diff --git a/.gitattributes b/.gitattributes index 82817d65882671da433b7db7816003686cd02829..3eedea9423b62069f04e62c581eb20da2feb302a 100644 --- a/.gitattributes +++ b/.gitattributes @@ -17193,3 +17193,75 @@ neuronxcc-2.21.33363.0+82129205/MODULE_bec56f8afdbf66a50c25+a02c3a36/wrapped_nef neuronxcc-2.21.33363.0+82129205/MODULE_e337d9bea67418c4cbfc+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_e337d9bea67418c4cbfc+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_e860112df381f8b3f4ae+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1bfa3dd1929fbcd69193+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_25ecfcd32b38ffcca9c6+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_272f23df0029fc228e27+6e4949b4/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4371876575046bfaddbc+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5882b7576829bc99fe1e+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/0cc25526e2cfc37a8875a3752f33c4d7505d8a07b869d0f3f41915cf6e763b74/88ab959ffd7f969e9ecf.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/0cc25526e2cfc37a8875a3752f33c4d7505d8a07b869d0f3f41915cf6e763b74/88ab959ffd7f969e9ecf.json new file mode 100644 index 0000000000000000000000000000000000000000..44d8c1c8ae0834ecab399f9008ad99f40b13f27e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/0cc25526e2cfc37a8875a3752f33c4d7505d8a07b869d0f3f41915cf6e763b74/88ab959ffd7f969e9ecf.json @@ -0,0 +1,59 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "ibm-granite/granite-3.1-2b-instruct", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.1, + "attention_multiplier": 0.015625, + "dtype": "bfloat16", + "embedding_multiplier": 12.0, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "logits_scaling": 8.0, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", + "checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d", + "continuous_batching": true, + "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": true, + "optimum_neuron_version": "0.4.6.dev3", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "residual_multiplier": 0.22, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 49155 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/866e4ae3016710258519.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/866e4ae3016710258519.json new file mode 100644 index 0000000000000000000000000000000000000000..31f86236f4ee23e597605dae30d8cbd13c5abdd2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/866e4ae3016710258519.json @@ -0,0 +1,88 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-Embedding-0.6B", + "_task": "feature-extraction", + "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": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.6.dev3", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 8192, + "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/0.4.6.dev3/8c90ac2593ed0b7f1ecb60e82cb184fb11f2ea640befa1cc7b10766a5c02525d/4d19457aee330abf74c2.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/8c90ac2593ed0b7f1ecb60e82cb184fb11f2ea640befa1cc7b10766a5c02525d/4d19457aee330abf74c2.json new file mode 100644 index 0000000000000000000000000000000000000000..c33ae5dbf8d0aeff8899e6c94ca25854560b9217 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/8c90ac2593ed0b7f1ecb60e82cb184fb11f2ea640befa1cc7b10766a5c02525d/4d19457aee330abf74c2.json @@ -0,0 +1,165 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "microsoft/Phi-3.5-mini-instruct", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": { + "AutoConfig": "configuration_phi3.Phi3Config", + "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM" + }, + "dtype": "bfloat16", + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "microsoft/Phi-3.5-mini-instruct", + "checkpoint_revision": "2fe192450127e6a83f7441aef6e3ca586c338b77", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.6.dev3", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "original_max_position_embeddings": 4096, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "long_factor": [ + 1.0800000429153442, + 1.1100000143051147, + 1.1399999856948853, + 1.340000033378601, + 1.5899999141693115, + 1.600000023841858, + 1.6200000047683716, + 2.620000123977661, + 3.2300000190734863, + 3.2300000190734863, + 4.789999961853027, + 7.400000095367432, + 7.700000286102295, + 9.09000015258789, + 12.199999809265137, + 17.670000076293945, + 24.46000099182129, + 28.57000160217285, + 30.420001983642578, + 30.840002059936523, + 32.590003967285156, + 32.93000411987305, + 42.320003509521484, + 44.96000289916992, + 50.340003967285156, + 50.45000457763672, + 57.55000305175781, + 57.93000411987305, + 58.21000289916992, + 60.1400032043457, + 62.61000442504883, + 62.62000274658203, + 62.71000289916992, + 63.1400032043457, + 63.1400032043457, + 63.77000427246094, + 63.93000411987305, + 63.96000289916992, + 63.970001220703125, + 64.02999877929688, + 64.06999969482422, + 64.08000183105469, + 64.12000274658203, + 64.41000366210938, + 64.4800033569336, + 64.51000213623047, + 64.52999877929688, + 64.83999633789062 + ], + "short_factor": [ + 1.0, + 1.0199999809265137, + 1.0299999713897705, + 1.0299999713897705, + 1.0499999523162842, + 1.0499999523162842, + 1.0499999523162842, + 1.0499999523162842, + 1.0499999523162842, + 1.0699999332427979, + 1.0999999046325684, + 1.1099998950958252, + 1.1599998474121094, + 1.1599998474121094, + 1.1699998378753662, + 1.2899998426437378, + 1.339999794960022, + 1.679999828338623, + 1.7899998426437378, + 1.8199998140335083, + 1.8499997854232788, + 1.8799997568130493, + 1.9099997282028198, + 1.9399996995925903, + 1.9899996519088745, + 2.0199997425079346, + 2.0199997425079346, + 2.0199997425079346, + 2.0199997425079346, + 2.0199997425079346, + 2.0199997425079346, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0799996852874756, + 2.0899996757507324, + 2.189999580383301, + 2.2199995517730713, + 2.5899994373321533, + 2.729999542236328, + 2.749999523162842, + 2.8399994373321533 + ], + "type": "longrope" + }, + "rope_theta": 10000.0, + "sliding_window": 262144, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32064 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/8c90ac2593ed0b7f1ecb60e82cb184fb11f2ea640befa1cc7b10766a5c02525d/bde8d1f238d097f95d53.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/8c90ac2593ed0b7f1ecb60e82cb184fb11f2ea640befa1cc7b10766a5c02525d/bde8d1f238d097f95d53.json new file mode 100644 index 0000000000000000000000000000000000000000..42125e3b6a2578a7b0bdaa31f960476132328d3a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/8c90ac2593ed0b7f1ecb60e82cb184fb11f2ea640befa1cc7b10766a5c02525d/bde8d1f238d097f95d53.json @@ -0,0 +1,165 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "microsoft/Phi-3.5-mini-instruct", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": { + "AutoConfig": "configuration_phi3.Phi3Config", + "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM" + }, + "dtype": "bfloat16", + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "microsoft/Phi-3.5-mini-instruct", + "checkpoint_revision": "2fe192450127e6a83f7441aef6e3ca586c338b77", + "continuous_batching": true, + "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": true, + "optimum_neuron_version": "0.4.6.dev3", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "original_max_position_embeddings": 4096, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "long_factor": [ + 1.0800000429153442, + 1.1100000143051147, + 1.1399999856948853, + 1.340000033378601, + 1.5899999141693115, + 1.600000023841858, + 1.6200000047683716, + 2.620000123977661, + 3.2300000190734863, + 3.2300000190734863, + 4.789999961853027, + 7.400000095367432, + 7.700000286102295, + 9.09000015258789, + 12.199999809265137, + 17.670000076293945, + 24.46000099182129, + 28.57000160217285, + 30.420001983642578, + 30.840002059936523, + 32.590003967285156, + 32.93000411987305, + 42.320003509521484, + 44.96000289916992, + 50.340003967285156, + 50.45000457763672, + 57.55000305175781, + 57.93000411987305, + 58.21000289916992, + 60.1400032043457, + 62.61000442504883, + 62.62000274658203, + 62.71000289916992, + 63.1400032043457, + 63.1400032043457, + 63.77000427246094, + 63.93000411987305, + 63.96000289916992, + 63.970001220703125, + 64.02999877929688, + 64.06999969482422, + 64.08000183105469, + 64.12000274658203, + 64.41000366210938, + 64.4800033569336, + 64.51000213623047, + 64.52999877929688, + 64.83999633789062 + ], + "short_factor": [ + 1.0, + 1.0199999809265137, + 1.0299999713897705, + 1.0299999713897705, + 1.0499999523162842, + 1.0499999523162842, + 1.0499999523162842, + 1.0499999523162842, + 1.0499999523162842, + 1.0699999332427979, + 1.0999999046325684, + 1.1099998950958252, + 1.1599998474121094, + 1.1599998474121094, + 1.1699998378753662, + 1.2899998426437378, + 1.339999794960022, + 1.679999828338623, + 1.7899998426437378, + 1.8199998140335083, + 1.8499997854232788, + 1.8799997568130493, + 1.9099997282028198, + 1.9399996995925903, + 1.9899996519088745, + 2.0199997425079346, + 2.0199997425079346, + 2.0199997425079346, + 2.0199997425079346, + 2.0199997425079346, + 2.0199997425079346, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0799996852874756, + 2.0899996757507324, + 2.189999580383301, + 2.2199995517730713, + 2.5899994373321533, + 2.729999542236328, + 2.749999523162842, + 2.8399994373321533 + ], + "type": "longrope" + }, + "rope_theta": 10000.0, + "sliding_window": 262144, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32064 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/granite/ibm-granite/granite-3.1-2b-instruct/88ab959ffd7f969e9ecf.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/granite/ibm-granite/granite-3.1-2b-instruct/88ab959ffd7f969e9ecf.json new file mode 100644 index 0000000000000000000000000000000000000000..44d8c1c8ae0834ecab399f9008ad99f40b13f27e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/granite/ibm-granite/granite-3.1-2b-instruct/88ab959ffd7f969e9ecf.json @@ -0,0 +1,59 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "ibm-granite/granite-3.1-2b-instruct", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.1, + "attention_multiplier": 0.015625, + "dtype": "bfloat16", + "embedding_multiplier": 12.0, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "logits_scaling": 8.0, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", + "checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d", + "continuous_batching": true, + "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": true, + "optimum_neuron_version": "0.4.6.dev3", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "residual_multiplier": 0.22, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 49155 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/phi3/microsoft/Phi-3.5-mini-instruct/bde8d1f238d097f95d53.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/phi3/microsoft/Phi-3.5-mini-instruct/bde8d1f238d097f95d53.json new file mode 100644 index 0000000000000000000000000000000000000000..42125e3b6a2578a7b0bdaa31f960476132328d3a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/phi3/microsoft/Phi-3.5-mini-instruct/bde8d1f238d097f95d53.json @@ -0,0 +1,165 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "microsoft/Phi-3.5-mini-instruct", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": { + "AutoConfig": "configuration_phi3.Phi3Config", + "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM" + }, + "dtype": "bfloat16", + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "microsoft/Phi-3.5-mini-instruct", + "checkpoint_revision": "2fe192450127e6a83f7441aef6e3ca586c338b77", + "continuous_batching": true, + "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": true, + "optimum_neuron_version": "0.4.6.dev3", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "original_max_position_embeddings": 4096, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "long_factor": [ + 1.0800000429153442, + 1.1100000143051147, + 1.1399999856948853, + 1.340000033378601, + 1.5899999141693115, + 1.600000023841858, + 1.6200000047683716, + 2.620000123977661, + 3.2300000190734863, + 3.2300000190734863, + 4.789999961853027, + 7.400000095367432, + 7.700000286102295, + 9.09000015258789, + 12.199999809265137, + 17.670000076293945, + 24.46000099182129, + 28.57000160217285, + 30.420001983642578, + 30.840002059936523, + 32.590003967285156, + 32.93000411987305, + 42.320003509521484, + 44.96000289916992, + 50.340003967285156, + 50.45000457763672, + 57.55000305175781, + 57.93000411987305, + 58.21000289916992, + 60.1400032043457, + 62.61000442504883, + 62.62000274658203, + 62.71000289916992, + 63.1400032043457, + 63.1400032043457, + 63.77000427246094, + 63.93000411987305, + 63.96000289916992, + 63.970001220703125, + 64.02999877929688, + 64.06999969482422, + 64.08000183105469, + 64.12000274658203, + 64.41000366210938, + 64.4800033569336, + 64.51000213623047, + 64.52999877929688, + 64.83999633789062 + ], + "short_factor": [ + 1.0, + 1.0199999809265137, + 1.0299999713897705, + 1.0299999713897705, + 1.0499999523162842, + 1.0499999523162842, + 1.0499999523162842, + 1.0499999523162842, + 1.0499999523162842, + 1.0699999332427979, + 1.0999999046325684, + 1.1099998950958252, + 1.1599998474121094, + 1.1599998474121094, + 1.1699998378753662, + 1.2899998426437378, + 1.339999794960022, + 1.679999828338623, + 1.7899998426437378, + 1.8199998140335083, + 1.8499997854232788, + 1.8799997568130493, + 1.9099997282028198, + 1.9399996995925903, + 1.9899996519088745, + 2.0199997425079346, + 2.0199997425079346, + 2.0199997425079346, + 2.0199997425079346, + 2.0199997425079346, + 2.0199997425079346, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0299997329711914, + 2.0799996852874756, + 2.0899996757507324, + 2.189999580383301, + 2.2199995517730713, + 2.5899994373321533, + 2.729999542236328, + 2.749999523162842, + 2.8399994373321533 + ], + "type": "longrope" + }, + "rope_theta": 10000.0, + "sliding_window": 262144, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32064 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/qwen3/Qwen/Qwen3-Embedding-0.6B/866e4ae3016710258519.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/qwen3/Qwen/Qwen3-Embedding-0.6B/866e4ae3016710258519.json new file mode 100644 index 0000000000000000000000000000000000000000..31f86236f4ee23e597605dae30d8cbd13c5abdd2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/qwen3/Qwen/Qwen3-Embedding-0.6B/866e4ae3016710258519.json @@ -0,0 +1,88 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-Embedding-0.6B", + "_task": "feature-extraction", + "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": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.6.dev3", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 8192, + "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/MODULE_034cf87f477c882b257f+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+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_034cf87f477c882b257f+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..acce97b877b5f39a07337e6c9e9711d6f64dbeea --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6070ba301fdd09bd8986151e94c7b92ce7819a1d22c851ff55373b6d132bdd5 +size 87331 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b848db71b2142a654c1dc08f31cdfe0e2d18a20e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3feae7061a6e87b40cf794818cfd435e42b033c7f8380972829f873fa9787e8c +size 236544 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ee0dd4b0c54757bd0926e8bae1e0f9ca3ea24b2b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e52cf7dc0e5f6cb7a27b7f359a858711690d867d08124c333abb5daa645c4718 +size 244847 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..58fbf6b9366d9e28d7f19321e85acd4cd96c0614 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/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/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ea080d99199032eda131f5d1b33b4950f85bad20 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e8239944f5c78d314d34c0e8ea62975adcc12d846f485c3c5fea351b127db89 +size 99591 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9f5d8a0c1209e350413b24c301d5f7b83981a863 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd41c9c13e10e8bde7c89554bd777f6c1c86a48d2df0bf4e2076c3086c4b5dbf +size 410624 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+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_0b9974a2d1726da77b0a+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d7f795dcc5d04cfab6ea709adfec7a023de0c1e4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3995113b9941789a06c77ea7f12cea66ce8f84e71f1c545e6fb307d19d5b330 +size 89962 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0e121956b8f2a1328c0e9119463cd1d97605990d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20e0ebd7df8002034ca5710ae915e4bbd03ea1897ed60c71417a46c80cfce934 +size 287744 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e3c25759d5c7e33512b4acd0f5f2d2ad7f794e85 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a17b050bc6ff253b2ed29a8a618ec985673ec3d3ccc738af645ab113f498de73 +size 296049 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..30b959bbd280d34b1bbf6daf388514213e35257f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_c7c088ba-1995-4e62-851a-c774a6069131/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_0c504f5fe9366071df6f+2b70e3a5/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6a2752c25c9f7e1092e2b55c010694e168610ce3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/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_0c504f5fe9366071df6f+2b70e3a5/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1e1b67d434a0825fb68af703f595059c73a68edd --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0af0e67de0c158c397a503ee4c1e80ca6bbfe89239565e96795dd3a821030e6 +size 103424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a30edd9141111b8a84fd9e30b7687018dd5718c1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f424802b4fb9ab1e755d51541e72053fa1436b169b387d6fe9f2c368c69f0079 +size 104320 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 93d459b10743a797cbda005a1ae1faf1fa90e964..a549bb0aa6262fd6cf0987ed27b45fa5b5e21f5a 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 73ab1f01539a8e396b7d742f7ee74013d42ff567..7e5eb38e3691fb2e5bf03867a60b534aa3ecec8d 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 7e2d30fc5c6ad11637dd1a4f0d1e5868af408a07..3946c1a7ea8396edd268027f99875927d6719d28 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 4c4364506f308b42c035ecaaad40a50511d9b357..88d6ba7a9f053a3138b6ba438417fe1dfa3ccaa8 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 d30fd4df1acd50f2bf392f6d2cccdf1f57d302b0..9680e7cd471e18eb40be647cf39f0ce52bcff053 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 f878c65cfc0f33913828e61b9d79acf04a7ff91c..c0efd259e42f1ac51bfc388ed47b2a05ff4af077 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_11301370888592189606+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_11301370888592189606+e30acd3a/model.neff index 7591eb220b96597f41af790472beb7735c59932a..e1f44a77e5f55b16a9cabb43aa6890bbbeeb3c0f 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_11301370888592189606+e30acd3a/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_11301370888592189606+e30acd3a/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6f50b3217d80f831aa266a928dfd5f0eb1f60737668b46a653da6035c136158d +oid sha256:c7e3ebadfc05c2572babe3aff125e581b50060d2ddf96e09ee3a4a0b55c19375 size 246784 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 7bbf60bd1b0e6d9f753ffc425dc54f46ce3cf9f6..047707a556b8ca4c8f713f9cfff5d8179693ffc7 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 a5e8d66199a43a95453933c360a372e323bb6ba6..af1cd0bfb3d2cb77767323b25a026ab0c2df7968 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 a804dbc2313b1e7a712c547b98c764df55a9fd72..01a6601c1deade7c66f5baa17ab78bc252243e80 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_13102010590082783346+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_13102010590082783346+e30acd3a/model.neff index 1486b9283414c415e7591d6826bbd6a011babe2f..ca518b4e5fdb5906d1b64c9e36dff8e1426c378e 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 7e6bc604f6f3ca0051f75362559e765ee6aa828f..bfe03f552b178072387399c095f764a405db0e0a 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 25655c5c25fa401091bceacf006eb5f29b590910..75c6b6b042c8db751277693625e88571d168c8a3 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 25d16d5cb8a0dd2820bcacb7255a98c16ef5798f..4297f586b04dd4e29a1fe044dcc0b52563395bb5 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 5cff3b009cc445af17753b0bcaa789ab2e59c485..fd7a93baf95d108fca00b16dce37debf97786008 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 8af8295a7c21082cd5a18f8f0be1702d7232b6de..b8ef7dc63d240f36c19795683be81c69f69724ed 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 a55b493bf50cb72ca643a5fa53a9aedee160ee40..7b67e1b452945530f75953e2e0e84c3109150ffc 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 4b46f1da21790fd8556b077fb7a108c35d501ff5..a6c5ecffcbebc7df6c23f8c426d4e47125c95d30 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 86902c1e393670ae52907cff83f883ecfe111105..61be42c2cf0c7ca3a728cd4eb39608b1a61249d2 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_14657035910656097540+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_14657035910656097540+e30acd3a/model.neff index da1643ae59a3a49bd814f754a4fadd411f44d458..ddea02ca250cc3865ad113b669db7f27d8e25ab2 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_14657035910656097540+e30acd3a/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_14657035910656097540+e30acd3a/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b839222648bdaa494af61a8fc9a9f05ab16323bfbe94b46469079fa51392480d +oid sha256:703a7e8e3848965928554cadbd5d5b8934c7f3d55d17152862a9579a043afa2e size 123904 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 ae428fa5ab499e03f1b5b9edc6587e162f3b3aad..e315ae58d5e22295eb0cbb051063891bcaf4ae40 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_15128894797204950836+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_15128894797204950836+e30acd3a/model.neff index b705bf690f49c4cba856c55f663115d65b2d2b74..7b391cb350dae52a3a4fafca084bffcc6d23ece1 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_15128894797204950836+e30acd3a/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_15128894797204950836+e30acd3a/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2651b3c11fc0d7599fa66a322eca8f38b728c267782e25f354ebb09e5dc53860 +oid sha256:d2bfe04556f19754f56e7322a2686563fef9d0fce7d3ab6fee4641cecbaef16c size 113664 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 45bb354a2d43d3c913078f75ea238df93e434e74..b207e980e5439561daeab21cb3323adfd7be78b7 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 f70107a590fd4ed5556f8ac30cde0d2b08158a25..b5dd900bbadea711698b9fe44bc5b49aaa6460b0 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 2db92cf2653206048bce4896624284a9917213b7..f03c2b76adb5a64aab948dfae77d1252685891ed 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 9a2fab7dd2b12895d429eb915840c81c9b57b42b..8a9d48cdc826aa3646610dd154dd220ab1738501 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 1ebc4d29ba87764de6bfe01102f265946ad16b80..a419887675b7c9116281e36914c8815a9bc07750 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 3f2b0eeca600ae80b0b3696af11976f719d66c1d..4472b44406d7042f5e1c13b6059f9e1d697f1678 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 447c2a12ba676a7a69912fc09e113efded2fd235..8aef027a34ed30d2d916aa6a3d046f1bd6f8d628 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 e25bc5f17777c0b40910025589d100c0336a8fa5..b6f67b88ef89917dc4eb0d028d1dd523022bdef1 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 0b0f6081a277cf00f1c6ba53a19f9363fc80ad40..5185f17560ff6c36f2e8b5116a41fffdb7d40cf9 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 448a4bd4d29ba914bd2f2a961fb1cfd203c06d55..c70de761e16a96c47a87c845683294819c9bf67f 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 555fdb94a3dd89ca695ff6d74dad0635c8267b1a..c78dff02e932b6640ef4b46dd34a946a29475325 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 470b67861176f973bdeac6d459d5bd7b0c606b25..274dcd2c214ce5109c1fb3293631607557445d91 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 f53a559d5b3a758a9fd4e5d37a67fa4549cbef60..6eaae6b24a80ba16038cc32548f845ae5d97dfdf 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 168777f2ca8cdd5ac508ab6e0dd1692077f62c9f..d49fd70a596e77b2c7ef963353fe15548f66b238 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 a0d4fd460b828b0499df4d9d0fb3e480dfc89c28..aa88dcb3bab4caf24f96af33c80709f8cb144404 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 9a0e0fdb38ffdebc5cd0056656c1cf1793c13dae..b7edc3faa4974a757c213cbf199ef3c48d0b2b3f 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 b7111084f4defa921dcfa9ef2247e3b2092daffa..8d463b6b6665c88d7262b7bf678b51b13ccef010 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 ecf52f347b5aca1c2065739a40ef9a5281c7a5d0..e0d125b92f94941e7191b93042f427b3dbc8c72a 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 7f70bb3df32e411ba258812fe998fcf9807e528f..01f6932c50e5fee00908d1e8f904c83769db3a06 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 56d4e207daf1e4f797a5a3701dd55af175cf88a3..220feec5f206264505e269f736ab0b0f7f4add63 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 5f2f4b355a08c839c16ea4f937a6588fe5839eb7..69071dcbbbde9361ac7117ae9f60fbed0b7f7406 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 4abc8e052254717ca11e6fb42318cf448847213b..0fc771a39959eeb081734430c7b3ed2e1703bc60 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 654ad0fd98816b360f3dc734a733e1ac655dfb77..9cc9a80035c716eeebac993e889e6c2b52686535 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 4c123cc272c2715b19765692cd396d6d05e13307..db9ea8632bc99545414a08ea1889dabc0f5243ba 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_1bfa3dd1929fbcd69193+6170d8e1/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_1bfa3dd1929fbcd69193+6170d8e1/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9c277888420f00defd99fc3c102007a98b09199d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1bfa3dd1929fbcd69193+6170d8e1/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1bfa3dd1929fbcd69193+6170d8e1/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_1bfa3dd1929fbcd69193+6170d8e1/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1bfa3dd1929fbcd69193+6170d8e1/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_1bfa3dd1929fbcd69193+6170d8e1/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..70722571666513ceb7fdf71f5d4077b760371361 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1bfa3dd1929fbcd69193+6170d8e1/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bbba449a7d271e5a8d4bacdda316bcd4fbe250b4fcd8c2cc48797b6df2f823e +size 576612 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1bfa3dd1929fbcd69193+6170d8e1/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1bfa3dd1929fbcd69193+6170d8e1/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6ed86e0478f3066f4cb09e5da917bfe0616bdfc1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1bfa3dd1929fbcd69193+6170d8e1/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdab6446096bf5a69ef8094d45c4af52ebe6a96052b2942853c8b955d4021c1f +size 30731264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1ed3a17cda0154a87362+a9ae6e8b/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_1ed3a17cda0154a87362+a9ae6e8b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1df346c44434b4ce662d4ba55dc40143bb8a7e7 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1ed3a17cda0154a87362+a9ae6e8b/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_c6ba101b-ea48-4866-93eb-72b0d6529f1c/compiler_workdir/SoftmaxWithMask/_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_1ed3a17cda0154a87362+a9ae6e8b/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_1ed3a17cda0154a87362+a9ae6e8b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1ed3a17cda0154a87362+a9ae6e8b/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_1ed3a17cda0154a87362+a9ae6e8b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f2ee42eb9f1aa790cfddd8e066da7c8aeb1214d9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1ed3a17cda0154a87362+a9ae6e8b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70f96487dad4bb02b98bf2c955fe59650a5fdbcf1d763fdf56ec412b62b5774c +size 5596 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1ed3a17cda0154a87362+a9ae6e8b/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1ed3a17cda0154a87362+a9ae6e8b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..636d43444c3ab648f3e20fba0b3ce4366be31f17 Binary files /dev/null and b/neuronxcc-2.21.33363.0+82129205/MODULE_1ed3a17cda0154a87362+a9ae6e8b/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2060474045114402138+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2060474045114402138+e30acd3a/model.neff index 6b247aad066560311c7ccb1b769081a3916d7093..12f951b729631a6c28b89db719724417254c4e6f 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_2060474045114402138+e30acd3a/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_2060474045114402138+e30acd3a/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:740ef99e8327b74c701d661c9a8ac0a9adc594cbb61003b76a111fd0009422e2 +oid sha256:e74788a5374e0f9fa746cdb72a7930cd3c3a51834cacfc6e04aeff32a65722d0 size 308224 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 a8dba788e077199f8c542309dbfdad0c35a4542f..a7eabda014d04f45f9353b42c02de063351dd46f 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 47d57ee791132fb8dad8f6059f27dad94032cdde..1566ed824253883d06190e1dcd92b59db6f29b77 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 cfbe0251def1e78689cd66bce9927e0d4b745d75..4dbc396c73dce9255227e00bd113bed205b99773 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 7981342c1f2c3a8d6bf081aa48a150c7db217339..8661cce9dff24faa4cd7b212c19f8a1c1c75e6a0 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_25ecfcd32b38ffcca9c6+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_25ecfcd32b38ffcca9c6+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_25ecfcd32b38ffcca9c6+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_25ecfcd32b38ffcca9c6+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_25ecfcd32b38ffcca9c6+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_25ecfcd32b38ffcca9c6+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_25ecfcd32b38ffcca9c6+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9a8f37ac6028da20a6fc48a5db5df10bae7d5825 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_25ecfcd32b38ffcca9c6+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:697104ca45a3b8220cd8b5005048d899143aba0ef32cb64d607921f3c3bef71c +size 698687 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_25ecfcd32b38ffcca9c6+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_25ecfcd32b38ffcca9c6+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7b006ec69095fefab0a8a154733290779ee1055f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_25ecfcd32b38ffcca9c6+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e11f8a0a87279c2e08b30370cb000cf08eaaf1b5304308751f0f4a777c65858 +size 646144 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+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_264f116884a2b72bfd94+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6458f163b8951b6d4ad5556b0b3d86d543ad2a10 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ae187c67a64a3e74e6011ae50b0e6c94dc42deb8837d5fd2d3815976ba432e1 +size 647980 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..14f77eb01ca9149572b8e2b56d044e949df0f2a4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:895c8e82690112907db75f5171231d516f995854e1e457475f71910ce8426705 +size 1721344 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fb41490a838041a7ad71c32f79ff37974d4c4239 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:252e44941ede467bc3a588799c8d1d7cf16bd444abe61442fd422e0f1ed4ef7d +size 1879095 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 30a0a11ac3465a5d8c8a7795beffd2bf78896e8c..3d47e3989f482e8e4744e56bb5b28051caabac83 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 5750732e5efe470b9b57f079419641300d777e00..c96402f92e6ec5e6f74121beaa6846345dd616c4 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 46207b7b488dc5be113735dafa52b50858b46510..16056c58bcbd071ad05e733b04c878028049da9e 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_272f23df0029fc228e27+6e4949b4/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_272f23df0029fc228e27+6e4949b4/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..2ad69cd01383a682715fed6c7faaf92a72533ca6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_272f23df0029fc228e27+6e4949b4/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/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_272f23df0029fc228e27+6e4949b4/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_272f23df0029fc228e27+6e4949b4/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_272f23df0029fc228e27+6e4949b4/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_272f23df0029fc228e27+6e4949b4/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3bd002443e382bd977473f159a240166b65dea86 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_272f23df0029fc228e27+6e4949b4/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ffe4053a0d1fa58b865155df091274ad97ee81c53fb69efb046674414efac1 +size 87497 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_272f23df0029fc228e27+6e4949b4/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_272f23df0029fc228e27+6e4949b4/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2b8481fa6440081a19431684efd08504faadc61f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_272f23df0029fc228e27+6e4949b4/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb7d76ba902b4a597e79fa601b7ec92ceea8adb63f93a365ec51d84655444f2 +size 687104 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 d41a56be8103a26e0e04ebf3daac0379f53dd92e..ebdcd2f72590fca4ad013c2f750aa56a58e421dd 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_2ec9ff4425f1d44d0576+a1c42422/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_2ec9ff4425f1d44d0576+a1c42422/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fe0db46178586838f7709a6602c9ba6fd36b9474 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_2ec9ff4425f1d44d0576+a1c42422/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_4ea02f0d-d6ab-46a2-9137-1c1d198d1810/compiler_workdir/SoftmaxNoMask/_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_2ec9ff4425f1d44d0576+a1c42422/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_2ec9ff4425f1d44d0576+a1c42422/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2ec9ff4425f1d44d0576+a1c42422/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_2ec9ff4425f1d44d0576+a1c42422/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c213570f630857303e7b0ec653018546c02dc983 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_2ec9ff4425f1d44d0576+a1c42422/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5efb0ea01dc0241314f91e19cbd9be551d1a66e7dbadd7cd4d6473d6b7d4b99a +size 3881 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2ec9ff4425f1d44d0576+a1c42422/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2ec9ff4425f1d44d0576+a1c42422/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bcd28bd3850ca0cd22d17bb670db442d42c9c4af Binary files /dev/null and b/neuronxcc-2.21.33363.0+82129205/MODULE_2ec9ff4425f1d44d0576+a1c42422/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 a5b78a85c0f92f5795817874c057d28c9540adb6..3c894d36d60bd1d343909d86540a4085bc3348fa 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_30f9fb1c90d72ce5be20+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..37de9a3ee84005de29cca59b6609e2cb9228a2da --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48e1617568b342c9625320623d41443db41d0299c2e4cc797461532341e9e31 +size 1112516 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..deef136f08a34afb3e8be8e1e4e4a440de1a00f2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:742faa0adfb2c2b72954353f6da2d323d64709797b12885cd7c003d975d59e95 +size 19467264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+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_35c78e406a558e46489f+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f1052d3240c4a54ad08c533fe37f79db20631ecf --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3664bc8f3f3c1fa0e185df41aa6990bc15cacf3e7b286ab8c41b6d85b67c35b3 +size 466477 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ea0eff85ea6570cba4fe95a620c1cf6849efb158 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52c9c37539cfb82225797c695b0fff9f2d86b4bbd52101eb0b2961116f5c658d +size 2499584 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c4892612bc3e74c449415d88d770a969de127079 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d076c9f13e103b86a8cb1fd1542a6322b209c0c221241356f167d50c8e5d6d +size 2574007 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+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_3be023fb36d494480eab+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a198ba7bce571138b4b06af78bd8dccbefbe71ef --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa458ce65b6f0fb7eadb4b6121961a9738c214b4472e8481d1700c71f63e9d5d +size 685219 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..69b9e4b3fd1c9abde545971cb749079c17e5746f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e0792c99b233ebf9a3c54cd029a9215c36a165b312168a97903e9209e28b3d4 +size 564224 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d636566cb9db72ca53bfd9572f1f82405eefce1c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce57aecb7318935aec7f8e89cd6876e85adc07130fd0effa440138e96d8d1c3 +size 583997 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cd62fe2a37aec84cc606fb66e51731e7347bfdfc --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c51e931fa6ea22b0eecf9a4950b3f8a3810995d5d3fc21745845cc0d61b3073 +size 86516 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a00d0f119e26cdf388699313c8e99f7e78edaaa7 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cb9aeb51fb2e58efea3ece7444882c58308b7feb5ba72463d9da59cfa7d700f +size 277504 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 94663b702c9423795a32e883a4b5ba45694110f4..f52409857f7e36744de4791f6c1cfe939aa8d898 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 34ca11bc69524df23dc6e5e067ec241c7a495fbd..75319fac2b9d5ec0792793a7b31b6b0aec093a6b 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 dc625ea03060bb3c7ac8dff9a7323d7385d42ce5..5907b9010aec150184a6bac4599df92cb9c69695 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 11e2dc8b698116794dbc5aee154e07423b7d8668..4a303cd66b74cf8c2dce59f8554f25b173ed046d 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_4371876575046bfaddbc+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4371876575046bfaddbc+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4371876575046bfaddbc+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4371876575046bfaddbc+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4371876575046bfaddbc+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4371876575046bfaddbc+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4371876575046bfaddbc+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..593edc82329726f3a8924172a7412b4ce7de3608 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4371876575046bfaddbc+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caec97126151bd653dbbf23fc78336671eeb9702fd4603e530ad70cdc393d045 +size 85781 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4371876575046bfaddbc+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4371876575046bfaddbc+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e5440b2902f4a9606108341d52d4447003929a4c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4371876575046bfaddbc+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44350698f3852f010bf1c980fe76ed0e68a82a6aa71053fc138ddcf0c57985ec +size 277504 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 f149812ab099f6d597121afbd722c3a0b19317d5..eb988d16ea58048335a9c0d0d8240857ba51a476 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 3b9516060e420437dc8e00de94c5285ac78908b9..3319e5031c539a9cc7896431be69836c3966013d 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 82c0e8d0d188908118c22e6f272c4872b36724ca..3ca3f8962dfdc0a49a43e35c9a3b51605e971151 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 f29206beb866648e3fc8d9d42ddc0297f8ac11a8..8ae1769a1bbf86f15f3ff90d823a87062a639355 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 b05f54ba0835b15f0b40f582c6e4a44fc8028cdb..9bbad00fd32205d07c55a6256d7a1f5e8c3616a6 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_4939721357859779936+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4939721357859779936+e30acd3a/model.neff index e15e501200f45dc19e3480185d4439c2e74268c6..6b02a3bfd01aec45007745e69d20eb9111f30961 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_4a866a7ab3440bf5039c+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+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_4a866a7ab3440bf5039c+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..945e57e16c7848c916b2f6eca8a1188960e23f79 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d22607d72aadef8956a0d954151ea298a2e814e5fcea013f9d3fe7608d67cd02 +size 1176661 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e4d63d1a755cd0d3942e8e85f9e84fd9000e91a9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37e92993932d095d6ecd7546399c32c7d7db086a06cb48e2544e43d370dcc77d +size 5284864 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..06f57cf6ced2e95efb11c124ec814f8497078a33 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05427eb7a7a987c611575051923ad575600b9aa40e4a4d7e7b1c22595df296a5 +size 5470443 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..aa1d2662286ce104c21eefd7e3a24d9ad19f5230 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_284d6788-f40e-415b-a2a0-c3bd0cbfc006/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_4c340605e5cfcfb52aa0+4cce07ab/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..25ed99420b1eed46a37676f21db6769f76718a00 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e060f177f47b303e69f2656ef1d2e77f322ea5fb3bb0d31df7af05dcff96f94 +size 15710 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e3bbc331e31e85d0c5d7b55b60000b8781ce7a39 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ab2c030ad2646a6087d9894e3da114c9d4b18e3e6d2298f10cf3651e8b144d +size 287744 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..911e4e1487f0b7bdf0510c13bd74c4cad1980be2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44152eacdbabae4f5b4fe5f7a9ad305d71cb467aecfcb8525110d364df10de9 +size 293460 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..7d1678bf25666438bbebf65702a2233ae75c43c9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+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_4e8633381936708d6422+ac10809c/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7b55a791216015be87b06cd9efbd22992e73b0fa --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8c99f319e3b4bbaf6a540f03e0afae6dd8fcb112645ca2138aa4dc94372f35 +size 1605083 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3236f28b7dade805876ebdb7815603ae3cceacb3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db741bfe34a35c7edf77cfbf87849852eb433fe3fb76dc4ec9176de8580550f2 +size 779264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..635d8c5af91aaec236cf26051f625941629d0c3d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e930876fd38228fb3fc32f582325a293592aa02e86c48a65fd04f12057cbe58 +size 787152 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_50508839decfe015ada3+f842d7ff/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_50508839decfe015ada3+f842d7ff/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..2c198e5ff0482a4d3c2ff23ff13b044f71bd6bde --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_50508839decfe015ada3+f842d7ff/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_0af9f47d-3042-4e26-a953-2f3c7cd0b80f/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_50508839decfe015ada3+f842d7ff/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_50508839decfe015ada3+f842d7ff/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_50508839decfe015ada3+f842d7ff/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_50508839decfe015ada3+f842d7ff/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f1e2473c54cffac949ecf31d3b6ec636c290545b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_50508839decfe015ada3+f842d7ff/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_50508839decfe015ada3+f842d7ff/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_50508839decfe015ada3+f842d7ff/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c964de5e8b3ee90f8698104ee5870a6d938c0af5 Binary files /dev/null and b/neuronxcc-2.21.33363.0+82129205/MODULE_50508839decfe015ada3+f842d7ff/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_522781774461263035+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_522781774461263035+e30acd3a/model.neff index 7b5937f2ccb95370242aeb254d50b6af14197862..6d9ac6fbb0230ab40d5e8d12e5f11f6aa58c9a78 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_522781774461263035+e30acd3a/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_522781774461263035+e30acd3a/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f8a66aeab5cd52ba30ae5fa833b03b8d13ff5f858954c10b83a171410665c7ed +oid sha256:653c6fc1b7fa72743f59a55b64031a7354f360f2afb585852ea6596c12d56eb6 size 216064 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 522e5aa858facc3f2ed2101c84cd2c0df4e4a891..6dec2aab7d1743c0e1e87bd41b5616eb0c8947de 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_5724544066416780383+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5724544066416780383+e30acd3a/model.neff index 71aa8f4bc8de08c1b7189e0da7d2ed2586111d0a..c600e357cb612d3d05f4dabcb7118ac4f0010e6f 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 0d4606f1133c5621d8ab600af31276a59ad0149c..7124925e18d3e3f740d0b77af3a8614ed87bfe31 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_5882b7576829bc99fe1e+a32116a7/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_5882b7576829bc99fe1e+a32116a7/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3c18214665ab208ee16402ace66a8dd081416d1a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5882b7576829bc99fe1e+a32116a7/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5882b7576829bc99fe1e+a32116a7/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_5882b7576829bc99fe1e+a32116a7/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5882b7576829bc99fe1e+a32116a7/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_5882b7576829bc99fe1e+a32116a7/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..055ed19c5621c00ee9ee0f0dca2b0e5e9efd4e33 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5882b7576829bc99fe1e+a32116a7/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a40f0cd3c7dca2dd3657faf7ea4be36730a9e3b658983e8eccb0e546418acf8 +size 1317628 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5882b7576829bc99fe1e+a32116a7/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5882b7576829bc99fe1e+a32116a7/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..10c122f8957e94dcfa98beb475e35d254e388d74 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5882b7576829bc99fe1e+a32116a7/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c948699671b4aca40b1852d4ea6e31cf1e420d8940921cdce9fdc8a45e5e16 +size 584704 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..6a8c3cdf7b0a0816ed69a29bdd58ed2cfd39e141 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_30c4c284-1abe-40ca-a4c0-28806364d0aa/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_5ca02efa566c733695c6+3ab2fb27/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6da2cba66863fc471486cc2a5da22b16c00d6480 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/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_5ca02efa566c733695c6+3ab2fb27/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2e458f57a528826dfd9e6b2683c2f46c62d4d13e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe2006daecfb29a250cb0277728f1e11e8b815f5f8de6d55e19d8bf7468afcce +size 134144 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3cc635bfbee57ce50090487c19ae95425c2b689a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b54bb7d29bd2f49c900e88e1e0772098a78b3aae24d64578448391b92de14b6 +size 136222 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 767cb39f05add925ab06d763153790ed8e79f9de..202ab43cde42f074f9166e0e151ce0c2d6b91c6c 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 6f9bc495ed372953d1660905dbb58b438ca7a654..f0d6f1233299c0716cc15f7c59e0f52ab10f60da 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 a72dc6c1720a3db3735fd0dc5ca06a73cb8e1e1d..8906625d1bff8a427500696c1c20a6c1c2d31c2d 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_649c25ed694844adcb1e+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+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_649c25ed694844adcb1e+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..16f742aa0c0ba4cf7346ea721a0e5941f8c4b03b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91758a92fc2482c52186673d040e5be878b57bca125a35908c2a0975b873afe6 +size 1190261 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b180247e9e45de98225b4cf38d4f3baad1d69483 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d461cb3e00072a703a6c09884b367ba386c45e53d59a5e1b4d5f7b124cbda49 +size 6104064 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2bd392de6353566315e16331e2a20182ef88b76c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30ee70f7e38e3fb573451db42d1d293e4ca461383e2ff298fa777534b4adee32 +size 6289083 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 785b7201102bc20ef4462ffa99f3ef2387c8e590..3780c0aa6c23310ef4776ddcbbdbd6e19c802682 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_6711765444274762085+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6711765444274762085+e30acd3a/model.neff index 4df7a6bc7305d6d71f2336e9b126d49f65235c9c..40149facbfa2e976582d22e22947d7250e82d0a1 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_6b4fc5b451fdfa1b744b+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+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_6b4fc5b451fdfa1b744b+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cba5354d54d942d72e992de3efe098410e499e78 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7a5cb950011497b733420809fce6a05df5747c5c0f9a39528678022abf16da5 +size 461030 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1e8f19c9fed5ea82c7b10807c9ecb7187832b810 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dfda5dda4da7ade55c832c26447eefe2b0cc6c86039e7ec7024f105dc0c794a +size 2407424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..32c52f55d6dbb5bd7280ab91b22a3324631c2c00 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d618a1abe8473b0f69e3fc8dbb07d3da8aa2e7f7d63a740f62fb5f445b5c8f95 +size 2482071 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+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_6e8fd65e06dcc6271828+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d32db0f62b17569743adc702e73a602e27a2198f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4653c8a27f1830cea0a2da02cba478b8ba0418dc66a0086a10696b56b44daf2 +size 88938 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a5920748f34d537f31bba8935bc3f5351dcf8f44 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64024d2b1067e7f01b3ce32b426a6d69d6b81e5dd16b1967963cfccb39a20ae3 +size 287744 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0e6b9e0ed8b22e06a35df4dd1d302065c521caed --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f411024cb830734967081215e37dfe9e85c07f71e08aee54a399f8a9b1d89b0 +size 296049 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 9aa369f5e93f5b0e3abe40c94b39e517f1d82aad..e2da7ab1021a4bafbb66036a86713cb83bd147c7 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_7247213647965899113+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_7247213647965899113+e30acd3a/model.neff index e363a8f0ec700563e9799ebc38dcb6bee87e3752..282f6d9f4127b73063c2b4fd1c1591f472ab388c 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_7247213647965899113+e30acd3a/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7247213647965899113+e30acd3a/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ed4fb78cd5566dc5686b6a30ffd7bf147f5d5282561af63607ef66d87b13b055 +oid sha256:47c38aec20ebeb1026ad841570f9bc20be92ff3a13f1b01fa29fc1279490929c size 113664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fef90614ab82c86d360411b32ebda263370a2a20 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97b4fbd4e4b1bac187030acdaf26a19248cfb8fc00292df038163833ebeebd1d +size 86516 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..dd658924ec97dfe49b3e45e43349ad20a701b983 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:127a8bbb7b4a869f65850f5fa71d05e5b369ea7d074b456da640790c24c50357 +size 328704 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b29ffb2a0c93236886340e245af915ef679fac13 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aa6af366b9cdb986dc519010b3c494246cd70f4383ccfac590ad2adaa086002 +size 82563 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ee1af989e6dab33ac804129e24d94b0f68bd5256 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79a93e87a00e01dd6a3cac7bb4b144d3e417c9a7b5c05463f126d4d34e9f2aa9 +size 349184 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7671391308733910418+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_7671391308733910418+e30acd3a/model.neff index e85319867643dc67af64a1fa9877e027e74e5085..cfc2d36adaa8a950ba8171ce3eab73c8bf687e26 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_7671391308733910418+e30acd3a/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7671391308733910418+e30acd3a/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:57cc409d4922ed818b74ff1c2766f41c74d1660418c5b67236ac8d5949ae4888 +oid sha256:1e61be9173d3701e38214f882bf47a7e52ab0e9d43933f2b53e1382442b823b3 size 308224 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9c277888420f00defd99fc3c102007a98b09199d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6c1fe5fdf7303e4461f7f6956db6963914280b72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d01563b8a34e0d0e71c2922834f4acbf50dfab74a75ceecd19631a57cfec956 +size 901341 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2e6b3a91c6e053d96c1cbf01f15b3e9b1ae882b6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f9d410d758a6e8ef972d6e8338675f84bd30737672ace885f81780bdd386b44 +size 29604864 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 8b06fabd09d9b151187006911e6769ccfa8da1db..f0fb3e2bd8b699c17656bc45f34c43d0fef5d2f8 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 e622ca4b732a548588d1981636438d2bff67ba5b..ed1bf459dd428709b6d5015af1ded9a8b9f77962 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_7975285533996118114+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_7975285533996118114+e30acd3a/model.neff index 93227fc0ceee68f0825de4de34f9ca71e4d7905b..f8921a6e1e982fc2aaaf569e82d4336971b8f3f6 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_7975285533996118114+e30acd3a/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7975285533996118114+e30acd3a/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:81ac5658d13299d9d8d40dd5b7328b36256e74d7f9442957abc1a9565c44de88 +oid sha256:842700c88897feed8a98925dcb003fb25db7e0ae9d559445b3a532a5cb79d24e size 123904 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+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_7d8253c434168957472d+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1ab3cd9ed119ad5af093b77d9dd49296a8dc0243 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74eb5f967b5d464301a36a1b050630eaa6b3fc53b788cc5ba31e48fa6108d3e2 +size 88040 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..30cacd29d372b079466d25611ae818454e8a9ba3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0c5c8dde5847ab4fdfd6fd995588f0d50042a22ab0a350c92eeabf790dc09e7 +size 267264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..951d2cb880bdf58b9e7718106eb44e47681c22e7 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc121767ec527d19649e5570646ef05fd791ab54a46b2a29b5731d8bc8d2a2b7 +size 275539 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+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_7ec08bf0fb6b63a494ce+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2a450b6af082c91183e5a7c7325c90e666acab43 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453a5d47d945bba2af30f475dd6e653f24bd282964d531a1847a2878e14cf32e +size 98222 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1715ebee4af7581dcca2d90e5c07d9dae5f3e35c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af99f603980b0e22b4bd0bcbcc9daacb0a60906537e3a2ed4d17af742237474 +size 287744 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..386c5963aa8230f1194e896e483aff4d7b40c300 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6e6d1f557317a4f6d4c0fa43485581c787b7cf51cccca3ae4c4993876cb094f +size 300502 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 8d9c1e6627f227c33fee85ba96fcf16e6aaa63e8..512d38b12049a7284df45acd0525433986823b1d 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 66f430525d2eba4ba86e803fdafdea32da6ff049..c9ac9c05cfb8f34170622a9a326504174e900729 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 2e64a5e8c2ee55e493aa09e1e4e5f973fd1665c0..cc83cb3daa6b4903d9a59031ca957d6623743042 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 ec0fc347ea6453622e5207419066ea6d9f9469dc..2ebd04fdab30191a7cd38217678fb7b6ba355caa 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_8882592820567938515+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8882592820567938515+e30acd3a/model.neff index 74647f58efa6ead62bc68efea6f12d9ca039ec63..a8a990ff09de5c57b5ae8d56dbdc6583ddddad3f 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_8ec74b7503cb0a5e0b12+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+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_8ec74b7503cb0a5e0b12+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a4c4d5c62f65775d1bf2cde3f8362ad9c93be367 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c4e593f3bb0360939090797b6d0c9b963e03e6b699c39027fb402c822068266 +size 85466 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5baf812b8249f23ec1d1fc454e16b52c9ca5aa91 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020ecbb296d5f0717eb1d401173cc220f58e7c4355a50ad1e884bfed5b5e5826 +size 308224 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fe7ecaf28eeb8ea2e5bb2b766828405684fb8e11 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:477abdfbdb0c09645c6c88b67b067b8abb05185b708c05407c649ba2c7a9d8ac +size 316529 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 f498a3acc5658df73797bdf83ebbac6602b09196..a3991940ad0fc81fde76e03fbc0155be04695214 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_9176004544586841168+e30acd3a/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9176004544586841168+e30acd3a/model.neff index 0f1524f9859b27022a2e0927b1ff137f6eda1651..7fb44723562adcaed222c886dd219fdd6805a360 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_9176004544586841168+e30acd3a/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9176004544586841168+e30acd3a/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a5982d62af64a0e7de09e0cffdd7dbb150df3fb323d7aeb6a11839739f6d3d14 +oid sha256:680550f36a11a20141c4d737b5219e6d9f052e637fe45d6d2255bea1f3926b62 size 267264 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 facd0aac9b0d67b84642002ece29fe7a1e66c8c8..22a0d1fc48e602552f0bfc7a76f50f47ec8566b2 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 ae039fba568665fe4c1a8fa7d38c87fdf1c6aef0..0aaeec477b8fb447fda041269ef5791db1f48060 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 28d4c79fc1507a78d1585730558479392914c049..e72fde973d1795a73c79ea135249719f1ab856b4 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_9efcdde20b63764672c5+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..dc0424e2316e399b9c17b166128cebab66965632 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773bc7c1c57c0bbbfb8bd8f5bc21006403d7a993763cd6c645cad7eaa9c49424 +size 626700 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..015af2b33c2fd90344d35bf2d5ad33f4bf11f76f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f39584a4867b10630a8cffc6de47ae32c0c97b59632688c6185161d5727c436 +size 3738624 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..66770cde335b0f98d7901ab01b28a3ad144925e9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_e31fdfcb-e2eb-4fa4-afcd-59587056a8c0/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_b0696c18110a46d8a884+6f0a400d/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7c9dad922c622d319a744f1a857081efeecfcbc2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fe6d462a2157cd14f0b384f680749ec3b54cebe313ec3215f40ec6a14dfad99 +size 10205 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3d21b0ee5cf18f5fd78cbf65520bc06a8372963d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d41133c33e6965dd10f1a72cd473ca3eb6a82534dad093cfaf70de827b0d7e7 +size 257024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..65a7928e8eccb0762dd097539e1cf90edf85af4f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eb77580ad29dbd02ff68e168ea093f136a9ede1bf1964b02d22964ef7d36abf +size 259902 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+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_b671fe852f9096fe7aa3+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4b5a2c1e454e790bbc08e7159d34b2943e410f60 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6bd1e1a6feb8de770e02e83b7b33989ec690d899d121f24067e56cb86688229 +size 700565 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b1e8ec18562bdc1a48e1bbab9b25c6f70b49ef7b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453a330eaad36f6175ded39706b57cbf269b5b0ccff84de6a33bdd0a330a9176 +size 1977344 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..71aeeadbf5f298c05d1a2e60c4e7109823f188c6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcb56ea78ba0e9f7158d5608326209d2c05521dca1e95e0ce4df6b088d076a11 +size 2135210 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+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_b72fc7afaa1831a24a09+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ba21eaf5ffcae556024bbc0e57b1ea4bd22b51be --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14fe46ba381c9b8837f7c31a50a8bc46546ac78fcb23dd7184012bb624f2c5ab +size 474669 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..96791735d6d1239cd9bad304a60a9e73edb0c74b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f0844147b09e8d566ac2e375f68e7aa770bc7156102cca3f3b6a449a08c6b0 +size 2827264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7e1ab1412972998a4c368331c702a32c62314fa2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f09d376fc155513bd9f58c8260783708a412afa97a4ef065ddd8575930cf3f2 +size 2901687 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3d7d85cd3d975162683053faa369dcc6259604af --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+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_bde9ee2bb7e53f22e095+80d05c3f/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e534379da78e6567a44fb68a72ff5f337e03e6b8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:806cdf41496d18ef12c951b58e46fd42c30c3c6c98c95099e4ebeed8082e4551 +size 77263 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c83bef75c85c3f2e81de0edf4d93c9ef119119b2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a05a33c353df928d738065e1ca57a35c74d929c31b8662fff455ccc485f932 +size 359424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e8d6325c4d097b760b9bf1ad337c938c4c7e9472 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb3c4f3aa7d70239ecc7a87a3472780acddaa5d9e3c9292fc224f28803224a2f +size 371418 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9c277888420f00defd99fc3c102007a98b09199d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..126b1da5012592932e7539bd78e5b7adbce82351 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81f7815b5ba3c0b655d17e94106a63989becb2cc1a8362cdc2c3cb8d35adf638 +size 1601984 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bfd985a4e0b145f82c1fdb1e1e4792f5f7052aa3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d7e6c268fe96c159c540a84f8fc5f4450b913fe36f0960ab0d7bdbdea7c7276 +size 123423744 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9a00e361e0c99c74b40c3124325f386b51d6c747 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_b572ae9a-abf5-4667-a908-807a6c95f1f7/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_c69b5542e96ab576f244+755a2aef/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b7d6b5e9e594424e13d52563c23238c415be7ede --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44717192a9764770e2f9a465d2bb14be5d4a5074d2608bf01335f863e368c136 +size 30765 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d304232722b553e7be21700e8dd0da2a68a95a03 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c71d5114696a541b4eb92fc5cf27c57bdb5a4a7491301edb9cd22fad1bb7f0bb +size 369664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2ec13fa77316e2cd95091c054b6f0f749dc09c6b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ffd9e64ca7910930fc6e9b296ddd91d78a2ff7599f010af7eb21cd5f05c0942 +size 375423 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ad06a280211af759fa39a3121c5a566272be1618 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_61bcb6db-63f1-4b99-a65a-309682edf952/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_ce61e92cac5a58aac125+4af285bc/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f231a34a9f47b396fb69fba3bb7503a6738ea844 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:743916e38db52503f5c886aaa255730e9e445ef8798f6f702023974a92bdf992 +size 12508 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d5d84dfb69b832b0df169b6f5d0db4cc4bc1ad1c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1411eb5dd8e61d98e399fbbca338ed3e8b29e735f028e6961cf7be8924c008df +size 1731584 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..94c8567a0b00b8c091c8ee47ccf63f3b9a3b1902 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:936d66057acc3d33489137b3df231b65dead421a275252ef09561426e9809d77 +size 1734583 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d13a49630f5dd1c33c30+a5701961/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_d13a49630f5dd1c33c30+a5701961/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..d009a516a4685c11eb8566986a4d554ea177b68b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d13a49630f5dd1c33c30+a5701961/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_5c64cfeb-de51-430a-9f7b-19b968d86f77/compiler_workdir/SoftmaxNoMask/_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_d13a49630f5dd1c33c30+a5701961/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_d13a49630f5dd1c33c30+a5701961/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d13a49630f5dd1c33c30+a5701961/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_d13a49630f5dd1c33c30+a5701961/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..36897c006be58fcc135059831fe41ce96ad676a1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d13a49630f5dd1c33c30+a5701961/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e542c76cf27c3f807feac47dd3f58fd4c308e8d9e932f0732774bee19d640d8 +size 3881 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d13a49630f5dd1c33c30+a5701961/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_d13a49630f5dd1c33c30+a5701961/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..85f5d7f41275d2335ba9019ad482b252dc1b7291 Binary files /dev/null and b/neuronxcc-2.21.33363.0+82129205/MODULE_d13a49630f5dd1c33c30+a5701961/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..a7a40c022faf4beb0fb20246d9c1f9c8f32c6900 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+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_d13ee67d85c8f49510c4+2dde74c7/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..34c10744605be7285511b75056ca542db7495449 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76ef501a3581a148437cc7c1de22a40a971f28e817b1669148c342bcf540dc8c +size 94389 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6a17fa471cac887075bb7100c752e5791daa12e6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:665e0a6ec6fa680622115a4b0df299637a2c5c45c892c70ce57274bd8b48c056 +size 379904 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3030b29948b708d8185d34fbcd338ef02ce8aa2d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3dd8f10a729eba836ec241191c3830cd94fbe20ea7212626af36fe9c491b91b +size 389573 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1b8cc492843eee5a787049e9fae1438081354a1b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace88606c9b20f0bb66e05d84bfe67c839bc818218be90eeebdb166780ad098c +size 436575 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2accc2b535ccaca1f0a0c4ac6cb88536ae4acb76 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13b654e3c1c3478ea60892b640f089ce47329e5b186a2fe2ce068e51c433461a +size 7916544 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_dc8b7694e4da228b54af+a3421cf1/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_dc8b7694e4da228b54af+a3421cf1/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..a52ed551021053f41b9be998bbbbff49fc831f9e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_dc8b7694e4da228b54af+a3421cf1/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_d5c788c4-3131-4e13-b124-ffc228a3b5f9/compiler_workdir/SoftmaxWithMask/_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_dc8b7694e4da228b54af+a3421cf1/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_dc8b7694e4da228b54af+a3421cf1/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_dc8b7694e4da228b54af+a3421cf1/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_dc8b7694e4da228b54af+a3421cf1/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1122d44653d734af6a44cd149690f70cdefd9b05 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_dc8b7694e4da228b54af+a3421cf1/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9a258ce111db27dc5ba46ec4f9f6877c56b0777a5534c0eba14488ff9eaf298 +size 5596 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_dc8b7694e4da228b54af+a3421cf1/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_dc8b7694e4da228b54af+a3421cf1/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5ec8ec4bff1b0eca321a9b48fe64336481118199 Binary files /dev/null and b/neuronxcc-2.21.33363.0+82129205/MODULE_dc8b7694e4da228b54af+a3421cf1/model.neff differ diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+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_e8a43167f74176083689+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1e56898b7af5d8e6e6b3104058edbcb8601af675 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b19af61fa742be1b7b1939355a8d08854d06690b4fedcf23ccdc735ac9c937 +size 787448 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e71a833628d7aed520f8e35566f844c754c56546 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93d15158cf12b6073c0d22f07f44812b13ff3b29d0d096c1793aed1eab9e2659 +size 7752704 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..872dcbd1841f7ec518b3a34ef4e505823656d8fe --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00bb43bdb070ae02c940ccab4bebdc8eddcd4193500c118973008afced0bd8ed +size 7900008 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9c277888420f00defd99fc3c102007a98b09199d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2d480107d0e0f5f805e7c13708aed8737174477e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27539d19b9af3475d28020176d5bf491a7561b27bf9603854838953ebbbeba33 +size 584804 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a5739c3afbf6f46e727aa996ae0cfa7aa6f31253 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56601835528fe12aead65834ef0d7922734177b27e8fa09ece61312ed1a65e22 +size 49460224 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d2cc8a0102704f9129e375ce2e5aa2e4e942ff82 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec4a32b91839317720cd5fd8d69c7e6a264b48ff0e26518ecddc87fa3803a810 +size 93725 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c5e1294c2747fd1a62833f73d46df60ee4dba8ba --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c49e0feecb4c42b3f5f528347164fb2bf55b2fd3132a132aa8a3dfc28df05f1 +size 513024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..eaef792799fd6fe5475f634fff18478679c03283 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8e2c4727ddcc462f4903ac93e37a574e27c92ffc217b6ac0ddab5c773cb7c89 +size 766575 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..736d13932332cb09fd2f713ab174b188477daaf1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8ac2cbe07a2863acab7bee12e367eeaa57b0ada8c64f8791d327272e66a4d5 +size 27065344 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+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_f76d71fc849f0090bedd+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e36f97551551de4a96e7e86d7066635d172e16d5 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24806723e52b78cda4a35dcf51cbcddfcc5dd2a436f0764821610e748c49ebb4 +size 647980 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5be83711c5e5bad316b78fc57f9ff2338330443d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ab4a4d19224b931fb6a8715f0f6dedc9cb89e011b386980932d6b74aa7a738 +size 1752064 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9ebb2f5d200f271ffb33a784e5da8b8573eee161 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f54a84b397bbe1713c7e505b1349da8a79c07a59f42a085c48aec01319c8b81 +size 1909815 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..812c7ef23ff89f2689b786e476140ad1eec20b41 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2d1fbe5487ee2a9172ff14bfd9464db9baf5d3206685b3b9a7c6353653b4784 +size 626700 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b86f833a14ea6869981c82cef5b2f2600346f4f9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d8451b083dacba0a79bf61ee10edfc9e0f0a9b371f606af91b43a46a1447d95 +size 3738624 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fcceb91266ba7987cdfaa95ca6c90595999f66e0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f334476e338d54c44756c80605b6e5189db2db2ec176ca24ce8646a7aa6d7f28 +size 84526 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7e2361dbcc491ee0a3c7c39514f69ffb650054ba --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2639add9d6fd27e3f0a5164d11bcea655a7434f4ec15e954dbd99d2af9af90e +size 267264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+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_fadf125c58ba12884396+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..67484e0f10dd4d127787f709c0ca351948f5a8fc --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aba95813c800d358a9d44716c42b2242031e30d328a6e121c6d772fe19e702a +size 773757 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0d372465bc621623e3435ec764778934dbc94d6f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634c7dd266a9c37a9ffeec61612cbdcf3aafe60b77f712c0838128e5a17036f6 +size 7906304 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..cff4e40a8006f1f9085e4b0ae476ca8892f20190 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa23d244cf5ec688cdf638c303b9c7f6bbca40af1a75e4c90b05735f8b249744 +size 8053608 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9c277888420f00defd99fc3c102007a98b09199d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4d2d625c24cac7e4f0cefcc964789ca3ebd85e30 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e88c43672584e656e17b9ad3f916495357ba040e463a87c78ff52421672da806 +size 1045279 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..71df9f785f2ff437fc257c80e64d83e9344bde39 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def0e8048b5f37253d7a57612b07a29db5f739cd85b16f13f9eae7e152e6da72 +size 111504384