diff --git a/.gitattributes b/.gitattributes index 276e0225d533f1ddf0f58f8ab17c89e7ebfa3c45..eb32b22cf1e4567ba3c893453f46be534b427bb9 100644 --- a/.gitattributes +++ b/.gitattributes @@ -14624,3 +14624,41 @@ neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/model.neff neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/de98fc65f348a2d8c295.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/de98fc65f348a2d8c295.json new file mode 100644 index 0000000000000000000000000000000000000000..557b9696f1d183c593f0988019ce04b3347bdbde --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/de98fc65f348a2d8c295.json @@ -0,0 +1,59 @@ +{ + "_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, + "dtype": "float32", + "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": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "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-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/llamafactory/tiny-random-Llama-3/00396ea181e4e8cb35da.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/llamafactory/tiny-random-Llama-3/00396ea181e4e8cb35da.json new file mode 100644 index 0000000000000000000000000000000000000000..83228c174ead0558ef55d691391124852c6e0f90 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/llamafactory/tiny-random-Llama-3/00396ea181e4e8cb35da.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 128, + "max_topk": 256, + "n_active_tokens": 128, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 128, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/llamafactory/tiny-random-Llama-3/0e306366d4a09189a1a9.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/llamafactory/tiny-random-Llama-3/0e306366d4a09189a1a9.json new file mode 100644 index 0000000000000000000000000000000000000000..06b6b5bd67e6f2fd9e5607a01e1c100442e85083 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/llamafactory/tiny-random-Llama-3/0e306366d4a09189a1a9.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 512, + "max_topk": 256, + "n_active_tokens": 512, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 512, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/llamafactory/tiny-random-Llama-3/dad125ca8a11952d0a3f.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/llamafactory/tiny-random-Llama-3/dad125ca8a11952d0a3f.json new file mode 100644 index 0000000000000000000000000000000000000000..9d131234491cbd7f12b5cfa28fdca0fac321f52d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/llamafactory/tiny-random-Llama-3/dad125ca8a11952d0a3f.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/1c7b97712ae2695a506d.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/1c7b97712ae2695a506d.json new file mode 100644 index 0000000000000000000000000000000000000000..22d4de192cbdf439b56f9b7f3b425431e784646f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/1c7b97712ae2695a506d.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama4_text/tiny-random/llama-4/cf5cee8c9de5d6faf940.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama4_text/tiny-random/llama-4/cf5cee8c9de5d6faf940.json new file mode 100644 index 0000000000000000000000000000000000000000..b1b2f1715c79b8924d94fb78d4f6e870c0a8562c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama4_text/tiny-random/llama-4/cf5cee8c9de5d6faf940.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "tiny-random/llama-4", + "_task": "text-generation", + "attention_bias": false, + "attention_chunk_size": 128, + "attention_dropout": 0.0, + "attn_scale": 0.1, + "attn_temperature_tuning": 4, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "floor_scale": 8192, + "for_llm_compressor": false, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "interleave_moe_layer_step": 2, + "intermediate_size": 64, + "intermediate_size_mlp": 128, + "layer_types": [ + "chunked_attention", + "chunked_attention", + "chunked_attention", + "full_attention" + ], + "max_position_embeddings": 1048576, + "model_type": "llama4_text", + "moe_layers": [ + 1, + 3 + ], + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "tiny-random/llama-4", + "checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layers": [ + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 1, + "num_experts_per_tok": 1, + "num_hidden_layers": 4, + "num_key_value_heads": 1, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "tie_word_embeddings": true, + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 202048 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/mixtral/dacorvo/Mixtral-tiny/3779219bc59a2ae3e045.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/mixtral/dacorvo/Mixtral-tiny/3779219bc59a2ae3e045.json new file mode 100644 index 0000000000000000000000000000000000000000..fa730a4c5315830d770af0e8877d5bc47cf90988 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/mixtral/dacorvo/Mixtral-tiny/3779219bc59a2ae3e045.json @@ -0,0 +1,59 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "float16", + "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", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "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-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/phi3/yujiepan/phi-4-tiny-random/2ebdbeae8a00090a231f.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/phi3/yujiepan/phi-4-tiny-random/2ebdbeae8a00090a231f.json new file mode 100644 index 0000000000000000000000000000000000000000..b29d47ca7ddfebfbe89e6d128deb855c85cab791 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/phi3/yujiepan/phi-4-tiny-random/2ebdbeae8a00090a231f.json @@ -0,0 +1,60 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "dtype": "bfloat16", + "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": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "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-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/36a51b598d71b2964dcb.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/36a51b598d71b2964dcb.json new file mode 100644 index 0000000000000000000000000000000000000000..78c95e138c731b2effc8ed1a3c2cea37016b2c8a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/36a51b598d71b2964dcb.json @@ -0,0 +1,83 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/e6f05187d051ac3c3e46.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/e6f05187d051ac3c3e46.json new file mode 100644 index 0000000000000000000000000000000000000000..77e8e597e5d165321fd44ead4c6923513a58539a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/e6f05187d051ac3c3e46.json @@ -0,0 +1,65 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 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": null, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3/Qwen/Qwen3-Embedding-0.6B/18af48e9de9305ddddd5.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3/Qwen/Qwen3-Embedding-0.6B/18af48e9de9305ddddd5.json new file mode 100644 index 0000000000000000000000000000000000000000..8db090bf48565ead29ee3e2363078afae64392f0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3/Qwen/Qwen3-Embedding-0.6B/18af48e9de9305ddddd5.json @@ -0,0 +1,88 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-Embedding-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B", + "checkpoint_revision": "c54f2e6e80b2d7b7de06f51cec4959f6b3e03418", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151669 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3/Qwen/Qwen3-Embedding-0.6B/80594a5958040f8b1ebe.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3/Qwen/Qwen3-Embedding-0.6B/80594a5958040f8b1ebe.json new file mode 100644 index 0000000000000000000000000000000000000000..76aaab7a4e6dd227a55f3a4112c14a6be9f5ed43 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3/Qwen/Qwen3-Embedding-0.6B/80594a5958040f8b1ebe.json @@ -0,0 +1,88 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-Embedding-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 6, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B", + "checkpoint_revision": "c54f2e6e80b2d7b7de06f51cec4959f6b3e03418", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 6, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151669 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/a5cf4ee087cd9567449f.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/a5cf4ee087cd9567449f.json new file mode 100644 index 0000000000000000000000000000000000000000..b9888d121aa489d51a57ac28045928a1acc5fcde --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/a5cf4ee087cd9567449f.json @@ -0,0 +1,66 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "_task": "text-generation", + "architectures": [ + "Qwen3MoeForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "decoder_sparse_step": 2, + "dtype": "float32", + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 128, + "max_position_embeddings": 40960, + "max_window_layers": 1, + "mlp_only_layers": [], + "model_type": "qwen3_moe", + "moe_intermediate_size": 128, + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "norm_topk_prob": true, + "num_attention_heads": 2, + "num_experts": 8, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "output_router_logits": false, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/0dd52d97ae004ed75387.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/0dd52d97ae004ed75387.json new file mode 100644 index 0000000000000000000000000000000000000000..32b4814f0f05569613a597f9e933e56ef226ea9e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/0dd52d97ae004ed75387.json @@ -0,0 +1,135 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bb0e723ce8d76544eb2e2c0282427d561fb45313 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04fa3d25bccfae87c411912a1318f7b09223d1a267d2024c09aef48a926aec16 +size 85024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8c9454d79476f48657ed2542ddec11e9a4e2c53c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78330d0126f21315965db10b7886d59bb5529eddf65f9ab957d85be798db51d8 +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e2b15ff3812789597910facd3571ac810f2c7983 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_039a801db23071a6466e+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2add5c12d4b9c9bc599120379e4adc9366c3ae04c3a6d263c8d7c5a3c9a8281b +size 285717 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0e09de6a37cf6cddcee906bf7dc92a8fd68cc432 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca7cc6d8e758f625d6f0c885073edb0b271b36fd6298ee026e8192a6764df484 +size 426072 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ee1fde88ee18063fba83eb4148ca448a684dbbb2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:762757cc5c4594f1bb9da7f513be76d1e60d1afc33e95d07135b0161c4d886ad +size 2100224 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..551c1615d262ee3f91cfb7e91f38eda966cf90e2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_04d083e7ddd421914edd+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60ea1cef0048c2c53649e2bb82a3ed6fc5949255b01379d34dc30037683711e9 +size 2174311 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..eec774db373d110af0ff4121c56ba44af03864a4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d5ba8ba294975721d17fdded5c4af525bd04086876dc26dc7894ba7f730de8e +size 80789 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4ea720c6bcaf0f20131cef0f5039d0d3cc871079 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14234203ba6b8e1eff330103eea5d0895360773a411a96d0434db8625570a452 +size 287744 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..400e001cadc6b9ed157afd24613a627010370a4c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0eafc4ae59566a24fbfb+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:544497c24218005627843c3afc2767dfb44673cebf9f997e31fe42ba60939d9b +size 295957 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_10217061096959125489+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_10217061096959125489+e30acd3a/model.neff index aaa0dd2bf7397c18dc3becfcffd8d95e7c083689..5073f98074ba6a8a7ed6a162302d0f3190ef0f5c 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_10217061096959125489+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_10217061096959125489+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_10244305442015770634+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_10244305442015770634+e30acd3a/model.neff index 44ee2d26ff1be34c9d1a46848045d3b5f3dde6fe..e37cf10e2da6cc0b01ff98c74dd820f01620972f 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_10244305442015770634+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_10244305442015770634+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_10606948783918825529+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_10606948783918825529+e30acd3a/model.neff index db9b475beab69b0428a33de3a9d9daa4a1845049..c245b4224a0b65ae789c99060046672a800c91c1 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_10606948783918825529+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_10606948783918825529+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_10645643398657092095+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_10645643398657092095+e30acd3a/model.neff index 6e765a50d1ae85b73aff7c7cf3d3875b2811cd55..0072c55ad813218b9e990c1e0451f8a0988699c9 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_10645643398657092095+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_10645643398657092095+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_10661660426924300837+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_10661660426924300837+e30acd3a/model.neff index 1f1eb615e640d4641d1ab10cf76dcd2726573a5b..35d11014712f2978fd15186b41857e17e3c4ac74 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_10661660426924300837+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_10661660426924300837+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_10746122569655005679+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_10746122569655005679+e30acd3a/model.neff index c0f183b149ea618dbb5a8c4e51c85b1468d0a981..ff5faaba5a55f5332e12474458699d0b6df7bb85 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_10746122569655005679+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_10746122569655005679+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_11086318750207148626+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_11086318750207148626+e30acd3a/model.neff index cfd3271afe0d168bedaa6cf824fbfd55164d35bc..57f6449f3890bb44a5a7f07965f4087607fa65cd 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_11086318750207148626+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_11086318750207148626+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_11909310600244571805+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_11909310600244571805+e30acd3a/model.neff index 1bee91e272abdae0bfd6bb3e00a9d782b354653d..f4d54ea0f298a156f7a210345ee4009ef59600ff 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_11909310600244571805+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_11909310600244571805+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_11933818254123612383+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_11933818254123612383+e30acd3a/model.neff index 8cd3dede048d67a1b6846b72341608f574de2a78..c4d31cbbf807cd3bb6c0c85faa248c7b56abebcd 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_11933818254123612383+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_11933818254123612383+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1210392327607194823+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1210392327607194823+e30acd3a/model.neff index 35a42d8ca9693bc31c8cdc7cec2181d8138431b3..b5b105859d2f0d9e59f92b063186db4c22d1659a 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_1210392327607194823+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_1210392327607194823+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_12487216553200321032+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_12487216553200321032+e30acd3a/model.neff index b250dccc52e78cdd390344fa1d0cbaeeb9ecdc8e..15051d0a718715e9cdad8924457d107314ad5009 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_12487216553200321032+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_12487216553200321032+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_13085549342645515693+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_13085549342645515693+e30acd3a/model.neff index 943115e58d5abe63f555c260b5a5db74bd1f0884..20369a42dab0c0532a8e0bf09e4dbdf0dabed8c2 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_13085549342645515693+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_13085549342645515693+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_13102010590082783346+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_13102010590082783346+e30acd3a/model.neff index 63e47a3a1f45d54c472fb6824d8c2be66fa9dbda..af65fae6a565266946969380bac05ff84b4bda49 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_13102010590082783346+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_13102010590082783346+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_13475273426270778455+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_13475273426270778455+e30acd3a/model.neff index 36fc07d96ae1b0216c2d234b95fb107dbcedb23c..1ad6a3bd5834d2981a22eefbf053765bdec70970 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_13475273426270778455+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_13475273426270778455+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_13728813963059599796+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_13728813963059599796+e30acd3a/model.neff index a59464067f95c67143597f2937227cf58a8f046e..2f0f5772a3d68886b6f0824cc7b6b3fe51d1b52d 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_13728813963059599796+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_13728813963059599796+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_13783872956654054643+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_13783872956654054643+e30acd3a/model.neff index 5cd5ed53dc2a9dcdf895df443ac24000f39f4887..093d5d84f5fd170c9f900af47aa93f14e52e65d8 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_13783872956654054643+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_13783872956654054643+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_14097776130612710282+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_14097776130612710282+e30acd3a/model.neff index 33c1299a5a4b373f4437eba782579f4ef91a8c90..302f1d2e1d8543b265bce786e8da201b451dd39e 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_14097776130612710282+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_14097776130612710282+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_14155105943057125178+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_14155105943057125178+e30acd3a/model.neff index 7468948ff77d210ca662613765e065a75efe5b56..ac0a00fd4531897ef278a093851c49f2cd8305c6 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_14155105943057125178+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_14155105943057125178+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_14173682194645188821+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_14173682194645188821+e30acd3a/model.neff index 7d9ac0c3ac78855c77a1f6b36da3e33c045826a4..96e59ea658137f15cfe111575561c91900a6177e 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_14173682194645188821+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_14173682194645188821+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_14274833313744358348+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_14274833313744358348+e30acd3a/model.neff index dd09f4504c6de3406945456a20ef0c798db8d239..457351c35ca887f04e4ca4d1c250cac0a7be1af5 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_14274833313744358348+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_14274833313744358348+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_14469716438804935215+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_14469716438804935215+e30acd3a/model.neff index 3c8bb87a5061804521224ce41be4048d793b0cc5..f45623a9a102389e71c2f49e5da8af97277ae71b 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_14469716438804935215+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_14469716438804935215+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_14739672283771660808+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_14739672283771660808+e30acd3a/model.neff index f2b6f300b9fae5dd1bbaac687cb17518f3b87418..d74dd3569d3d46ba64aebc2b4cf5c15b47d6d0ab 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_14739672283771660808+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_14739672283771660808+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_15442663025941492357+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_15442663025941492357+e30acd3a/model.neff index c21358e315470d7c6e21a5bb05ff416fb30772ac..e3b7c96db0bd66a184a3f0b78049bf7725990075 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_15442663025941492357+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_15442663025941492357+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_15557971880365771457+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_15557971880365771457+e30acd3a/model.neff index 7a605c2a5afc8ba74a25a28bb939031912706e13..ed519ff5c3a55d812c5d4a33657ff7d544e128a9 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_15557971880365771457+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_15557971880365771457+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_15564425602929126510+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_15564425602929126510+e30acd3a/model.neff index bb8b8b2cb169127bdadeb7d0dcd35917a1ac41a4..4cd87d127c988417684dcacf5d13812d63f81dec 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_15564425602929126510+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_15564425602929126510+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_15589838460896944293+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_15589838460896944293+e30acd3a/model.neff index a614dfba5aa2cb144d04a16481fd3cb4e61f84cb..32e9f4729f16173ea793294eca8009c6816bfb9d 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_15589838460896944293+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_15589838460896944293+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_15654572849171857535+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_15654572849171857535+e30acd3a/model.neff index 7e8fd6abd02bf97aed8448235862561e5514c22f..9733d8cc3ff5e0a6d946a458e20e12fbccb04100 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_15654572849171857535+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_15654572849171857535+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_15767383571209512795+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_15767383571209512795+e30acd3a/model.neff index 0e7466223eb86b5f7335cd567a2d6670419663c2..f71a661bdd497642fcd6c98c3cabc0e39255d06b 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_15767383571209512795+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_15767383571209512795+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_15888836045088309511+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_15888836045088309511+e30acd3a/model.neff index 723709dd71c06e487f20d71f60e53d0bbb7679a5..94716bc51f7eab57cf314930f4986e0039bc5209 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_15888836045088309511+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_15888836045088309511+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_15929451261464042997+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_15929451261464042997+e30acd3a/model.neff index d136b124ca4c21ad21c1f8571d87b5fc8bf48b38..38d62e530bef857e0173d595887b2c3a6412423b 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_15929451261464042997+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_15929451261464042997+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_16016505958416521648+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_16016505958416521648+e30acd3a/model.neff index bc17672efd975e919f882cc972714a326913cd8e..ca1c89c025fff55465f98afdce01469cf96474e7 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_16016505958416521648+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_16016505958416521648+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_16053163479112702088+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_16053163479112702088+e30acd3a/model.neff index 626a9c928dc74126bc176b8c52b7e5eeed1833e4..569672397c385dc43c46bc32b9e70b7f18d3974c 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_16053163479112702088+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_16053163479112702088+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_16204387852795926216+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_16204387852795926216+e30acd3a/model.neff index 6ae0206f37f1179cb21f903c7e07ee9c2c53e2a3..fc2b86b7454298d96b021c2f83c27466118b8141 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_16204387852795926216+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_16204387852795926216+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1656719109221189948+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1656719109221189948+e30acd3a/model.neff index 61e6f2a78dca54158fbeb0d5cdafa085999af18c..6bc826b11a382e6f079fe2080cbe1fa302e2426a 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_1656719109221189948+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_1656719109221189948+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_16599571375348449904+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_16599571375348449904+e30acd3a/model.neff index 04a6621c0a980483ddb9fe50e85fb2e5638615da..42a9a58663c370cd02dbc37217577e294981d98a 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_16599571375348449904+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_16599571375348449904+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1663757798483801648+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1663757798483801648+e30acd3a/model.neff index 432fddce2be048e5ace512256b5b663961c932d2..349e146ebc8d4a3bb0c3352530ea40eda8b7a8a1 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_1663757798483801648+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_1663757798483801648+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_16738296820980389103+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_16738296820980389103+e30acd3a/model.neff index 4c95b4b54b00148c2cf22c85291ff7b08f5bacbb..3a999d0ac4cea2fb04dbcd5613705bdd70d2812b 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_16738296820980389103+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_16738296820980389103+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1696825468766062114+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1696825468766062114+e30acd3a/model.neff index 88eb6c1e9776335f620468f28135068ff26e8aa1..21dcf27519f0ed6c96c585eb64751775720f0305 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_1696825468766062114+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_1696825468766062114+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_17476209562158013765+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_17476209562158013765+e30acd3a/model.neff index 674c0f9899744cca3dbe9551773234069ae228da..b25f1150518f8dbdab9a6f0c982310355a606b0d 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_17476209562158013765+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_17476209562158013765+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_17781596253725927902+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_17781596253725927902+e30acd3a/model.neff index 90a393f69e3b062f90ef247fcc18d2574b3fc927..276774c8e168cc8c29911963660dab4dbed9eb90 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_17781596253725927902+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_17781596253725927902+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1795740353831178306+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1795740353831178306+e30acd3a/model.neff index 046490cbf13e130e86a6d8a115c3661e036155f6..55307a39d4b4271f2925f05ec0f8f66a98e7c60e 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_1795740353831178306+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_1795740353831178306+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1800832390737682969+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1800832390737682969+e30acd3a/model.neff index 665ba105cd7b5256226ee461cfb8fba05ed21d67..819d84b6fae5fffaf361de58f48b9b45b0b728f1 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_1800832390737682969+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_1800832390737682969+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1805481651134498710+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1805481651134498710+e30acd3a/model.neff index 550db3782433ef30135c3e53309ea4e32b7a4225..bc4801ca1fc06f3e04db86f35601ad01d02123fd 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_1805481651134498710+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_1805481651134498710+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1805728312057401221+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1805728312057401221+e30acd3a/model.neff index c4d2d87c1923a0a35f3a366122e17ddd79d598ec..a3f4ee65c43609d86c7ee55e4da22d3bfa03a167 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_1805728312057401221+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_1805728312057401221+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_18070749384531238695+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_18070749384531238695+e30acd3a/model.neff index 616cc459ecef337a7487367b2f3248d8a49a4de8..b10c08c9e5e362bb08fcdcb176e2484c5b521aa7 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_18070749384531238695+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_18070749384531238695+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_18134517905922687964+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_18134517905922687964+e30acd3a/model.neff index 72dea983135807bf0c93c5b997b75f3e1b7f089c..22d2480b0cae668cef3c130bff6275f2de5cd0d5 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_18134517905922687964+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_18134517905922687964+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_18207475553554060390+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_18207475553554060390+e30acd3a/model.neff index ce0f651b2ae53479194fc01dd7a6130a264f3028..b1629781838a03f76abb27a0c883b38039e8ed76 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_18207475553554060390+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_18207475553554060390+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fb5029244371f4e128892cec7237087eddcdf04b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_6215c673-3a05-4ddf-8a4c-d17adc9ee851/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b7f9f80de01bab3afae30f106439a7600609730b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a4f4cdcd60e648ee1c6f483fd7d775daeec9d14a980ac23a3446e8df4ef38a3 +size 8979 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9a499c676a18eda778e45ec504119be004c8fceb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b04113ede1ffae3f6b613943c126579dea03b75c06b7b30e5662ba61d20863ff +size 246784 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..52ff09e30a90ce0224dd460657e249dc85b57792 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1d68c1f36fedc19ad300+68b8f1f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62a145794f8289e3a8c5bc7b9fde2eb4074a202a24236d2d09b2302ce97ccc0c +size 249608 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e624d0856e1911e8f657fa16776c6e8f10644f9d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab85d7c603bb13b73b521000a86de4160af14d09b8b3dfd1b565eab024b2d717 +size 678755 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a71c39d59c7c542d5ed87cdf57050e1d72c1fa91 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:190abeca3b9a8ec847df119733c93570a2dcd85982ae381f4628659ac4968bc8 +size 533504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..688507113dd0162ddd3254dba90eccb7aaf777ff --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1da4e8eeffa9da667477+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e6c297729affa6afd0e803abc878e879fa32fd3f0619d5beb50a2889e083980 +size 553005 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1df28a40cf4145bdfcae+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_1df28a40cf4145bdfcae+24129607/model.hlo_module.pb index 1e94856d49026db435f0a486402c921039d46a94..4d2d52b719ee95069817408f27c1b116e509195b 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_1df28a40cf4145bdfcae+24129607/model.hlo_module.pb +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1df28a40cf4145bdfcae+24129607/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a26f69878b069d3a3ceb6fcddd59f1d0a0a0cc09c23aad1fa39acb3866f24320 +oid sha256:c8512bf4e6aeb6df80fb45dc7894b2d89f3f2b4b170d276d4c3314ada0ddeabe size 593552 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1df28a40cf4145bdfcae+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1df28a40cf4145bdfcae+24129607/model.neff index 892e7ac385b25e537a9fb1ceeb0c0fc4151afaf0..40f4b4ddaaa70c2238730eef5c86cd9ce01f606d 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_1df28a40cf4145bdfcae+24129607/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1df28a40cf4145bdfcae+24129607/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c780df29ecf9178026fba188a6c11294090cd5e1fe92c091ef11340172ca6dfa +oid sha256:b08f8d2b97c97f7110a50b3404f5e3719ab8b1c47928621acf663f3c0a5d07b2 size 3769344 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2157613318347839507+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2157613318347839507+e30acd3a/model.neff index ba02054945523906b07971ffc2adb41a5c1d02da..1bca733c574750f74d7707d1e2b48c2fbdfed16f 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_2157613318347839507+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_2157613318347839507+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2203200257461345827+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2203200257461345827+e30acd3a/model.neff index f564a073aa0bd31d9f8fa7499bd43fdf843fb34b..62be0b0d7d66fa2e5b5b3653567a239c361eb9f9 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_2203200257461345827+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_2203200257461345827+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2410426589418994260+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2410426589418994260+e30acd3a/model.neff index c6143baf80901caf8428a0dd8152dc3c32c1ada6..4960fda05bd5b61d41f0dbb7e572363c9b56bb8a 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_2410426589418994260+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_2410426589418994260+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2426414314187505427+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2426414314187505427+e30acd3a/model.neff index 9004f702370e1123b76a39c5a8c67d3a64f2272a..754766f144fea66bc94590fbee6b13ae912aa3e4 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_2426414314187505427+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_2426414314187505427+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2576759111807165188+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2576759111807165188+e30acd3a/model.neff index 5e5e015b5d4b392613ed55f74cfac39b7714a2ca..5f4db516d116ae26ee8564f9c2a041d7dc1a49de 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_2576759111807165188+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_2576759111807165188+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2650447136112456251+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2650447136112456251+e30acd3a/model.neff index bb8f59e79cbcf3b2481dc06a99dd318635577489..270867c8d30515bf09e8794167653a9b0bccd0a4 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_2650447136112456251+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_2650447136112456251+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2682953264353234433+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2682953264353234433+e30acd3a/model.neff index 1a31972a6b0554107690aa22e780a50c8573476b..cc6dde70698994e78a927c6c4031d64b2f0a31e2 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_2682953264353234433+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_2682953264353234433+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2699280712748688265+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2699280712748688265+e30acd3a/model.neff index 90e2d5087055d4f53d47586fb2cd440852ecb4fc..51eb91aef3c4c4a77d82e04fea87af09f36a6858 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_2699280712748688265+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_2699280712748688265+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_27143ff5b0e3602becba+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_27143ff5b0e3602becba+24129607/model.hlo_module.pb index 4d22a38d9dc6583f9d5404470696c34474a0e330..c60900ba381154eb791edc399fd642d82e2d7a8b 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_27143ff5b0e3602becba+24129607/model.hlo_module.pb +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_27143ff5b0e3602becba+24129607/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:52087e84b4ff7caca484fddd14a99801401a845edbf8cd8671b861697587d922 +oid sha256:f4da7912903ac15c84f4ae7dd2bb2dffde034a0754b5746a0fbd328ea034f552 size 474402 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_27143ff5b0e3602becba+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_27143ff5b0e3602becba+24129607/model.neff index 9b62c55a159ddba8e3b63fde275704ea9d2bb497..c9618c98b7fec4e8d09648963ef6b82b5d05a7d1 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_27143ff5b0e3602becba+24129607/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_27143ff5b0e3602becba+24129607/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fd9ae26fc5e32369b36cccda809a762cb0fe98bb45f8f238213b7af93dc62ca2 +oid sha256:d947016590971cae215cdccdc63138c7a2576148fc5073d4ea6eb6f5fd78dd10 size 42322944 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..715276b152d1aeacefa3ce59da9fa1ce7dc8a9f0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6d63d7e965d9319351949e66cbad9a3c799e1687254fc9e9b2a96c87adb32fe +size 865291 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e6c4272a84ecabb9bc1461e0230590f389a5375b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef4c6a01a22c86c59225e5dee33faf2cfef2f689acbf8b73599bb1418a2cfe4 +size 4967424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d7d37e9216f87e08aa7c255c334707104c2cb1b7 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_27c781f8dcce02211674+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2dc40fcc3830b56f85ff0d3bba44789159286be0ffa20fda3e8a4ded68880ef +size 5133948 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2811495285170804454+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2811495285170804454+e30acd3a/model.neff index 4f94ef6c48e17a0f85719cbea9bf4fcb40213f7a..e1ac089d385fd0c9c17344bf89e466777492250b 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_2811495285170804454+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_2811495285170804454+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_302950992539679003+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_302950992539679003+e30acd3a/model.neff index ef62b3853020e4c9f9145ee4461606c2065298c5..15f944ed4036b97bcc09bc9f7aa89f8dd3a42d71 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_302950992539679003+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_302950992539679003+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4013984518400530928+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4013984518400530928+e30acd3a/model.neff index 3b7ad03e1c5477d647585a6c5aeea9681612d84c..f104dec0b8455b3a4330ac72759998c849a5e516 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_4013984518400530928+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_4013984518400530928+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4052264821257342969+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4052264821257342969+e30acd3a/model.neff index 1c06c81ac9cffb1bbb5713bdf48830ff2180a0a0..2370dadac2c8c76cc521547b6922bd871f90592b 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_4052264821257342969+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_4052264821257342969+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4166695227062860792+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4166695227062860792+e30acd3a/model.neff index e87e668e2b1ad138101426c501ce97d14d2bbaa6..5ed3bc1684e428de88d1b70bc8c7d03cf9bc35df 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_4166695227062860792+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_4166695227062860792+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4232557591140652245+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4232557591140652245+e30acd3a/model.neff index 71fa67682aaab21e46c84d75ec5adf544c2311b6..48493d8886f331eaf4647436d643b8defcbe2e5c 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_4232557591140652245+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_4232557591140652245+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4606491920565381523+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4606491920565381523+e30acd3a/model.neff index 5e23cc151318883a78d9d2477fd13b08f7ab5ce6..5658cfbc7a8ffb68184b1c4406d51dacda729f05 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_4606491920565381523+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_4606491920565381523+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4608333438381222049+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4608333438381222049+e30acd3a/model.neff index 742bd71f2611ca3e49b78b4bbb7855e1e46f1b77..92230e0fc68cefb26bde72a885a3453990bc1251 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_4608333438381222049+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_4608333438381222049+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4683016291147007110+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4683016291147007110+e30acd3a/model.neff index 4d26024d41f9a5541b50be991de05ef54fee510c..6e7337cb54340b4e28d390093a8bb6706d547cc5 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_4683016291147007110+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_4683016291147007110+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4816422433712790690+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4816422433712790690+e30acd3a/model.neff index a20e81debc728a2cddc445d5fdafab31cf3ed6f3..49c8f44528cb860724570509ba73d227ce51bcbc 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_4816422433712790690+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_4816422433712790690+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4842952601010372434+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4842952601010372434+e30acd3a/model.neff index 322e9d3bafdd7fd3a1952de398515857c8ed0fd0..479dd27ac02c04284676ae5107c5903c6d98a219 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_4842952601010372434+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_4842952601010372434+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..877edca29ae13728c4b62afa159c12473183d794 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc5d22607282b38e6ccc318f3d4d6f232ae382dbbf78a4b7ff65a37c4cdfbad8 +size 82653 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..28b1dd2674a236a1b325f6bcef8b9d480f087510 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f48a35435a9ad9c98b8c85741229648beff296fa3f768612fb6e75f0b0a6bc7 +size 216064 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..37ff7a74cf3a7a6162eb5f699da1184b8d86c915 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_48c2a65ed0526670ac2b+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:093d5ba28d783811ab004793610964f37dacaa434e481186da196efbd92faa38 +size 224275 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4939721357859779936+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4939721357859779936+e30acd3a/model.neff index 95e48a30b3783e21e8a861dd80d1781b0c557902..3f065e959d2aba444b1fc9e1adcc45f40c952a85 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_4939721357859779936+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_4939721357859779936+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8ede26621ce23e35f8e3a46a1f4e41530179b0d6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17f3c9602ccf9ca37eb5424dd73ccb3f9bc85185d5d98b444486e9f79946f812 +size 84000 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..36aca5421d8e762325a72d89b2cf07a3971cf134 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cc9301e69cbfc919a84799ce95219dcd2d241cc59b51a3cf42bc3a01548d468 +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..89d2236b45ff7f398478563f82acf6d6c053dd8e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4b73c537454a640556d0+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52d45dc2c822cdf538f1a5f2380a1b9edf1a6ea59268618b170af3c6d0e0c668 +size 285717 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5397223456911199516+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5397223456911199516+e30acd3a/model.neff index 784c4a6ccb5d0bdcdb5bc2448912cd133c5e35ad..8560c4b0320f304f42b0dcf886274c90422e2fcc 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_5397223456911199516+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_5397223456911199516+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3d7d85cd3d975162683053faa369dcc6259604af --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/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", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f747ccdad84657b0dc17e367c0ea5f3f76f7a00f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a329d31fe8f44a19d767432740ad0fd5b4a5b395f46b99f9b906fa11236932d +size 72553 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e4fe85460e152b71408f19c0c4600e31ab148b0d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e3ce67cdf0cc358d1bafee19ac736ca899eac9844ac5d329b027a9ee7f71b6 +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f5d58c23453b950b003877370015241ea4dd639e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_56e4db9d55bc669958bb+80d05c3f/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5759fd3e11344c7929eb854380a8543a6ec925d4c575cfe6c4f796cf4f71b58 +size 289434 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5724544066416780383+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5724544066416780383+e30acd3a/model.neff index 6b2f696b3a42dadf0bac2b7a53833253fc9ac934..d568a0ca433be645952a9ec08be324e22fa0f5d1 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_5724544066416780383+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_5724544066416780383+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5765916484866650909+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5765916484866650909+e30acd3a/model.neff index 061f55afc224ff28eaf9ce720a5685d57b9f0ca5..4422146ec61f3a9d647819b2ee84313d0419ff9c 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_5765916484866650909+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_5765916484866650909+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a6b6a691c57cebfa27e38dcda056b83c29c21952 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:948a51e7715bd8232b0ce82f8cca432d73c2a709e6a794d3a228525868c057f7 +size 93425 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b66cfcffe3b75ea9d46540605871fa8850de3ae2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878d9f308e8c51934bc9bc94e82f04c2799e61f8f2d577c3ce6875a6b82e65b6 +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a0b3128f9e2bbe4e1b54500e734010686f962e76 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e9dd03a5402edc46c71ece40b025941a2854628ba71c435f740acdda6f4a3d5 +size 288898 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6368409506294683105+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6368409506294683105+e30acd3a/model.neff index f8207e1cebe93a6870bdaef9bb40c239b91cc0d2..6c79faf52b2fcca602762c751298683e8a51c19d 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_6368409506294683105+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_6368409506294683105+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6375780938374445148+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6375780938374445148+e30acd3a/model.neff index 1095176d9af76ef45a2500515e1efb27a513912c..8d013810ff8f0ff8f32c1270b1d38658239856b4 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_6375780938374445148+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_6375780938374445148+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6417297157123190451+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6417297157123190451+e30acd3a/model.neff index c9e349002d7314f13109a1e4a63e80c1755df288..22b3665b486e9231548e34fb093170ed2ba6ab96 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_6417297157123190451+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_6417297157123190451+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_665145310648895012+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_665145310648895012+e30acd3a/model.neff index a3c85770b9444d878a23f6a95782594797603417..96dab32df362f3032bc57d40639b3474298a5a53 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_665145310648895012+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_665145310648895012+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5a1ab77b920c1c9abc7c0f23eb1c7434b60b9919 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_cc03ce39-9306-49be-a53e-45a6bb68ad96/compiler_workdir/DecoderLayerWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0e51cb39a846e4f58cfe3d5ec50ea34e7babca50 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c233e7013daa344cb368079ec790fbf10f597bc7f8708f8c91ff6684cdc1cd2e +size 29412 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..861e5cfe2bfb334227a9ae26dbcc481d884d7883 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86872eb226a01d1f17c4ca0b0b85a59440304c193b6a4968f35e2d23341092a7 +size 328704 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..eb6255cef8f9ee349bf1a3a36a4da8dc16581152 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_669314db7dec737b18f7+fe605a18/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a00fcd971ac885b117a71e5f685ef0056c1bc477148174776a1fdb786b9453e7 +size 334452 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6711765444274762085+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6711765444274762085+e30acd3a/model.neff index 072fdf69b40faa32c811e7e435eaafe0bf3f6611..f109a2bc1c26a5d1afe147990093ae7ef679a1b2 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_6711765444274762085+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_6711765444274762085+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..64af5bea5c318d4e8d61ab32f5b2ebb8573ef3d2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aeec7d218e22beefd303645f302d7a805df96146ecddac686eb936f8d682209 +size 84114 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7cd9e55f49304a0aeb17115ca8e6e8565e401cd2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b63a1bf5a64c045e6c2f5441227b9dbab3ac2348fbbc095193e7771dbb9bc83f +size 246784 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..11e986cecafe80df397f885dbf2a366bc9dca9af --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6f86d2c037011ecaf2ba+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c96caa5ff66b10fcd04c9a764bd45f902dce78c8db9fb4046a36e7775bfb704 +size 254967 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7049343467335223052+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_7049343467335223052+e30acd3a/model.neff index 90cdf135f3de8819d738e7d39e89c9980480b70e..59874676e59d19d6fd12bb68a7b6898d8ae20796 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_7049343467335223052+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_7049343467335223052+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7877866862268499659+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_7877866862268499659+e30acd3a/model.neff index 974dea1a2142f0b6f992a0a62ddabbce4a835f21..2634bd1367cef79f316e5c394c84d61ed8200007 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_7877866862268499659+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_7877866862268499659+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_793722132614349680+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_793722132614349680+e30acd3a/model.neff index dafddbeab0fb695c9dc4e547945fc57f2db1f359..7cdff6c61a3e4e5c6785f1073b3e8dd27df65837 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_793722132614349680+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_793722132614349680+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8142158350842512240+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8142158350842512240+e30acd3a/model.neff index c957737e4800b0c6373162f29f84f73ccbd9a852..f1b8fe20fa02415e72427afd3d3c7a7c3cc8ed44 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_8142158350842512240+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_8142158350842512240+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8146958338478347620+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8146958338478347620+e30acd3a/model.neff index 7d96110b53fe8389d46a5fc03f08a3a875333d28..eb54cf47d5f1f3f10f692b95b0c7aaf16df04f76 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_8146958338478347620+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_8146958338478347620+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8245165830758578911+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8245165830758578911+e30acd3a/model.neff index 60ddd83163aa5c27b0be30f428b95f1bde675604..61d022d725b29a1dafa7d6e558d17d278eb7e1be 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_8245165830758578911+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_8245165830758578911+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8679096817551502409+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8679096817551502409+e30acd3a/model.neff index 9a292ee225c8f0e043214863a04073cd91e536ce..0a70cd0d39c68c2e63ccc93acd7f5ed2d28a1e52 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_8679096817551502409+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_8679096817551502409+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..7d1678bf25666438bbebf65702a2233ae75c43c9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3fac217d0dcbd842d225c2a15b4ed2c84b49d9aa --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d5eed8c73157f700713d9c88907826f66d99317b071dc1a02010910d7270f23 +size 1600143 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2cac5704ed702320425ca2d2bff54ae25b2352ad --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f00f1d743b38cbd729c275c260c780b2ded7247f6aa22b498c3e2cd64beb9cc +size 779264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4dc57ec5fa73e5df66aa8590168a76fb433dda8d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_87c76df0504ff4178cdb+ac10809c/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c4489cfaaaeffbe4e50bc3e7ff093986c77f83d5c4d6e4669cf211ca3803994 +size 787074 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8882592820567938515+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8882592820567938515+e30acd3a/model.neff index b14aa01495b16c5c556ae0561dda3a27077a3a44..384a44fc55c4b07f312fb4782225f61eaa65e67d 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_8882592820567938515+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_8882592820567938515+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9168843780052024308+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9168843780052024308+e30acd3a/model.neff index 71038a1ddd869ecd32f514d0eba6e34ddfd9eae5..49396320301d75f82fafdbac6ca10cb4d939273f 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_9168843780052024308+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_9168843780052024308+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..f0af8b755dc1df380369eecdd7d5ffb03c10d5ee --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_0b9682b5-0d41-4723-92a1-1ee298c8fe19/compiler_workdir/NeuronLlamaMLP/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6da2cba66863fc471486cc2a5da22b16c00d6480 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:993f99d2d09d34bd152af4c7f96a1e6e1d8788e1cd4aefb845c601d2f4d5fcfb +size 1931 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6f7341ef580d39b9e07b4f0e88857bd86c753ed0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d49899663e6e9dbb501e137cc089d170a6c92f211814a2c6ec8539bf1cd77b +size 134144 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..540a5f9818a9e887848f524d2ccebefa437c2464 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_91731af9dd140b99870b+5914f5cf/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdfbcd4ff2dddcb7f295e23e4902d5f45a7a655fcc5ba17c7919bfc5ed4c6bb2 +size 136222 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9527558113976496538+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9527558113976496538+e30acd3a/model.neff index f8666e5caf6b626d7cdfaf3f544a9237c7f40015..4f5d8e35f02209275b458960e03148ac4888a001 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_9527558113976496538+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_9527558113976496538+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9533302140457976101+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9533302140457976101+e30acd3a/model.neff index 40f17bbfc3d8f338a07726f78324cf4c0faadcf5..54812a3bdb452b6f1279c43ba8f286ce6c844c5a 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_9533302140457976101+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_9533302140457976101+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9770544877851564228+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9770544877851564228+e30acd3a/model.neff index 605a128538445b3f0098a221fa91234c02a3d84d..92f26009b9ef915e06ed0b730a0df232b25a01a5 100644 Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_9770544877851564228+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_9770544877851564228+e30acd3a/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8e58a8d1864722332e8050a0be32af046da2e5bb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_6ea5378b-0e9e-4e97-99f2-e54a0ae9b874/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4bb45842ea0894b69b62a879499055cb6a5cb9ae --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be2fc82d01eae877238b23e1fa62d9bd75d648e5ffdf58b8cf01e4f672c3e27e +size 11280 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9659fbc3fa4cf9deab1ce33e4c63d832547bd28f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f960cf1bf22344841b53164c39d58866f2c202f6cd4e187e5c8292e28f3e86fd +size 1444864 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a0aad5cc5416b344dd95141a19f00d5ee4e79303 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b9ff344d08e0fdcbc3cc+5e0c3dc8/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d85208532e75a320c5a09926facdec1db8e6446b13dd793fa64ce519c7daba31 +size 1447845 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7a1d77a94199152750a0d9ef9008e4af87353eb8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e8b912560da43fc635c4044cfb7d1f65300cdc0afe421d9c6d0b386f4838634 +size 590808 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8418cc1c009477a727dc349bf20408b487a15b5b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:022c5bfaf034dff82d9958b91d3a444a48494d496b589f25c87f7cb6148193e7 +size 1547264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c25c102ea5fc2356b3e7f166a6b23bc1cf006eb2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ba6231346e52f5ca827b+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cb1d4ae05fbb5c716576213608a211006302872feef27fdd9c1dc42fde598d7 +size 1703455 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..16295afa4198da78ab3409d4d585ebe233eaff4b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_9cf4e649-331b-458a-b90e-ffd5263fd7eb/compiler_workdir/NeuronRMSNorm/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6a2752c25c9f7e1092e2b55c010694e168610ce3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c774c6626fc91684e924b843c1fe807dadbbac6d8a8e19443663b43c13eac35 +size 1165 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ceb578a22f06ddbdd9ba2688be54c1de8e7efeee --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8765362d5fdbe321186bd4b3e4baa597825b91f18837b34d546c285d4a49a698 +size 103424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d38b9e05f68739dd6d4c8ae470833d6dbddda0ac --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bd200ea195eb497d6cf1+a3ae1b3a/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5957d998f48cab026a347076057a627122dfb5bc57413fd9ffe0264b14217f13 +size 104320 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..b331dbd4295a22bcf8abbc11b55b53f498c0b143 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_29523186-f31d-449c-822e-992f4bf4f3c4/compiler_workdir/DecoderLayerWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..618358c2b96cde9d0fdd8a5363f4e3756584720d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42a756345a0e47699f8c540a039458d52f4072f93c3d432124a626815c5383b0 +size 14480 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a65404b37297b226d08ad97becdea713bacfccad --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d247c517489e2c55f781f4527dd0caf93d981375dc0cc290c19e9d5013f9734 +size 267264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a34a74e2f70b9f962a202253f06cc4be734939e9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d2a7290ed64376d91880+9313a754/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52923c08e26cb68103477c643f22337816bd1b5d9028b155d48c3277faf5b892 +size 272962 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e9fb1245491af446b3cb+56f125c2/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_e9fb1245491af446b3cb+56f125c2/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e0c4e49fbbaae6fd8c4488ae5796063a90237e55 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e9fb1245491af446b3cb+56f125c2/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_dd0c6d73-2c58-450d-a0b0-3a2b862f899a/compiler_workdir/Llama3RotaryEmbedding/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e9fb1245491af446b3cb+56f125c2/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_e9fb1245491af446b3cb+56f125c2/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e9fb1245491af446b3cb+56f125c2/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_e9fb1245491af446b3cb+56f125c2/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f1e2473c54cffac949ecf31d3b6ec636c290545b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e9fb1245491af446b3cb+56f125c2/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a29d4cf27aec9af90e53324eff9ee69e033679482f4016a9dd3e5416c7c68a +size 1584 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e9fb1245491af446b3cb+56f125c2/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_e9fb1245491af446b3cb+56f125c2/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2d3704437b22db08a79be533151c06c5bfde0588 Binary files /dev/null and b/neuronxcc-2.21.33363.0+82129205/MODULE_e9fb1245491af446b3cb+56f125c2/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..a7a40c022faf4beb0fb20246d9c1f9c8f32c6900 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/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", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e3e15a31cad10ce1cb55cdd26b518a6a5798991d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1c364e560eed61f02284b32afbec9ee92735a7fc75f5da0fdebf4e6f62981de +size 91833 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a9e01b6cd223edc2fdcff253af99e75d52ffc032 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2fc11aeb301cae1575deb49adb1618447c5ccd2c657b6641acb3de80ef9c1e2 +size 369664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6f0f6f2d7e62706c895cebb901e71dd11b5e67b3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ed0cf24b55f7fbc63380+2dde74c7/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23729c5200e0dc49071785068296f1237ce5ac372d970f2ff6cf6d6bf2ccac9f +size 379225