529e4a37065497647dbb +size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..43d0dec6fbda3a30f2dcb1f2554b99c5e9b1d936 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab169a10d51ed4ac056160c9a66d20aad7e5d770506d25f9022b1ec795494236 +size 16631 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..35eaf59e4569a6ace330a97f772fbf434c93ac55 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ded081af385b009a44e7ff43869d04607bdd00a4d574b4f1f54b448aebf60ad +size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dc442f1bb29b1c95d459413ebe0d1229340f95b1 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..22cbcd143c56d49b36da23fbe589299e253a298a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2de5abdefab5cf8469996b59fa13f1d93f51f5a289c5af7e5121671dd2f7a721 +size 68279 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..027ca47957e166ffa0ba880c30a50e99f719c3cd --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:079ba37cc8a97e34bb01086078203a7aaf70a5da79594f3853db5317f5160a1a +size 257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..51b9b0b2557f1e999baf29235491bcd29767adf0 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4c7a037892e1990c965967f45ca0b0b49df98a071c686109e3b150d00ef63af +size 268322 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e7e98abc16c79167b76d6d682779cd369bd99c37 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e882dda7ca8d1e7ddcf2c54143922356b4f41b29afbc979ecca776884fae42c +size 22951 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9fde1eb41395459fffe77601b7597ae5c2526af8 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe19efff6275676e89d30b8e58fd70ef5898713dad2b6784bf74cfe6661e3e9f +size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bb398860e50031bfd3e8249d9ace594704114ec2 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc998a517871f9971580382edc47f8e45377a0dab229bff749798ab51c992928 +size 181367 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..af215adebfb23c628a9466bcde6e1fbcb4ccd25c --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caf1327f71106ddabd1e9520a072caa825f149a36002edc82fc20cd0890b86cd +size 2458624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2df2ab269e3006b628a43a78c09f0fd04c07b48a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e6693f31ad55428431f8380303e8dc91ca44830232eaea952d4b260f95957fb +size 22558 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..159332447376519b7a96b600ad1e8b4220311302 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:672c85ceb2153c2436ab1caf79d8631cc88fa82ddff2ae6048806d67fab947bf +size 154624 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9fa996af8937c49a5a5ceced87c69913aea681d5 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc82c7660e5291c3e6ff8e2d543a91c98d439a82ddfd9d72c6b94f879783aebf +size 16718 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8eac9e02c5169e345419a20dee753f287d1a7fa3 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaffcc9d4bafe61a0d2285533a491c4233043557c8408c8df9acb44eb1026ff0 +size 134144