diff --git a/.gitattributes b/.gitattributes index 57d3df4ea6f3716048527fccb78c1d55cbfccaca..72b6800c25504d16dedebdc38612cefa6f2c6e13 100644 --- a/.gitattributes +++ b/.gitattributes @@ -14691,3 +14691,90 @@ neuronxcc-2.21.33363.0+82129205/MODULE_a60ee6952450ce742f72+f00715ce/model.neff neuronxcc-2.21.33363.0+82129205/MODULE_a60ee6952450ce742f72+f00715ce/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_e0dc711f77a602f2be1f+25971132/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_e0dc711f77a602f2be1f+25971132/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_210575e529dec63f9202+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_250ecf58b3a2e7ac5757+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_42601fbe748660a77be0+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4ac5ed244908e0b23eb7+677eeb9d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4ec35bb57fbe1fdb6c78+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5299d075a10cd88b75ef+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_60946426f567b03182de+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_78a467fd5a1d9f7adeef+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_8c6b204d1bccf64885d0+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_8e336cee3fb428dcae05+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ad0618d39f30ab05071a+677eeb9d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_bee928e1ff2bd1f5e3e6+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_bf62cea1b964ce1cb653+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ef557fc37471d6bfd06d+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama/unsloth/Llama-3.2-1B-Instruct/3403115c880863fe4065.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama/unsloth/Llama-3.2-1B-Instruct/3403115c880863fe4065.json new file mode 100644 index 0000000000000000000000000000000000000000..e61b6b2f77a834566a6cd079527df0dda438f50e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama/unsloth/Llama-3.2-1B-Instruct/3403115c880863fe4065.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama/unsloth/Llama-3.2-1B-Instruct/5d6508f3c305508a9e35.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama/unsloth/Llama-3.2-1B-Instruct/5d6508f3c305508a9e35.json new file mode 100644 index 0000000000000000000000000000000000000000..6b2505e40453b13b307847b80d1bbdd00627cb00 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama/unsloth/Llama-3.2-1B-Instruct/5d6508f3c305508a9e35.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.3.dev3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 5, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama/unsloth/Llama-3.2-1B-Instruct/fcb5fb70d7e694e229e7.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama/unsloth/Llama-3.2-1B-Instruct/fcb5fb70d7e694e229e7.json new file mode 100644 index 0000000000000000000000000000000000000000..12977c903e112c4abeabd8687cc920699e27ca61 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama/unsloth/Llama-3.2-1B-Instruct/fcb5fb70d7e694e229e7.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.3.dev3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/granite/ibm-granite/granite-3.1-2b-instruct/7bd52b717d35cfb4df0d.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/granite/ibm-granite/granite-3.1-2b-instruct/7bd52b717d35cfb4df0d.json new file mode 100644 index 0000000000000000000000000000000000000000..39138bbf2aed5d191546576abf2ff337599187c2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/granite/ibm-granite/granite-3.1-2b-instruct/7bd52b717d35cfb4df0d.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": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 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/0.4.4.dev1/granite/ibm-granite/granite-3.1-2b-instruct/c7cc8db735ece7aeba17.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/granite/ibm-granite/granite-3.1-2b-instruct/c7cc8db735ece7aeba17.json new file mode 100644 index 0000000000000000000000000000000000000000..492c8c0472a0a4055ea833a61720a99eb2c64091 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/granite/ibm-granite/granite-3.1-2b-instruct/c7cc8db735ece7aeba17.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": 1, + "capacity_factor": null, + "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", + "checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d", + "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": false, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 8192, + "sequence_parallel_enabled": true, + "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/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/0ed08478601ada771841.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/0ed08478601ada771841.json new file mode 100644 index 0000000000000000000000000000000000000000..d536d332e72b08b96844fc738765c776f28af481 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/0ed08478601ada771841.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 5, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/4b20db2f875ddad665e5.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/4b20db2f875ddad665e5.json new file mode 100644 index 0000000000000000000000000000000000000000..a2bfd0cbd71336d1c7ffcb9646fab3e13fc6f3ff --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/4b20db2f875ddad665e5.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/69ab326570dcf8778e4c.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/69ab326570dcf8778e4c.json new file mode 100644 index 0000000000000000000000000000000000000000..918c5f7404699e10e6bbfc51f2910ad694bfa5e5 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/69ab326570dcf8778e4c.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/8a48ba4681cd05481cfe.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/8a48ba4681cd05481cfe.json new file mode 100644 index 0000000000000000000000000000000000000000..81b5a7342dc264847e5d358e4cfab6fccacd78e9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/8a48ba4681cd05481cfe.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 8192, + "sequence_parallel_enabled": true, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/f92daef82938443934d0.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/f92daef82938443934d0.json new file mode 100644 index 0000000000000000000000000000000000000000..4634fbb812192cc34b665f09e3ddb8786203dddc --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/llama/unsloth/Llama-3.2-1B-Instruct/f92daef82938443934d0.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/phi3/microsoft/Phi-3-mini-4k-instruct/45bac7b83a13be6ba9d0.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/phi3/microsoft/Phi-3-mini-4k-instruct/45bac7b83a13be6ba9d0.json new file mode 100644 index 0000000000000000000000000000000000000000..f11d6544130f6230104e11aa2aec54f20df00169 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/phi3/microsoft/Phi-3-mini-4k-instruct/45bac7b83a13be6ba9d0.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "microsoft/Phi-3-mini-4k-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": 4096, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct", + "checkpoint_revision": "f39ac1d28e925b323eae81227eaba4464caced4e", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 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": null, + "rope_theta": 10000.0, + "sliding_window": 2047, + "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/0.4.4.dev1/phi3/microsoft/Phi-3-mini-4k-instruct/bd06e66d087fee3632bb.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/phi3/microsoft/Phi-3-mini-4k-instruct/bd06e66d087fee3632bb.json new file mode 100644 index 0000000000000000000000000000000000000000..2cea56c62ce3eeddfa5eb7fd763af0aa1e2ccef1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/phi3/microsoft/Phi-3-mini-4k-instruct/bd06e66d087fee3632bb.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "microsoft/Phi-3-mini-4k-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": 4096, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct", + "checkpoint_revision": "f39ac1d28e925b323eae81227eaba4464caced4e", + "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": false, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 8192, + "sequence_parallel_enabled": true, + "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": null, + "rope_theta": 10000.0, + "sliding_window": 2047, + "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/0.4.4.dev1/phi3/microsoft/Phi-3.5-mini-instruct/639c2df611ecdbd507cd.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/phi3/microsoft/Phi-3.5-mini-instruct/639c2df611ecdbd507cd.json new file mode 100644 index 0000000000000000000000000000000000000000..101ea9b7a54d761ea05dcf08a0ff3842ca3f287d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/phi3/microsoft/Phi-3.5-mini-instruct/639c2df611ecdbd507cd.json @@ -0,0 +1,164 @@ +{ + "_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": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "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/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/2c2550e69bd7b8401151.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/2c2550e69bd7b8401151.json new file mode 100644 index 0000000000000000000000000000000000000000..93124ceb54f8a1b2f768cc4c2d3f85dedb32bec9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/2c2550e69bd7b8401151.json @@ -0,0 +1,83 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "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": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 8192, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/39d0494022f8af95d63a.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/39d0494022f8af95d63a.json new file mode 100644 index 0000000000000000000000000000000000000000..683eee2fefbc854f34fffa6ec6cf45ea4e45af19 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/39d0494022f8af95d63a.json @@ -0,0 +1,83 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3/Qwen/Qwen3-0.6B/a65675cac42f945a53ae.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3/Qwen/Qwen3-0.6B/a65675cac42f945a53ae.json new file mode 100644 index 0000000000000000000000000000000000000000..df72bc44cd857ef9de35af20307fcc10d32cd0b4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen3/Qwen/Qwen3-0.6B/a65675cac42f945a53ae.json @@ -0,0 +1,88 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-0.6B", + "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca", + "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": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 8192, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/3717bfc5b3b2064b6cab.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/3717bfc5b3b2064b6cab.json new file mode 100644 index 0000000000000000000000000000000000000000..1f34f63013dabacc686b611d73cd61593361a409 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/3717bfc5b3b2064b6cab.json @@ -0,0 +1,134 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/6460e8bdaaec6d3aaf4f.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/6460e8bdaaec6d3aaf4f.json new file mode 100644 index 0000000000000000000000000000000000000000..2956e511ac13e1c64bcbf95938b68c4c4bc5fb16 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/6460e8bdaaec6d3aaf4f.json @@ -0,0 +1,135 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/b3f860566b83df7cb655.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/b3f860566b83df7cb655.json new file mode 100644 index 0000000000000000000000000000000000000000..f1a6fdcabb79b8501799b6fced1479b070b3fdcd --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/smollm3/HuggingFaceTB/SmolLM3-3B/b3f860566b83df7cb655.json @@ -0,0 +1,135 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev1", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 8192, + "sequence_parallel_enabled": true, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9b76c8559ff823b3cfa98e5db0d486cd2c6d8b90 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/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", "-O1", "--lnc=1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--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_01328268a19023ed0f24+f8e6d902/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e1c7a90ca8e1b18d6f623143b55987c66f3a0976 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef50e479badb0312e208336533316393fc797857eb5a2cde744753c266d7f3f +size 97794 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e4bfe59d6155f39fb2dc7b02432b14d2efc62266 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671f2968ee09229cb96bb22be152df8bd197829d6ce7ad77ef854a3963b716b9 +size 410624 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+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_0efb0afa4ef56e94d498+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..64af5bea5c318d4e8d61ab32f5b2ebb8573ef3d2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aeec7d218e22beefd303645f302d7a805df96146ecddac686eb936f8d682209 +size 84114 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d388eded7527420d1e7b7407f06567aeec76ec79 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f7732c3ad2ac92d6eca8c6efd83baeefa27be9061021e79a069e2496d6faa00 +size 246784 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..854b659d69603fcbde58509631b3a7b3a07079b5 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0efb0afa4ef56e94d498+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9411f69d1d13a85dfcf64804e552e540bfc24470b7f2b52f419c5eceb8f6357 +size 254967 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+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_14cda09d048ccfb252f8+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a6b6a691c57cebfa27e38dcda056b83c29c21952 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:948a51e7715bd8232b0ce82f8cca432d73c2a709e6a794d3a228525868c057f7 +size 93425 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5a367cc0501399559e2e7a7119a185b4548b2737 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2c30438f983884de1b30e5866ed44b55b755f839caf513e2312cbdfefc8eda3 +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..5a8c8f6e4d486e56522c1592c3a2f19aa44d8039 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_14cda09d048ccfb252f8+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbbb4dba625a46bae0587ff94ea66196c0ebfd2bfebd5b2d8680fa00fcf7292a +size 288898 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+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_1934c2fc93e7793f0aef+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7bce5095c949934184123fb96719ea53a2057667 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6361b23631f22b3534873d4bc3fde1c4197b34dc2d5d84b8097108cc7faed45 +size 596952 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d9d3bb858681b0723bda25f49abcb33571303d5d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0be47707e53a60759826fc077df760c768f27f3699574a1ca42a2c1721ac66bc +size 1936384 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b83454042532437969142d6d7309a8a4feca0510 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e23e21a3d39349b0a3b066fd29eb841c6bb9dba1fde90c7a0792c5717638a18 +size 2092575 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1944f672afeaa6480c61+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1944f672afeaa6480c61+24129607/model.neff index e016686cfa3244509a5230bd513124a75b8d5b1b..5bc62ccff49928f839b0e38f0104812d45543b92 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_1944f672afeaa6480c61+24129607/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1944f672afeaa6480c61+24129607/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c63a961d38d6e2faccfb3057e2a3a8ac96875fbd1ade15ba62f09333cfa1e1f0 +oid sha256:bc4ee4b8b64d4dc6330fdd8fae2947adf4f88ba10b2505b8b51907e13863538d size 36148224 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+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_1f6141b704e8b040fc5f+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c38f5760fd95785d36d532be710c09a1c212dbf4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ca40769d5d3d00298600feafb4f2bdfe3f38f29001fa2e039b0abdca262b79f +size 707389 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e76c183a27efed4b81a06e3cd9fc1e0ac934dcad --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f4bd2263928878732290e6596fa1c0e4a7814eb0474a84d84f85f9b64adccd6 +size 8920064 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3b94af1579170023bf5dea677fb0ccb95e4c92b5 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1f6141b704e8b040fc5f+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8e3eedade64e6006b05c3cca3bd0dadb4d083a1537c460c92a2954778c957ca +size 9067080 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_210575e529dec63f9202+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_210575e529dec63f9202+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_210575e529dec63f9202+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_210575e529dec63f9202+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_210575e529dec63f9202+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_210575e529dec63f9202+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_210575e529dec63f9202+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..30155e30ce91d5a4058bc719a342828abd5dda97 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_210575e529dec63f9202+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bc87b5ffad1211f61cfe408bd0f36ef1b88887fb434341f067d7f562301bbc1 +size 474402 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_210575e529dec63f9202+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_210575e529dec63f9202+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..576ab3898d7c355d9d43b9862b25292904cfe5dc --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_210575e529dec63f9202+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cadedb7a2a926529dfddc0443cf969ffb2d353356781957c51094d99e2282717 +size 115057664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+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_245d388b7b8c64a4d846+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..877edca29ae13728c4b62afa159c12473183d794 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc5d22607282b38e6ccc318f3d4d6f232ae382dbbf78a4b7ff65a37c4cdfbad8 +size 82653 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2b7cd26b2e80d596ea1b2a6e20b8f7d168f57971 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb1c68e78267670445d5a05741b98754ca8194705a9ab1bdfb3ce7d44956568 +size 216064 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7d2ba5eec37314f84f55d7e9422159f3dcef4300 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_245d388b7b8c64a4d846+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780a4a6a0d57688dd4bc494548c72ecaebbfb862d6d3e880442cc279fd2d9437 +size 224275 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_250ecf58b3a2e7ac5757+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_250ecf58b3a2e7ac5757+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_250ecf58b3a2e7ac5757+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_250ecf58b3a2e7ac5757+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_250ecf58b3a2e7ac5757+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_250ecf58b3a2e7ac5757+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_250ecf58b3a2e7ac5757+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2454aac239b8ec369102b0184785d212d54d5a33 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_250ecf58b3a2e7ac5757+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c161937d0eeeb2eca0dfcca2535ee497d38d1e83b3dbc45f21ccf5a0100888 +size 1061093 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_250ecf58b3a2e7ac5757+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_250ecf58b3a2e7ac5757+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..20ddb57879805fbb4d393d858b69286efb35950a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_250ecf58b3a2e7ac5757+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af2c4a236a1f97d56e0840ca8099bf268c1fad8b15295cae8f906ae0c5534a0b +size 9473024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+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_2672b897bf6327bea9e4+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d396e291c54b3b1e1c83a9761d827ea5c2b5a5a3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b56b0d331077542e72e5da19741dfcd8d5d6bdd01d35c1cdbe74227327956a6 +size 82772 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..24f815ffa5bd57a7edac132c9d55d934ee370402 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1cd6ca36926fad065cd480b6e705f247170aeb533426465d808212c1b7a5123 +size 267264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+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_30826b478ad3db0c312e+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bc964e60783749ddc527a14f11209bdbc3a5c4c6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582186d6720ce0ec6cface8ce4f88aaf732f9fb6f153b9026e4086c88b7bf975 +size 726810 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..16c7676dd8b94c18157f0552d288ac62d8945361 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:703e9869407930e4c758082af24dc8f38370a34a61991c8115d0135a70e5a8be +size 71302144 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/model.hlo_module.pb index 9ecf904fd033d8f075d100d2710d98676145a3a5..ba0cf1085ee1ca1b690a28da4f506f7036b8cc87 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/model.hlo_module.pb +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a009da1b0f420f4556b03630a8156f63f7d7fd03c8a41d7a3beb0139fb04f6fe +oid sha256:4401203211e8d18c167262705e7928fcd4b6f8dabee4a08d484c652d07e0c036 size 711424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/model.neff index df1f4f79e07b5f151c41521f13bae26a401a1464..4f809cd67362761109ea5e7b0fd40f064284f87d 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:918360b6790df987dfff2b04cec833dc1e35cee9259df376f26df08929d882a3 +oid sha256:e5477d813971bbd860779e46013216672c82d9307c9018cdd6df9a2cbdc45dbf size 3503104 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/wrapped_neff.hlo index 59dae2b290cbd1edfcbd1991614bfab864b48df3..0703f5fb9fc7eedd8cb588bd5d8f693b8777e87c 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/wrapped_neff.hlo +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_313c4e4e44b74c64a01a+a02c3a36/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b7c96605380b1cc2d978f6a16091c34b9b58d461e1d65aeadf31c119b2d8fbe1 +oid sha256:f4231b25c02fede81b37a9b22d913b0989eaf5281d447b2a9f30304db4c3527d size 3640161 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+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_3a758a7122ca68a1243a+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..715276b152d1aeacefa3ce59da9fa1ce7dc8a9f0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6d63d7e965d9319351949e66cbad9a3c799e1687254fc9e9b2a96c87adb32fe +size 865291 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ff98c6bd8edac01cae66e383e13fe31008b6d413 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94b4f8ca1cd6dceeea9e1f3cab2cd6d38961323966034736ce0190d3011373fd +size 4967424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1844fb78a1acce2eac236320d48e2168e388de60 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3a758a7122ca68a1243a+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c379355b24f769c6ef1b9dae63ff12937987e7a12f79d81471854f83c88f565c +size 5133948 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+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_3c75648f1b6d85bd72d5+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..781ef29d24dabc23eb054215bc19b2abc3f419bb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f113c10c77741cc08a19adc7d5e09e035a03a03d751dbefede3d51d70aa3a37 +size 426769 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8b5e9b5929c041f51bc1955afc24d21acd9eecbb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6b941c15ed66c686b8acff2b452ead98bcf0a038a2569fb7a79463ea49703a +size 3073024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ddaba73d698a3c624e122b4d2fcbf3d56b483c5f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3251669900d2348ad53608811a4ffc8d5adb276028f5b97a24b9dcb52014473d +size 3147125 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_42601fbe748660a77be0+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_42601fbe748660a77be0+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_42601fbe748660a77be0+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_42601fbe748660a77be0+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_42601fbe748660a77be0+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_42601fbe748660a77be0+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_42601fbe748660a77be0+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8e197c567018eaadae5985e26111641ed208c2fb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_42601fbe748660a77be0+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d007bb7f19dc61262140698229d888d0b068426fac10d9b9b91caf164ce03f62 +size 923430 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_42601fbe748660a77be0+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_42601fbe748660a77be0+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..02757a845d768b8e2a635157bcfbb1e8fcbbe156 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_42601fbe748660a77be0+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4afe796b0d005955e0e3c76c735b50c83ce7b5c0ca9c0cd5b76b031131b4f6e4 +size 5213184 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4ac5ed244908e0b23eb7+677eeb9d/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4ac5ed244908e0b23eb7+677eeb9d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ae7e0c6790082c43cd145aae8cc7e3cc89e15ca8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4ac5ed244908e0b23eb7+677eeb9d/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/speculation_model/_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_4ac5ed244908e0b23eb7+677eeb9d/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4ac5ed244908e0b23eb7+677eeb9d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4ac5ed244908e0b23eb7+677eeb9d/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4ac5ed244908e0b23eb7+677eeb9d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b4c40605da7851ffe567c9778de9d2083d306e1a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4ac5ed244908e0b23eb7+677eeb9d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:185054b8ba80e7f52847989d5a58e3fb4aade61a671dfa510960053999998743 +size 423848 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4ac5ed244908e0b23eb7+677eeb9d/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4ac5ed244908e0b23eb7+677eeb9d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6c6159f8d47db8fd8279f29a598f88cf5f4cba96 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4ac5ed244908e0b23eb7+677eeb9d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9edfbb33bf7c99e688e8c548d7dd44eb866e3c89386ccf98942ae4694ebfeba +size 3687424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+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_4cfdf541f39ee43e568e+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..341db3e67e9480f895a26a33f89ddd4642b76f75 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cddac5f850e59aa9e0669069645a01a6e0d5fc99a91415f7a16e3ff7d7c8eb2 +size 62810 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..647026bc72edda9361f212de15d61ec4be885399 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a6f7e991f8a38d8d84488f3bd63c9b5dad3935d4ed0db84dcfa30dff077b607 +size 205824 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..8986fd5de7efe2e94989344d12d1a9389c78add8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4cfdf541f39ee43e568e+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1db5b69e808ea9d40f38f765ebf67c763f095bc2e898f718c6478f80aba9ceb +size 211973 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+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_4e5d28a9a05b8ba71697+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f82508137fbcfd816c5e06edf47dc7d93738a062 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d13268ddb80c8558a247eb10ceee35167e93494a986409ed2d3be1eaf821e8fe +size 1122989 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9dbf7041f3bbf94a1c7a5f740262a01c5e597e03 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715cb890b27c64d579949ee98a97f23fd738b1ce702f2ccbc14574ab89fbf2ed +size 4957184 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e1636b40b8c73b5ffc03d5f7e60c6af91e77b4da --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4e5d28a9a05b8ba71697+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4432d7a93e4a1e88d48dea0334f3c9a14a1e43c5b9b1f350c29e74aae468fa7a +size 5141125 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4ec35bb57fbe1fdb6c78+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4ec35bb57fbe1fdb6c78+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4ec35bb57fbe1fdb6c78+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_4ec35bb57fbe1fdb6c78+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4ec35bb57fbe1fdb6c78+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4ec35bb57fbe1fdb6c78+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4ec35bb57fbe1fdb6c78+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..895edb3462afd732c644c9f7bdcba520ae1d2f4f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4ec35bb57fbe1fdb6c78+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6541330eaced8ef5bd62804c6e06991d2bcb38f68c71b2cabb4ce571665de2 +size 1050679 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4ec35bb57fbe1fdb6c78+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4ec35bb57fbe1fdb6c78+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4706e6ef2fc9d02aea23b7d7dd1b7f62c0776276 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4ec35bb57fbe1fdb6c78+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d387ff6d3dd9954294cec3810fadabd0718735a038aaebd74ab358c209fd2b88 +size 5827584 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5299d075a10cd88b75ef+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_5299d075a10cd88b75ef+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5299d075a10cd88b75ef+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_5299d075a10cd88b75ef+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_5299d075a10cd88b75ef+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5299d075a10cd88b75ef+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_5299d075a10cd88b75ef+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..71c624de3916ff8c8efcc77600f636209108196a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5299d075a10cd88b75ef+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be3139b484b25558451394fd522d6f5a663b45ccfb34c8e5a6ca9c955c29668b +size 874394 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5299d075a10cd88b75ef+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5299d075a10cd88b75ef+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cf23898b6d7a12a911b158c6924800ee4dde544c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5299d075a10cd88b75ef+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c2ab8f50c06259ce78d0c8775a2076dbd169e99163ed1074f4fceb79a365612 +size 22283264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+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_5960bdedd7549bfacf7a+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..dbe1f9441e2a7b2c4185bbafced0748b740f4d63 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5231390fb7b7b3c9416cee6d063cf72f57c3e66de2333a27302fd7480aad917a +size 694128 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b4b9c29f0411998756002266e85b7d95ef151b1d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d609c20314399dc90d7d3efc2f573991a8799ceb9c8c13a0528387d15454663 +size 625664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+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_5a1775d2dd85719fa52a+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ca2139b0a1c89d82bfa0225cb7b5731633c2c9f3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e684a3c433b3d1931b42c868bc1f8e187d8d344041c428cfd571ae78019cda22 +size 872065 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..85e79360d6e09dcd11d7ee7195d717c34e7e6256 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:558d00184fa1bac07430de16a73ee90da6291d87bdca5c37a0861521f936e86f +size 6759424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ac67cf1b1f6b08f88b88277daf86dc0d968f2f51 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5a1775d2dd85719fa52a+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3f72238ea26ef23b1555bbfebd0581b0e7192da33c47dabc912a8987fe7a106 +size 6925948 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.neff index b66cfcffe3b75ea9d46540605871fa8850de3ae2..3efe21e0a6fd6572539bbfc93fe015dadd456b17 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:878d9f308e8c51934bc9bc94e82f04c2799e61f8f2d577c3ce6875a6b82e65b6 +oid sha256:aae99c7c352a3bf0003fc6a1d3cf17bbbd7360829224f73be9a92a36fca32245 size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/wrapped_neff.hlo index a0b3128f9e2bbe4e1b54500e734010686f962e76..04357ca8bf7906cf10221628f27f6fbbeb316006 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/wrapped_neff.hlo +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5ee5dade1050cf89f316+a02c3a36/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1e9dd03a5402edc46c71ece40b025941a2854628ba71c435f740acdda6f4a3d5 +oid sha256:02fc3c1e2ef02e67ce1ef2daf774a482f12c32bcea4cf8e8c91ce3505d1ee588 size 288898 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_60946426f567b03182de+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_60946426f567b03182de+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_60946426f567b03182de+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_60946426f567b03182de+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_60946426f567b03182de+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_60946426f567b03182de+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_60946426f567b03182de+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7769035dc0fddef4f2ac74beb3a76ff0a67c53bc --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_60946426f567b03182de+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:998739b81e8fb6df43db32922a94855911e8da031c05927c50b42ac5226a6418 +size 468052 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_60946426f567b03182de+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_60946426f567b03182de+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..286221ffdbeac81c0c304838c716be29a324c874 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_60946426f567b03182de+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07b59de7cf85b7e28890fbf02a8b4b9e711b951552a367cebed63ce4117e0c5 +size 114258944 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+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_69c3f39b7e46f645ac72+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e01f58df1f216742e4144ae15c123a4804bdcca5 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36cdda40d731bd735c5496051ba474810d60adacd1312f59657108a47198a310 +size 669150 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..44288a905d4ad1981a2abf7930e099bc94d13071 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a0bbcf3ed5faabe5a79a6539084bceb95745452c7ac028690d91b33dd02cf45 +size 8889344 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..cf4495e1ad33c754706f6c6cf2b05c14835e656d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_69c3f39b7e46f645ac72+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2e402cbe320b6933c44229259b901a08ee66373c1e0b684616572060bda776d +size 9036245 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+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_740c88e5b7c7bd2f9bae+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..781ef29d24dabc23eb054215bc19b2abc3f419bb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f113c10c77741cc08a19adc7d5e09e035a03a03d751dbefede3d51d70aa3a37 +size 426769 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1d19ec58ea30fbc60460e92a65f667d9ff589ff4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f7a47d761c50e5ce0c9150e15d0e9f32726afb1e95a6072553758b37a853663 +size 3073024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2ec9b817684a199180fefb951640f29396b46be0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_740c88e5b7c7bd2f9bae+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c366c2aa9312137e4985670cf006f130a78f6f383ce45c8c327a270a772b4bf8 +size 3147125 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_78a467fd5a1d9f7adeef+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_78a467fd5a1d9f7adeef+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_78a467fd5a1d9f7adeef+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_78a467fd5a1d9f7adeef+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_78a467fd5a1d9f7adeef+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_78a467fd5a1d9f7adeef+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_78a467fd5a1d9f7adeef+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b5354b7b5a65a43ef1260aa0e8de13980762d080 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_78a467fd5a1d9f7adeef+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:649ff83e0cbee13abda84e02c1a114e8b60d780456161e42f68c99c57744691c +size 739558 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_78a467fd5a1d9f7adeef+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_78a467fd5a1d9f7adeef+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7ecd1ce442179565edc8bb4d1660d21aff8162f3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_78a467fd5a1d9f7adeef+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40dfa607b020ef9e891d5a4dca71cd75f67a5ecc7a86e72b2146a17479837b20 +size 26133504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+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_80b2eb092f15a0509d79+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d5227d87a579dd8442f35f9629dd489d87436cfb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace0b72947ee8c924377c70ca80a5c844a07f3bab35b5c6545c272003e4c53c7 +size 434264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4895cf1d278a5de689d41b940ba6ca64882b41da --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:665c7cbf4b3bf25916f7edb3f06afcb05ee1efe9c23a5b5129f72f60f9c5b567 +size 2366464 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..eec878a41be9cfee10bb5bcc35c91c938577810a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_80b2eb092f15a0509d79+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:583f060aab33c53b8f28d94330476f714d9545a26843f00bb7a535f93761f3df +size 2440551 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5a228a7a4cc7c7df9e8b4887d22dcd862c2f60f3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/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", "-O1", "--lnc=1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--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_864a283be77e0814947c+bafdbdde/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e3e15a31cad10ce1cb55cdd26b518a6a5798991d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1c364e560eed61f02284b32afbec9ee92735a7fc75f5da0fdebf4e6f62981de +size 91833 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7684292c7afed82987849f4c30f477053b699538 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac0a5f8c623e69c32df0f65a514ae1f29f63c1e4629f5fd16842c7f8630970cf +size 369664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..21224147e96310b42c09e7fa413d89c7544b29e8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_864a283be77e0814947c+bafdbdde/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad55b6aa538df835c51877539b04aa7ec79969d2cfbbc39edc3ecc7feb5ee267 +size 379225 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+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_8b2505504a54575836b0+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bb0e723ce8d76544eb2e2c0282427d561fb45313 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04fa3d25bccfae87c411912a1318f7b09223d1a267d2024c09aef48a926aec16 +size 85024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..980554b830b79d6043b0e66f12cb5da3231e5312 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1060286be5259ba3f3a1e6e70edf309b3a5f9c2b9edfa4b7f049ca9554af484f +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0956f642a1c56013de60d20aa462a2a9f37e3282 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8b2505504a54575836b0+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:859951631f7283c904602b69178d2c25c5a5ea29f500211582d11fd68fcb2cb7 +size 285717 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8c6b204d1bccf64885d0+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_8c6b204d1bccf64885d0+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8c6b204d1bccf64885d0+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_8c6b204d1bccf64885d0+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_8c6b204d1bccf64885d0+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8c6b204d1bccf64885d0+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_8c6b204d1bccf64885d0+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6bb68d47b8989e4c891debacb03c7e9c3cc95f3a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8c6b204d1bccf64885d0+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e9dfcec844d75789db374ec7fac00a85070e6911e7592ba7d9ba54de1aceedb +size 64986 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8c6b204d1bccf64885d0+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8c6b204d1bccf64885d0+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7fe5adc6cde4b6b35fe6b72f4d1d6e5da3bb1439 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8c6b204d1bccf64885d0+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d32a151ebb57d6b9a540897a1f7998fe84163c9ac166cec7236a96a70e071cfc +size 226304 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8e336cee3fb428dcae05+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_8e336cee3fb428dcae05+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8e336cee3fb428dcae05+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_8e336cee3fb428dcae05+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_8e336cee3fb428dcae05+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8e336cee3fb428dcae05+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_8e336cee3fb428dcae05+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7f4922059edd9a1c076457f9fa63e5f7dbdd582d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8e336cee3fb428dcae05+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28fc616c12ece846ce812a658e80999ab7dd59879008c33451a9ec4687191e9b +size 1070310 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8e336cee3fb428dcae05+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8e336cee3fb428dcae05+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fb4a566c61a057b41e24875e880a2b2b33aeea1d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8e336cee3fb428dcae05+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d640d44f59330bfabb52df0ae6f957016736c60e49f4362b08eb486ac98fccdf +size 15852544 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+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_906d1a9a7651a30426b8+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e558c80c6fa380fa203e9cdbdcafa525635b7089 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ebbfbf714e8c865c751e2a1ce06f8636b523aab56e0f5a4a1fbe1b1b6e90384 +size 395607 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3347d18eac302576c6a3413459fca140c1a9764c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b59f454cfb422e5922ade12661f3b68cadcf0f2635ca48f99e80a6f9f5cd6335 +size 2171904 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e78348cdff9b220ee272be24c4b10b684525ee1d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_906d1a9a7651a30426b8+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c761617652abb8cda2c1ea7f9dddb65e7cd62ca1cfc2afadd366a6464fd65ab1 +size 2245876 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+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_9bc06d024b9ce47e5f56+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2dfe28bd941cdcb1aa0cd8e62b7727c1b2ce8f58 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa7ee587c6dd7eb719c810d0b3390042fe6e1ba6c8c33b36d4f10a723820f13 +size 509380 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9120cd17e6add4b59847b4c481e64723b78e789d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fcc51a8a2631ef64a3fc55d99615f28707984ec5d38a3df36fa25006a98fe9a +size 41585664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+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_9c53a5ac284b649e893b+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..25602daa193be1a6350ec9ea8a1a27658ff13aeb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f0ed0940bd1b89549985db77fb8cc87a96e9dc18df1e244c439dd83f51c764 +size 1080658 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..97ce758dae65295731f1803d803ded3f316ad263 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4abcbcd9ed97fc54df10216f947fd987bb4a49d0d9dd32dcb0020f5700e0505a +size 6933504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..da9e6f6ac2c6cbf41e43d04854bdf148e6d137e4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9c53a5ac284b649e893b+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c552fcec7dd7ab6d4bc6aa95ba48435854f7a8c7ced6894a50ab596ef3526e5 +size 7117697 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9b76c8559ff823b3cfa98e5db0d486cd2c6d8b90 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/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", "-O1", "--lnc=1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--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_9d52760610a001af812a+f8e6d902/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..41b34a9f77fe802ab1aff5378e888ec8b792fe46 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75aa20ad640c40319a599827de7275b4989637937e69b4c859e53b00a8bc9b3f +size 84807 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0ce3bfe677e37bbe8937405949e98969e95b3235 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b32b26173495629dd59108bcb4f98b21a4b73aff9e6736bdb979ddb2c118126 +size 646144 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+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_a1dbfcc237b9198dc735+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e9414baf188efa02ca1bb1b550950ffd3d412a2f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc920b7aed93d7bd37857bdfacd60e8c3d8549c853d2c02a6d7f995b094a071e +size 982549 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4ac20bdd167c7fa0f9181ec3849350571c2675bd --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_a1dbfcc237b9198dc735+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c704e928a3e4e1a4381be150a26f7f138a2877c06937e93facb82098e2ef081b +size 22774784 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad0618d39f30ab05071a+677eeb9d/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ad0618d39f30ab05071a+677eeb9d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ae7e0c6790082c43cd145aae8cc7e3cc89e15ca8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad0618d39f30ab05071a+677eeb9d/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/speculation_model/_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_ad0618d39f30ab05071a+677eeb9d/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ad0618d39f30ab05071a+677eeb9d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad0618d39f30ab05071a+677eeb9d/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ad0618d39f30ab05071a+677eeb9d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..58b844b6061c1f9a1ab0b3c6c889c594ba91dd4b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad0618d39f30ab05071a+677eeb9d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca80d55257caff0cc88a182611da0df7d95d1903c9dfe7bf87cf178ffb39718d +size 423848 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad0618d39f30ab05071a+677eeb9d/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ad0618d39f30ab05071a+677eeb9d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7fea78ffe864943869eb85b5f8b1d3311eeebdbc --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad0618d39f30ab05071a+677eeb9d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97d16e7f4e5daba93c2dc13f4131fbf3740f73af9c4660db3daeb638325320ea +size 3687424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+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_ad7c8ac474ec4bdeae52+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..748c409b8729fc9463051767dad159bc8d1c7cdb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb4342d18a3192874a17bcc4ddeadc592624a4db04b0444c931b0f2dc4e6d9b +size 761066 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.log b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.log new file mode 100644 index 0000000000000000000000000000000000000000..ca4a6cbfb4540f166b46b77700bb8952d3180c7f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.log @@ -0,0 +1 @@ +Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/context_encoding/_tp0_bk0/model.MODULE_ad7c8ac474ec4bdeae52+24129607.hlo_module.pb', '--output', '/tmp/nxd_model/context_encoding/_tp0_bk0/model.MODULE_ad7c8ac474ec4bdeae52+24129607.neff', '--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', '--verbose=35']: \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+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_b6a329fd6d4912085786+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8b5d8df376fcdc652f40c2fb7fc0398eff9f6c0c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70d262e66d2fc1d09841f5c0cf8aac87d350ff22163dee1fcb520515189c79d6 +size 643371 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cdf8d8121d6e2bbf3fa4dd5ee8e87145836b4dcd --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b2e76b644a973caa852fbe966d2f4832aeb83f4ee6b130c4112910437adab6 +size 1721344 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9254d97b9918918dee117496a1ec76b0cb2020cd --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4928e4a9ad2a4572b8955baeacfd08de80d2a6433d1f56bff33e2d1e70be6ae8 +size 1877650 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+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_b860b7ba935f627d151d+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8050ecdd638a2b3d1ad7919d0a5441fc65bc58d0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb9311e1af146eb0084c47d114f4ef6c659ddd5cbc2b4e5e937b3fb9bedba03b +size 395607 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..968d2c0f012ba974ba1a469b977cab200d07399f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:330d7844d49296f81e87b4593b775eaeffa3b190e0645a232dc2f7f941169e7d +size 2171904 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6d615bc18d4011d35db95deb23d091fc18d864f2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b860b7ba935f627d151d+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8019d3275179c50d3e1242910d74ec7d7bfc71fe93d5506124a594e59239a461 +size 2245876 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/model.hlo_module.pb index 9ecf904fd033d8f075d100d2710d98676145a3a5..ba0cf1085ee1ca1b690a28da4f506f7036b8cc87 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/model.hlo_module.pb +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a009da1b0f420f4556b03630a8156f63f7d7fd03c8a41d7a3beb0139fb04f6fe +oid sha256:4401203211e8d18c167262705e7928fcd4b6f8dabee4a08d484c652d07e0c036 size 711424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/model.neff index c5bc1d8997e9a474f8bcdb10c84fe940cb64089e..d1cb45aa3493bbbfe211ecc0fe6590e266f38974 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:51733771a690420ffa86450e03c4581d1ae1cbd5c1ad207bd5b6521e3c6fa30c +oid sha256:c5b538fec49c566c4dba67b76246c085ecd3db63a40a9cb58489de851efe6ef1 size 3503104 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/wrapped_neff.hlo index dc6874fc24775503acb39ca3e41dfd906f947989..7aab40a553a07a69e6e3c5d22f0c9b8ac54aa6ea 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/wrapped_neff.hlo +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b9b261eb8d39678d6323+a02c3a36/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a945dbca161bd9f96c79046d5127698c1f0f5aca4abaecd22f1388b6274a01f2 +oid sha256:f0249c1b417e7c92056376bf762fb3446f623be7b039715f8df3a40028383ab6 size 3640161 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bee928e1ff2bd1f5e3e6+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_bee928e1ff2bd1f5e3e6+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bee928e1ff2bd1f5e3e6+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_bee928e1ff2bd1f5e3e6+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_bee928e1ff2bd1f5e3e6+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bee928e1ff2bd1f5e3e6+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_bee928e1ff2bd1f5e3e6+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..74a986a9d581a594fd63a6336fb19d916c9f9f08 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bee928e1ff2bd1f5e3e6+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df767bea5fc286a6d1522fe3c3831bdb7b5535e84ff7d0b2f36950c7d9b30b97 +size 468052 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bee928e1ff2bd1f5e3e6+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_bee928e1ff2bd1f5e3e6+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..dd6752928bab9d2170e363ea2e527b2344b8258f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bee928e1ff2bd1f5e3e6+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc1585004696ac747467ec21f6a48b092553edf3e866e4b4b79847d5f0d868cd +size 114258944 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bf62cea1b964ce1cb653+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_bf62cea1b964ce1cb653+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bf62cea1b964ce1cb653+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_bf62cea1b964ce1cb653+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_bf62cea1b964ce1cb653+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bf62cea1b964ce1cb653+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_bf62cea1b964ce1cb653+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8cdc1fb8a6b7b6584fca2277921820cf148f3c3c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bf62cea1b964ce1cb653+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da0b586fe3ff38769f53ace21af6272328153e4ad731ae56d3a9ad4c8ef9dc54 +size 1009826 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bf62cea1b964ce1cb653+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_bf62cea1b964ce1cb653+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..87daec9748695110655f1db9c0b90dd9803719c3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bf62cea1b964ce1cb653+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e97450a061d50728b1844df20df33e590bd93894b14ae6de6b005dbecbdd96da +size 22887424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+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_c26856b929d58ebddc23+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..32942c066618e9d65cb12b4e62d9a5097ba42e3a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb45ccdda05a2a2ee1cf89ec265cdb0766071dc0512a114d5a7a007c1d523b9a +size 83504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0bc673303d2f6a85cb41332e26052b5a2a238a8e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36c9055608092f4be44de678aa77e873c858f75429d901c3851babbebe581dc4 +size 328704 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+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_c4913590384814c92cb6+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e624d0856e1911e8f657fa16776c6e8f10644f9d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab85d7c603bb13b73b521000a86de4160af14d09b8b3dfd1b565eab024b2d717 +size 678755 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..603e263e7639033cdd42450033aa62f7dc5ec10a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83b4bf1b2d082b28f1532f71605140f064d6721d2350ac17f4a374fc75113a5a +size 533504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..52eb079cc3702c1b058b37a09d8bf93b3c461418 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c4913590384814c92cb6+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:132cba03b88b2eaee37dea1292777e2b0f326225db8b726f7525666ba3c05d80 +size 553005 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+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_c9349ccef5ee7c09a049+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ec77da0f1432431604acee681bf7424a82cbc394 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3465d7b49126d913bb0de77fa5424be02dc65564b63849b4f57d2625ecc23da7 +size 840774 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d880c2c2c47f975012d647940a2aa5210d4a27e2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5df6a96e26928163be3d4c33e34082f7dd8b9b0829f283fcefb587f9005643d +size 5243904 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..786f65dbfcc022ce4b5081fbe31f6d59cca99528 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c9349ccef5ee7c09a049+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb67b693538da668cd38462b3729d7b1eaf8609de1a21e76f5c5ef60cc7fba57 +size 5410313 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+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_cb05698d60b06f387ed6+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d40b921f650e4ca344d330f95f6380893d402d2c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d9150bc5aa42ad4c1035fe623592bcc639869b51cf86746a0c48faaebc5f464 +size 388429 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0083265b54691c23bcfd8771bf0760520b39eea7 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c01aad13b2242ae951c9a436a7adf9e84cbe635d3081d25263bd805bb98d0dd +size 1936384 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..480761eb1bec78bdce6e66f1cea058bbc13f4cee --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cb05698d60b06f387ed6+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34e6f48c26ff800cd9495c35c884ce722d4d1b894400909b93a112cf72719d8e +size 2029297 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+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_cb6b880fc977b7ae4bda+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..28ee1398fee500d4fd4ce4bd55db6a4f4eb78dba --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d12d23545ccb2c03c3978d33636c9589b7b6da434697f7b5507f28fd0062075 +size 81516 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0ebe76da33da7f535289f868ecf2170765c2801f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bede074a656737d1b8bb3a4c99933c04b3172880e2528fa29965fad3b087226 +size 267264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+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_cf7ffe281543e5e4c3d3+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ecc3ca05e8ae0662f2cff8f22dbb020e8b85acef --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66355f45b5a564dad737213b1575c3673e50af834b71a571c765842a1e0bf372 +size 700208 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..36d25e435ebc793ea302ba99bc247708d4f6a1c0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b79ab853570488a3007f64292decab6f885c357c3e8e2e94f7c6b5fdaf6d1b41 +size 12411904 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c24fe002cc88ceee39f3e94d57c2cebdee6c397b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cf7ffe281543e5e4c3d3+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36206b877cf4645fb5310d17a09b9cc0188b428861c3cac9f14cfeaeb335de96 +size 12558920 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+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_d107c2d38c7104284da7+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ca2139b0a1c89d82bfa0225cb7b5731633c2c9f3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e684a3c433b3d1931b42c868bc1f8e187d8d344041c428cfd571ae78019cda22 +size 872065 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0ac067481f7755d6504b493d60162972a5344f85 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8306479522f060c8f82b9ff6097f22c3870ccc2557c633cebcbdec3c2bbd6428 +size 6759424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1f2c904a45097c673559d03c293d70b43d325eb4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d107c2d38c7104284da7+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872cb80c488fca803ee6e89f584bb835d5077d61bfc8213b7715593f5766c987 +size 6925948 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+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_d1e075f89e8272c07272+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f21398bdf65223ea40611935dc1618612da51eaf --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:261eff5997fc5502abd2934c6d03a16f16a9fe4825e3cdd1d70b7a71dcedc957 +size 843918 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2913e048c57ac14781b9c601b5e3eaa65731419a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d1e075f89e8272c07272+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b807a77d244dd1bcd11ba903a78da23985dee79a1183ebf806ebb29b397a8f7 +size 96881664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+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_d407bccc563987df7700+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..17a66b0b7bd105a546cff5df91c30f1889692097 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c477778d59a58c309e07bb9b0ac2fb5f8f2eb6f611f1741ed86f25b3b1059ea +size 879627 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0b1a15b7235f580cf024994357ab8205e4eac39c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bcf6723db5cda134534547940656bb9ea80513c22ddef46b4a61c14feebb0bc +size 5397504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4f77dc27128cae37f49c7f73ff464ac763e36afd --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d407bccc563987df7700+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bcdae5c472f3bfe86d84eff76dce64e18bd5358afacf9a9688ea3e53b0d1506 +size 5564028 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+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_d9f17410cfb469b24055+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6df160e2ac4a8f21ac89411704700a1bb5a6530a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f645679ef1301d5034c77ab45d1e900e4bb2587bf70f521d5621b18142d447 +size 758053 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6b197ccec72be36b49753d1558aa51983b101d02 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c56b7d13b825ea938e3be42b4a7e04856180bfda6036f5da463bd90eca71edc3 +size 2417664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ce1c3b36af1b57f78bb5c5ca3c3f6c3990c92571 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d9f17410cfb469b24055+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:456a7167b59dc42a1c862bacb8406d01a6490f64f9f996ba9e75b08bce5e0ec0 +size 2554832 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5a228a7a4cc7c7df9e8b4887d22dcd862c2f60f3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/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", "-O1", "--lnc=1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--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_e0ccc071060e441622c2+bafdbdde/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f747ccdad84657b0dc17e367c0ea5f3f76f7a00f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a329d31fe8f44a19d767432740ad0fd5b4a5b395f46b99f9b906fa11236932d +size 72553 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..10ac39499db5b11276567f3694bf56c952163ffb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4ff84d0ebb6a91826b2fe2bc821051669af29385e9536a2ca77f1dadb3b332e +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0943b1436c12eae63036aa23109c3c2a742517a8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e0ccc071060e441622c2+bafdbdde/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af26fdd7236eae7fb1f1b53da776d0b43f8c1f35f80d9d81b58bedbc31ccd442 +size 289434 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+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_e899b698a237c528bb16+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cf7107baae9339edc2d8373b74081ff19581db39 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1250088885cd64fc4a0be3a10d2f8222c991a426632b4d7a86c18a890d6232ff +size 90382 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..868cb15bc41071fe8d10f01f207a994c89b1e9f5 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de7fc6b6461262a518d9b4e6d67c1c6fe943b04806e1f726deaf29d599cb1911 +size 359424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+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_ee8ab158a9c272b70f44+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e273fd0722ce8ffe0e967376ff2afbdcca6fda04 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2913e1dfc67fb201967593ca210cad72244a745757d1e7bc3aea7db3ea05712a +size 388429 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7eff559275e2672962b48b51eedb6a04889fab7b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d7716beb9c13eb7c1c78f894b95a728e7e5328786bca494183ffe9bac29087 +size 1936384 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e384e93b0290a003cdc2c110e1a74f327ea3126d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ee8ab158a9c272b70f44+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e52f89184f2cfaf87162c3bfcb7b0f554b0030ad0c173ef1bb100950728fdb54 +size 2029297 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ef557fc37471d6bfd06d+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ef557fc37471d6bfd06d+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ef557fc37471d6bfd06d+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_ef557fc37471d6bfd06d+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ef557fc37471d6bfd06d+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ef557fc37471d6bfd06d+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ef557fc37471d6bfd06d+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..42e18b4abb38b0eebea9a72014461d0fff3dbc4b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ef557fc37471d6bfd06d+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95391917db41aaa7639d8b388a4e9bf56dde98daa09fffdbcf44338133284ae1 +size 854266 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ef557fc37471d6bfd06d+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ef557fc37471d6bfd06d+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c871bfe171c385c620c1ed716812b292540cfcd4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ef557fc37471d6bfd06d+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2fc0e438a8f9aef8bd6da60776e61853b6f005dd2ead506ee2d3a418747fde +size 12237824 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+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_f2ba194e95963ca457c2+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ecc3ca05e8ae0662f2cff8f22dbb020e8b85acef --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66355f45b5a564dad737213b1575c3673e50af834b71a571c765842a1e0bf372 +size 700208 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3137c2911607162b3709df115c937401fdaeaaaa --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dab91a2defcdf6da09de04cd1e7c2f29a26ff093603f3c8557bc90132d43616 +size 12411904 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6969511446904860e7649c42d766c4705a0c339c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f2ba194e95963ca457c2+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb3127cde3d04cf5d9bc208ad0a3cc1b9e98493bbbdfd8ff1808bcd8a72e6858 +size 12558920 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f9c594cf85ceddc7f3ad+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_f9c594cf85ceddc7f3ad+24129607/model.neff index 33ee38a350202f31f0b5535fc21e601ec5f473a3..52f587144dfb66fa07965a6d729ea0879b61bdb1 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_f9c594cf85ceddc7f3ad+24129607/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f9c594cf85ceddc7f3ad+24129607/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0b9c7f92b8007c09d6a0bd8452c79678b468381295ce3645189e585f5cc837bd +oid sha256:2fe0b39a7aa653b0e1f2e2bc4f7788534bc878abe481c0a3831bb977a40d5e86 size 36148224 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+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_fd476e174a39b55eeb18+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2b843c21a9eca44a50823d9d159c8f60a770c4e3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ca0a9c8719d71e823180edfc6eba4a8842e74134383b6713cb51cd6134d5fb7 +size 596952 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8630c7ae02aa23e1bf3476988b51be691e35a36d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e72ea34ac3d917e71710c6a1013878ffd1eebe91a544f4cb6e39b7bdaf7d800b +size 1936384 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d837a84f7787924cf2a7a6d742cee4e356d1a7f1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fd476e174a39b55eeb18+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9831cd4d45d394bbf42f0c26cf3bea9f5e3d97db6212e0980cc3f897547307e7 +size 2092575 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+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_fff86602d73f8f8ecb89+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e6ec306f7ab061cf698adf9c17e1b3f915e32024 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68dfa030c87eb9209a420800c3ae0d115976dedf19d514f4b2795d1749deb5e8 +size 1080658 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5e30301b7c0181038e61b35c867a272bbf433a1a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d42b800473117cac0c8152f05460f900a8b837eb5d9e5bd26550030e81882b +size 6933504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6d41cfa8c3d2441271a2219247f871905841cf6f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fff86602d73f8f8ecb89+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21b8f73f9e028654f54c1d2ec82f373dc3fd6ca7a8ac56b5b5b8860de04ededd +size 7117697