diff --git a/.gitattributes b/.gitattributes index 6a088ce9e41a26a40cf508efc8c130a55d59ec98..bce021e34a8c6454becc7f1bb1991dec846e7b8a 100644 --- a/.gitattributes +++ b/.gitattributes @@ -11995,3 +11995,103 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_569911dfdf036e1e8532+877608f3/model.neff neuronxcc-2.21.18209.0+043b1bf7/MODULE_04cf2c8f87dbd5bf288f+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.18209.0+043b1bf7/MODULE_04cf2c8f87dbd5bf288f+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.18209.0+043b1bf7/MODULE_c6fe8e7f1b767a000573+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_28d01c41effbb13bf546+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_3bcaf76326aa82946559+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_450f587e94e46ad910ea+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_58bfab3ea35f7cda10d3+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_5db2cb5268c1af1c38fd+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_6141e1bb55c6f48144db+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_6748a4382c808a15332c+a92b0e80/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_728c3b7e3ec5305504a4+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_75c9a7a4c810a6349cce+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ecf3321018998eea75a+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_920c248c8c17f5746461+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_999e22b80b6484bfea64+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa028c0ea0061525edc0+be13b572/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_dcfbae5d14fe3d7bc51b+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_f52103be87a16d51075f+564b7b5b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/granite/ibm-granite/granite-3.1-2b-instruct/64a790f83e0ac2530718.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/granite/ibm-granite/granite-3.1-2b-instruct/64a790f83e0ac2530718.json new file mode 100644 index 0000000000000000000000000000000000000000..e531d7a938b5920bb1a4a6cc0ab5987cc6816180 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/granite/ibm-granite/granite-3.1-2b-instruct/64a790f83e0ac2530718.json @@ -0,0 +1,58 @@ +{ + "_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, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/95b73139a686e5a68909.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/95b73139a686e5a68909.json new file mode 100644 index 0000000000000000000000000000000000000000..1f9b1f1108ce9ca8aee7acb39695f4f1c3a3dced --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/95b73139a686e5a68909.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, + "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, + "enable_bucketing": false, + "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": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float16", + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/bc967f1931527e5da661.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/bc967f1931527e5da661.json new file mode 100644 index 0000000000000000000000000000000000000000..78cfd7169d3ec32f0e4d698e240ab3208e62c88d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/bc967f1931527e5da661.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, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/f8334621341fc36ddda8.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/f8334621341fc36ddda8.json new file mode 100644 index 0000000000000000000000000000000000000000..e3c19dd7fc84c80f166932c9d5857662336a3c15 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/unsloth/Llama-3.2-1B-Instruct/f8334621341fc36ddda8.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, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/phi3/microsoft/Phi-3-mini-4k-instruct/11bfc3849cbefc5e51b1.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/phi3/microsoft/Phi-3-mini-4k-instruct/11bfc3849cbefc5e51b1.json new file mode 100644 index 0000000000000000000000000000000000000000..8a563cb512a5e2f3622feb2fc1aa00929cbe7c9c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/phi3/microsoft/Phi-3-mini-4k-instruct/11bfc3849cbefc5e51b1.json @@ -0,0 +1,62 @@ +{ + "_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" + }, + "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": "0a67737cc96d2554230f90338b163bc6380a2a85", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen2/Qwen/Qwen2.5-0.5B/2b36e02ba26d92abb848.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen2/Qwen/Qwen2.5-0.5B/2b36e02ba26d92abb848.json new file mode 100644 index 0000000000000000000000000000000000000000..d361c44511f62dbbd10f4115a5f82945378441b4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen2/Qwen/Qwen2.5-0.5B/2b36e02ba26d92abb848.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen2/Qwen/Qwen2.5-0.5B/ea3581a8419394c4603f.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen2/Qwen/Qwen2.5-0.5B/ea3581a8419394c4603f.json new file mode 100644 index 0000000000000000000000000000000000000000..f531ac5021960a771902ba1074bd17bcef7f2040 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen2/Qwen/Qwen2.5-0.5B/ea3581a8419394c4603f.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen3/Qwen/Qwen3-0.6B/c783db5745a82fc95b29.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen3/Qwen/Qwen3-0.6B/c783db5745a82fc95b29.json new file mode 100644 index 0000000000000000000000000000000000000000..4237c310ef05fa82425e51c8824de826821d2859 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen3/Qwen/Qwen3-0.6B/c783db5745a82fc95b29.json @@ -0,0 +1,87 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "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": 4, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-0.6B", + "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/1913e6a7e80248fe5394.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/1913e6a7e80248fe5394.json new file mode 100644 index 0000000000000000000000000000000000000000..4b1c1295a0495b29773df1c1108b8f1e1b3e7415 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/1913e6a7e80248fe5394.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, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/180ffc12360632ca0552.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/180ffc12360632ca0552.json new file mode 100644 index 0000000000000000000000000000000000000000..03037bf66866b329d1f65e4883e992de02aeec35 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/180ffc12360632ca0552.json @@ -0,0 +1,58 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4ff566ae03f09752651b.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4ff566ae03f09752651b.json new file mode 100644 index 0000000000000000000000000000000000000000..742d1176330d794e400fc5e65ff1b01d04100a4d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4ff566ae03f09752651b.json @@ -0,0 +1,58 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/ibm-granite/granite-3.1-2b-instruct/85c4a3dff9218e4c84d1.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/ibm-granite/granite-3.1-2b-instruct/85c4a3dff9218e4c84d1.json new file mode 100644 index 0000000000000000000000000000000000000000..09c0ee244412888bedf1bd690a52c871371aee16 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/granite/ibm-granite/granite-3.1-2b-instruct/85c4a3dff9218e4c84d1.json @@ -0,0 +1,58 @@ +{ + "_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, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/4df385f6aeaa42fb9756.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/4df385f6aeaa42fb9756.json new file mode 100644 index 0000000000000000000000000000000000000000..0625873f707a25e734e9dbfdb7f1e15e655024d9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/4df385f6aeaa42fb9756.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/88aa32108ed4101d3866.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/88aa32108ed4101d3866.json new file mode 100644 index 0000000000000000000000000000000000000000..3fc4f63bfcdab569587ab967a1e7a991979e3a07 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/88aa32108ed4101d3866.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/a0f5e6280aa0f309b18e.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/a0f5e6280aa0f309b18e.json new file mode 100644 index 0000000000000000000000000000000000000000..51b7a0d7394469a91ef7886decf3c0d208aa3927 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/a0f5e6280aa0f309b18e.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 512, + "max_topk": 256, + "n_active_tokens": 512, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 512, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/a17c0997f47472bd5dfe.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/a17c0997f47472bd5dfe.json new file mode 100644 index 0000000000000000000000000000000000000000..d2ed2bcb30ac778e034eb9f3d1b67252c5cee73b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/a17c0997f47472bd5dfe.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 512, + "max_topk": 256, + "n_active_tokens": 512, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 512, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/b7af84a78116c62fd7df.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/b7af84a78116c62fd7df.json new file mode 100644 index 0000000000000000000000000000000000000000..58974e0b3b07edb7e483023ad6da443eae87a4e3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/b7af84a78116c62fd7df.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 128, + "max_topk": 256, + "n_active_tokens": 128, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 128, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/c2c73293c7780c0f9ef5.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/c2c73293c7780c0f9ef5.json new file mode 100644 index 0000000000000000000000000000000000000000..2646f86226b0882e7d7cd12250dd2fdc16b8838d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/llamafactory/tiny-random-Llama-3/c2c73293c7780c0f9ef5.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 128, + "max_topk": 256, + "n_active_tokens": 128, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 128, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/25991d38bce4cea01a35.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/25991d38bce4cea01a35.json new file mode 100644 index 0000000000000000000000000000000000000000..425c6e13a256b8fb5ece23cbbc7bc9db94bb2deb --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/25991d38bce4cea01a35.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, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 5, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/4893342f82847a2534a2.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/4893342f82847a2534a2.json new file mode 100644 index 0000000000000000000000000000000000000000..e7bb8a192df1bda533f3c36e645dc54dc9b93e7d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/4893342f82847a2534a2.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, + "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, + "enable_bucketing": 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": "2.21.18209.0+043b1bf7", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 5, + "start_rank_id": 0, + "target": "trn2", + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/ad52ab59b4f63a84b952.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/ad52ab59b4f63a84b952.json new file mode 100644 index 0000000000000000000000000000000000000000..76d0db594b9d1ee60923308164d45d17152a9223 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/ad52ab59b4f63a84b952.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, + "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, + "enable_bucketing": 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": "2.21.18209.0+043b1bf7", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/e3cc0e33d28db8b7f878.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/e3cc0e33d28db8b7f878.json new file mode 100644 index 0000000000000000000000000000000000000000..46c34295f66c09b4b5a3981e8c81fc2649d4ad13 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/e3cc0e33d28db8b7f878.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, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/fd29e4123845a682a97a.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/fd29e4123845a682a97a.json new file mode 100644 index 0000000000000000000000000000000000000000..904a0c0570639745665c7497f7d2391977a78d07 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama/unsloth/Llama-3.2-1B-Instruct/fd29e4123845a682a97a.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, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama4_text/tiny-random/llama-4/42056289c8690a12c97c.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama4_text/tiny-random/llama-4/42056289c8690a12c97c.json new file mode 100644 index 0000000000000000000000000000000000000000..70a31f04c18bc624aba704070d763fb10cd57785 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/llama4_text/tiny-random/llama-4/42056289c8690a12c97c.json @@ -0,0 +1,81 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "tiny-random/llama-4", + "_task": "text-generation", + "attention_bias": false, + "attention_chunk_size": 128, + "attention_dropout": 0.0, + "attn_scale": 0.1, + "attn_temperature_tuning": 4, + "cache_implementation": "hybrid", + "floor_scale": 8192, + "for_llm_compressor": false, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "interleave_moe_layer_step": 2, + "intermediate_size": 64, + "intermediate_size_mlp": 128, + "layer_types": [ + "chunked_attention", + "chunked_attention", + "chunked_attention", + "full_attention" + ], + "max_position_embeddings": 1048576, + "model_type": "llama4_text", + "moe_layers": [ + 1, + 3 + ], + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "tiny-random/llama-4", + "checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layers": [ + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 1, + "num_experts_per_tok": 1, + "num_hidden_layers": 4, + "num_key_value_heads": 1, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "tie_word_embeddings": true, + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 202048 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/469f61d7dad2f014bedb.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/469f61d7dad2f014bedb.json new file mode 100644 index 0000000000000000000000000000000000000000..474d9c616ec68f6de7706f07e407e68145cbe480 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/469f61d7dad2f014bedb.json @@ -0,0 +1,58 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/b787c4dd68458fa32228.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/b787c4dd68458fa32228.json new file mode 100644 index 0000000000000000000000000000000000000000..9ad9965e8cee3b4cd3cb3dc5b3dbf0673f2ac304 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/dacorvo/Mixtral-tiny/b787c4dd68458fa32228.json @@ -0,0 +1,58 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/phi3/microsoft/Phi-3-mini-4k-instruct/a22785acc9abfc6a27c6.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/phi3/microsoft/Phi-3-mini-4k-instruct/a22785acc9abfc6a27c6.json new file mode 100644 index 0000000000000000000000000000000000000000..ad9996b6bcfa266c77f93e898033e564645a20c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/phi3/microsoft/Phi-3-mini-4k-instruct/a22785acc9abfc6a27c6.json @@ -0,0 +1,62 @@ +{ + "_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" + }, + "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": "0a67737cc96d2554230f90338b163bc6380a2a85", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/phi3/yujiepan/phi-4-tiny-random/41d8000b51fc7c8f2ab9.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/phi3/yujiepan/phi-4-tiny-random/41d8000b51fc7c8f2ab9.json new file mode 100644 index 0000000000000000000000000000000000000000..b16ba10343390fe921f8480d73d5c609da59545b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/phi3/yujiepan/phi-4-tiny-random/41d8000b51fc7c8f2ab9.json @@ -0,0 +1,59 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/01c33dbdb9a7e6fefa00.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/01c33dbdb9a7e6fefa00.json new file mode 100644 index 0000000000000000000000000000000000000000..ad95e4babb68c0470e98be0c84c2295eaa9ec1ea --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/01c33dbdb9a7e6fefa00.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float32", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/170003f56784bc220718.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/170003f56784bc220718.json new file mode 100644 index 0000000000000000000000000000000000000000..7cfb2b18afd9d559b9715f1222a01f9bd69446f1 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/170003f56784bc220718.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "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, + "enable_bucketing": 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": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/69e6364014342d864b02.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/69e6364014342d864b02.json new file mode 100644 index 0000000000000000000000000000000000000000..4401aee8d598824a210026ce48aece0a7552be87 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/69e6364014342d864b02.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float16", + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/852bbe8390fac2afac2d.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/852bbe8390fac2afac2d.json new file mode 100644 index 0000000000000000000000000000000000000000..0c73edc0ea6dbd7697a560712a72d9535aa34767 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/852bbe8390fac2afac2d.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "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, + "enable_bucketing": 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": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float32", + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/cb09c070393c1ae56367.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/cb09c070393c1ae56367.json new file mode 100644 index 0000000000000000000000000000000000000000..badcb61b81a47bead04f6cc7836bca1ba8c64bc0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/cb09c070393c1ae56367.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/dbde8408df1e33f88a65.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/dbde8408df1e33f88a65.json new file mode 100644 index 0000000000000000000000000000000000000000..245f813ba8bd1ce103d4551926ece96f8f127899 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/dbde8408df1e33f88a65.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/6c0ccc000aa577aa1f25.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/6c0ccc000aa577aa1f25.json new file mode 100644 index 0000000000000000000000000000000000000000..464a695c58a92026efb5b043eef0222a02f83d7c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/6c0ccc000aa577aa1f25.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-0.6B/e7e66c0e61277ec50342.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-0.6B/e7e66c0e61277ec50342.json new file mode 100644 index 0000000000000000000000000000000000000000..b6d8882c5829d9bc23d5be91f78e6ebe0c6bd4b3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3/Qwen/Qwen3-0.6B/e7e66c0e61277ec50342.json @@ -0,0 +1,87 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "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": 4, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-0.6B", + "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/2502f9dc059367ba4857.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/2502f9dc059367ba4857.json new file mode 100644 index 0000000000000000000000000000000000000000..3b11f3f95e91d25738912116981ed4ee6127c502 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/2502f9dc059367ba4857.json @@ -0,0 +1,65 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "_task": "text-generation", + "architectures": [ + "Qwen3MoeForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "decoder_sparse_step": 2, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 128, + "max_position_embeddings": 40960, + "max_window_layers": 1, + "mlp_only_layers": [], + "model_type": "qwen3_moe", + "moe_intermediate_size": 128, + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "norm_topk_prob": true, + "num_attention_heads": 2, + "num_experts": 8, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "output_router_logits": false, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/895e022ccf1f32a63b38.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/895e022ccf1f32a63b38.json new file mode 100644 index 0000000000000000000000000000000000000000..f290f451c3ba9462e3f822617d948cb684f30871 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/895e022ccf1f32a63b38.json @@ -0,0 +1,65 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "_task": "text-generation", + "architectures": [ + "Qwen3MoeForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "decoder_sparse_step": 2, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 128, + "max_position_embeddings": 40960, + "max_window_layers": 1, + "mlp_only_layers": [], + "model_type": "qwen3_moe", + "moe_intermediate_size": 128, + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "norm_topk_prob": true, + "num_attention_heads": 2, + "num_experts": 8, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "output_router_logits": false, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/13ff1c08a4739824c960.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/13ff1c08a4739824c960.json new file mode 100644 index 0000000000000000000000000000000000000000..16ff7af2c4b95cfb4056651684308bd82500f37b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/13ff1c08a4739824c960.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, + "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, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 4, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.1.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "bfloat16", + "tp_degree": 4 + }, + "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-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..df85255dba94673f9de7f0198722e607340b5f89 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cb59182c5a1cd75a3d4b851080fc65d705d93ada --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:707a314b3cb8d0b9cca6236324024a7ae621644e0b34692f767dc40fd9dcf50e +size 415281 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8fdabee69f83d2d842d9b1f8976ec81a4b0c3c51 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_01470c42207e9b29b147+a92b0e80/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d2df672ed6f34df0686c1bfbba9d6a2d179520c768482c6ba46254c541e7526 +size 2601984 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..54473b523bfb201a8a73e96477dbc9db177abca9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51ec4463f406993c156718e436f7065c5b50b96e96b8b29e15b268ac0115b1ea +size 2446940 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..74171bd0afc051365f7cc173bd7016b8886d4489 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe297ebcf89dd16a03a53e4e0185500341da7cb47d3a219b230b07deae5f353b +size 2960384 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a711ba59386baafd7dedabd6e4272db2a4b7f394 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_0324ac9e35fd5fa5e6e8+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07b49c2c498c3917599c3c0f242acca562739d1f0778cd4d78435f4f5e56ac40 +size 3097299 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3e82c09fcd0c4887137b1c4f2689d5af13d91e76 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2908d815ecdf47c411fb65abab1f8c0c89a907146ca5585c50e8adf2f4a0c85e +size 453074 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..79b0fda1bbb79c4a0471ed8640b1d10cfa2df94d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_195b09cdd0c0438f2556+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:330b3501f67ff9b8114338982fe11ddec1492285947061c3cacec10590154531 +size 18975744 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d4da13501d882a71433248d346d9dc700940a6f0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:497a414a7e5aaa7c8cbf555223dd68c047c98aab19f213030360db2dc5e342a0 +size 2332276 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c59bbceac189d668a9b824bc169cd0e63ea2bf01 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abdc805f1086ff302573d6c7b318ca5d60900b19047b81c76ba4887205709da7 +size 2724864 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f1e1d46e284f1e38bde35a1695403eca41e17b2f --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1a286be93a0c3641f5b3+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1779fbd84b1754831f0a3c6a8fd56f39dd7101aec51ea7ba3669e50a823628a6 +size 2881316 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..6314cd417258813cb7d558f37a985f13422d4a69 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_97f69534-a6f2-4995-adc2-d7d40068808d/compiler_workdir/NeuronRMSNorm/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6a2752c25c9f7e1092e2b55c010694e168610ce3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c774c6626fc91684e924b843c1fe807dadbbac6d8a8e19443663b43c13eac35 +size 1165 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a9eddf961eb1b25dff10ce7f35a0612bc0d6cb31 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5b096badb6086196ec5a04499d8965d0c198bf3be7cde2e994a3ae44d106c1 +size 123904 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..85adb182c5c25d484290c012625d5727835d3ef3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b54f21d033a73ffbcdc+a3f02148/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c8403de522d314bb6bf3090240712eaa54c727536d7d054514ff3ea393706f +size 124800 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c97dec0a657909b286574ff621c8a5ec5a077855 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12499857648c59f839f6a04d4cd28b11128f5adac01a20df9ea2326c5583239c +size 1727543 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..27f68928bd42258a9bf87b2dcc2e97a26c271fb6 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:812678a0459d7bf3ed770262be15ce83b65e8821caf3791c5d344b7c4aac4d5f +size 1803264 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..edce2e93086dce7601c64dd90d99591675449e42 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1b5caf61147adc2d934e+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df98e2dcc3438508af5cd0ed706fc30757cce774bd32da809c97be350cbe64a0 +size 1959713 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..910439cb861ecc1d67872550f4f386b1ab46d4a2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51f9d21d7a03b72e80759a6fa19a09c7e71d8a2e874388f760eb03e4e4c92766 +size 1828641 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8cf00c5aa8b8593b189795fbcfe0085538284ae7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:433aa40bc35fc194582a36bab350f5179d942bbdcd577e9ee1a0a5e4265393ab +size 2448384 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..632745bf9e82d7e5f69680836bcb1e719202ddf2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1d73380b8f8ff586ab85f97f5bbbdcda51c7bc6415c4a892896b2a384410e7 +size 2604836 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d949ae2f4aa3f8178844696c513d8aa1a4494c7d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a6eef6ba0f2f8f2e5b2b08d0b1267a1cb9f5d863c6a9663b8734eaf119d5c7 +size 1299219 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..79fa0ccc250a403137055ac9da7fc92ee4508648 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_24cfc117f33f64ccf2cb+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d4107a5d0bd4ba3554f897e6813755bc970d8a204e1d6b43c18a6d45b9017a +size 656384 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_28d01c41effbb13bf546+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_28d01c41effbb13bf546+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_28d01c41effbb13bf546+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_28d01c41effbb13bf546+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_28d01c41effbb13bf546+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_28d01c41effbb13bf546+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_28d01c41effbb13bf546+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..459bf94c6876c3ac04c78424abcc4f777f13949d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_28d01c41effbb13bf546+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6c59baa5b152dde421f3f1e9e3f16f808025f1c0618fb8b2926234001607b85 +size 1302883 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_28d01c41effbb13bf546+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_28d01c41effbb13bf546+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ca4b5091ffa8353fa7a7bc282688b6fd2abb0dc4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_28d01c41effbb13bf546+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa14e30a4936f07a97140de050e459675d4fc9f777bf8d1ec0562ab5d4862c9 +size 646144 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2ac190bdc4561a89b8aa+5ba4a294/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2ac190bdc4561a89b8aa+5ba4a294/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..a172a33926889ce6f4340045867d8094a11e207b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2ac190bdc4561a89b8aa+5ba4a294/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_6b4d1de6-ba8a-46e1-b742-8132c4bd3bf0/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2ac190bdc4561a89b8aa+5ba4a294/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2ac190bdc4561a89b8aa+5ba4a294/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8496781848c02ecd308b5b2c5a3c342b702425e7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2ac190bdc4561a89b8aa+5ba4a294/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e79a5cc325f9a317d158d931d75ec73ae1cfb16a4d83343a2593edd95d0044 +size 8979 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ff0e02ee01e12d4d6b319e6d55242ac3d3ed1057 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b005807c7a81663fa48c930a8a7dbf2921a609124c888e0cff2a467de662daf0 +size 2025695 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6bcfeff4517c2b77485b009f5e98f1d76883a3ac --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4d259dd2baf2a9646a85b04d2dfe1b883af2acb2e51efd91637ec56168353c +size 1025024 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6c3934b6fe2d84aba52061a0726e09cbca14fc41 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_2efa5a7cdf24fddf8392+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:574e10c9771029469793550328413ff4398ade0f1a5d1161cfee87bd18428468 +size 1044660 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..717ebad2c6ba53ec4f76afc2db0901c5f1c1abca --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cde91b58c424dbc1ffefec99a1607b8de70254cebab0f5f54daa70b941268bb +size 1680431 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e00e7454f3cf8afdfe8bf8e2a66338f286ac811a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00ec2df95afa4e2a765153eb57f48bb83440d1579103231a2c8e781156820342 +size 1854464 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..08024184658c12525e0e89d67df314e5ebe34094 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_315517e0acf6029aca9b+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cd3c50e84edf0b15004b6e742e0408c9259a21c1bf012319ae80173f10da31a +size 2010913 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..77550054960373cbc83343e8486ab9e5466cdb56 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab3f5c5b7f60b8bf1f3a23967f03bbe347a788088d7764f634b462ff7ab04d2 +size 985198 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f39761ab8f3574dcb92c9d4de6cde9296c8cc987 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d363135efcf905916ec3d7963c3729b2dbcfba86ea92e5196eba15b38d0e41d +size 5397504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3bcaf76326aa82946559+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3bcaf76326aa82946559+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3bcaf76326aa82946559+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3bcaf76326aa82946559+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3bcaf76326aa82946559+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3bcaf76326aa82946559+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3bcaf76326aa82946559+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..54e6858cf6bbda4853b9a70fd91832eeae6b942f --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3bcaf76326aa82946559+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb157a44882f29ae948c11839e56dd2bde7fb8300f217bade959d561959b045b +size 1246857 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3bcaf76326aa82946559+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3bcaf76326aa82946559+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7038d4163787397b472f23df227c3dea08e56684 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_3bcaf76326aa82946559+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49fd73a3d1a4aee83cca8be21bb42baef11f3666e4e9f45b358f2d2d165a6e0b +size 523264 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_450f587e94e46ad910ea+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_450f587e94e46ad910ea+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_450f587e94e46ad910ea+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_450f587e94e46ad910ea+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_450f587e94e46ad910ea+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_450f587e94e46ad910ea+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_450f587e94e46ad910ea+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b5693c25d3db59a3cc99fff72aedf2f55da66c90 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_450f587e94e46ad910ea+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c91940faf003520b5fd6767279eff41f6313f9e9657980fd45c1c9431453b561 +size 1772367 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_450f587e94e46ad910ea+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_450f587e94e46ad910ea+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1dee9281add7956c10df5f57ca97176ee6173c47 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_450f587e94e46ad910ea+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e0341ca13b3ffa9a163cacd7c2166a12e4fb70ba62ce4bf10fc3eceb6385e54 +size 34632704 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..59897bd765036ef87720c3a1d1544b79efa0dc19 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..60353e3e7034f0b0cdf08b4fa9680250cc421785 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c051e4879cfd8bdbf2d56c9246144686cdf549884c14709e9a26b9a0cc7f646 +size 1338548 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..af083cfcc9ae987ca4b2e48dc5af049a2e47e455 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1976a4dde9fde2a2b9ed5c9e9560c7003622dd4a301111dd8cf47e3dad9c9882 +size 646144 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..29a9d944d0d49c41e662dc382de9b0729c8775ec --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_48cf67a7f3630493577f+d0d57c8a/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5471821b8db21496fcfb39dc4a8b0b5aa7fcfe98b7480c8497f8ff717f97bedf +size 655842 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f44fac22acb575b06778919d848d9842ee4dab7d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b61fff4fd459f6f5b9436447069544757836fd8c198c2d87f985898effb2e01f +size 1124430 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5110ccce111c827f2266396caa2d54e7882fc48f --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4a2b64355e0bb619a721+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e330b18cc3560dd7ac1256b72ea18762742985a49cf46e59aa6ae1b75a1ad73b +size 451584 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7c5d90345f377136608e22a743e0f9360b6698ac --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34470d66f21f6684108954e2afda2e19341a1ae0e2c62a25c9f5515d33f0b82c +size 2460667 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..351a9a76e4e2bea65a95a4526a540a830387d869 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1160c2137aef01908dd3c98ce8f21193153af7f65cdcf32c5a9c0ab946ca5bad +size 4475904 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b71e65899d1837fb2ba6061986e88a9281a60619 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4c9228ab4a2ba1e63983+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:108c12a3efe2bb642d6676cb85baa316a6e7b3911d0c77d91174cdfadb8c0b15 +size 4643591 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..be8697fd1eb5cdc081fd50c7e702cadf6db7bc54 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e31115037da788f075142249fa62389f6e31d8d99649b1dbf37505118ed381a +size 1340396 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..db4b7853f7408076a2b24260a6aab46c3e3718a6 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a2145326dcac3bcf6e6f337e58adf2e42be0822d46be97c613f5dd7d123b582 +size 523264 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0da8dd9afc79362bf4b7ed7c61b1c6a66add7341 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4cf09670cc966314fbac+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fce51e14a9a83bd7330558c180d36592790311dbb287438eb4118e5ed89facc2 +size 534798 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9ce94040b7e852267647997b3b125d8724c243ff --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fab487b60e64aa87f59b9509967598653bccaf3243f66d36f3f19933e36742b +size 2028423 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3105ff1ea1f2fe0dc01fa77dd232fbf225bc99f9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ad2953e99c0eda80e69e410eedc8023c82df3a70c76b395dfea8585b598c66 +size 2591744 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..28865c65c84a76ffd4a798d5a490a900f1473345 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_4e2a7e9d6c66ffb997b0+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:530bd890352167edebe5adc9eace8c1c43b0f16eefc144f490423da003b1d0b6 +size 2667330 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f6293d04c619d90665a386a7f8f07932f7b638bd --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a42447f12f8604b34318539a5637fb83bd81f35748cc41ec8788c063b2c5b7 +size 2187414 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..959052de9bb80f9642b0a6d051ff116c5e9c9255 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31dcbda78281314eadd5e7936d6011f89210c120f30e348211c1c2b614108b9a +size 23716864 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c9400ec44928e6ec00b7009fad4135d06b921313 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac081a7019c8c8d8b2ec2514f41ea1f888fcffed36d7987816744304e4135a23 +size 1284382 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c6712cb8bc3c2fb249ec1b27c073a080aaf8a0fd --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a284b85f1397d9d8a3188cf7e26f99aef4acf887ab0d473607f56e0d0d99c6 +size 584704 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..563fe52fef28b87c7a2e4a574daebcf0b51b7b10 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_54d943c37505f10935bc+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1462b8427b3e8651acf481a93d6401426dfec69fc658c0028ebf7b97011087fa +size 592623 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7e4b962b5eba89a4a049891f837893128ccb0c0b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b696f9f7074d5455a31f46ea93f51268ea495bc86a0ad6dc3095c5f4084049a +size 2333362 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a98ba19abc56d4e5a916b783ebfdd127d97253e9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ab87c0901d401248ffbdf2cab776b32d6d42cf0cf83a7a1076f36ae04790e3 +size 5213184 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1856e8698eeeff6e2b91335c40bc6ba132a15d84 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_587bc590d8801c17f369+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d476a1c960a97ab2443b433199cab6e8aaa9d4a3df8008afbcfc8bf3a63f76f +size 5400869 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..835084869a55d56bd7dc9f863da4b9a093fafdb2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c88972d7f48de3b646203567d4c481a3fa70f4779f366432dc48598c2d4320cd +size 1128085 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6954c840a2377b7012c91d65cb4f1d2498b9e09a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4866b61fbb2f9ec06f7cfe98a222dc3c8025ac5a372f6d697b97da8dc6edff2e +size 390144 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3beb52c8a8671a65f1f32215b21fd4a74ff0a22b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58a213e4f2515a39a3aa+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71375dc4398c3af0120a4de37c55f1ce262af7a2f95509cacd495d02a7389c5e +size 398499 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58bfab3ea35f7cda10d3+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58bfab3ea35f7cda10d3+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58bfab3ea35f7cda10d3+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58bfab3ea35f7cda10d3+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58bfab3ea35f7cda10d3+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58bfab3ea35f7cda10d3+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58bfab3ea35f7cda10d3+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ce43dfd596e7fd7152aeb62d786ecf450d2e06e0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58bfab3ea35f7cda10d3+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04c91bce5a07f805ef6ed1c8db4175ae7235bac9976b5c1029bab2359448ec4 +size 1918275 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58bfab3ea35f7cda10d3+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58bfab3ea35f7cda10d3+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9022d75c005f25db8351951c4a7832bfbb88190c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_58bfab3ea35f7cda10d3+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc0b1ffe24292c1a3fecb871090714d5a8b783b90a707f511d8c72c4e52abe6d +size 13128704 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..90c01de768b0367611f9e5f8ef3e4aeca45cbb1a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2117dab3e3ed8caad749b8256ab430c591d3b72a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec57d9d2f9d9be197ad88a58ece6b14b0ccab97c121b8d20cc9512558ddf6562 +size 70276 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..466eb2a828a0608522109e684b635b573a218a58 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddafe107c9ccd625e44c60097b05c006d5591a36d01e1d8e997e8b69be0fb2e1 +size 431104 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c55b9437903d977a983325b460001836ff7ffdc4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5949b466ee5d32903b5e+0b01cb42/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5a1335ac17ebfa49e49622676cbc6563c7b29018ab34cd018858af4a3aac85f +size 443199 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b42e8a26ac02c68d7be2439677eb09c4fcebb604 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e1f8ab9178c91201dfce6b4ff42207669032c0d34dac775fb25114204b1253e +size 2227261 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..089e993d5a48a40817d40fe493abcefb542b4184 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5507bfbebf110c0c3bffaea3d42344ee8a7427ef33be6d08f241b494d2594fa6 +size 21586944 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8ea7e06c69d1bd865ab1ccdfb58a7291030f4620 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3506308859fc50af44b98dd27a9c8cdc9888e190ff1ce4c63195db654245052d +size 2531606 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8c1ab841033fc60a8f5f8d9fb05328a39eeb00c8 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c58863c39188ca3503d1803b0f0c86dbef6332bdd210e767096b9f45159c5ec +size 4547584 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..cfaff0f4c750543160a822ab5d4bbbd94626bf15 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a0c7b596daa3ee0be4c+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b92600e075efa464b7f80782ce602fc9fdc92b057091052f5dce59449bbcd19f +size 4622595 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5db2cb5268c1af1c38fd+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5db2cb5268c1af1c38fd+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5db2cb5268c1af1c38fd+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5db2cb5268c1af1c38fd+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5db2cb5268c1af1c38fd+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5db2cb5268c1af1c38fd+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5db2cb5268c1af1c38fd+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7c97898052846631300a0ca899085aaef672b589 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5db2cb5268c1af1c38fd+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c3aa842caace792e2c70fafa62cb24ef766a6ca866008a3051948c6a072a477 +size 1647947 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5db2cb5268c1af1c38fd+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5db2cb5268c1af1c38fd+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c8c6d6e32cb8b3c8f4527ada4a5f98c077f3f10a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_5db2cb5268c1af1c38fd+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1d711306060bae498718fd791d50ab2f3b3fd81ac5a8fed11e11bacec976af2 +size 18340864 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6141e1bb55c6f48144db+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6141e1bb55c6f48144db+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6141e1bb55c6f48144db+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6141e1bb55c6f48144db+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6141e1bb55c6f48144db+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6141e1bb55c6f48144db+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6141e1bb55c6f48144db+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..091633b2ad96588cab0a0847b3ba6b18ffcb919c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6141e1bb55c6f48144db+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4203af642c48921fc1853622c87e6e75f5a367f5041103dcb4e38d03dff53b0 +size 2267120 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6141e1bb55c6f48144db+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6141e1bb55c6f48144db+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..90835ee4763e7f1b26e24ba50b97afce83b17771 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6141e1bb55c6f48144db+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f89b149a40d56c657ebca407497e3bd1a1b7c1c932c22ac20fd2975207d7d9 +size 34028544 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..243fe6804de438394f130092f65fd1bce1c5fce9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_7ccfc1e9-2653-434a-b853-0db82da7e687/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a11cc062167102b0f4faa9fdf16388d72d9e0015 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4590b82eb167fd46963abdbb717cc18cb9511961a3393d100eeacdbdc45b0243 +size 11280 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7e435fe6c7692a46a317954e70059420e5f9b2e9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9adf8ac202de2700fb558b322d7d14ee584bac8e78958528c288aa5607e2a37 +size 1342464 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9c680d14a242e85199116fa02551eb7461f6ddab --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6606a82d7268d6a927f2+77114d4a/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51ca42851dafdbc1d97aab82a49c77c9da16357adc5d5a4c25104cbbcf9059a3 +size 1345445 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6748a4382c808a15332c+a92b0e80/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6748a4382c808a15332c+a92b0e80/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..df85255dba94673f9de7f0198722e607340b5f89 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6748a4382c808a15332c+a92b0e80/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6748a4382c808a15332c+a92b0e80/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6748a4382c808a15332c+a92b0e80/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6748a4382c808a15332c+a92b0e80/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6748a4382c808a15332c+a92b0e80/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d720ab66f166d266c2852b1eef13cd4d6f0638ca --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6748a4382c808a15332c+a92b0e80/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98adcbeedb5b17438eefb927f8aebce924ed0b4c178268ce4440981f5ff8b1c0 +size 415213 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6748a4382c808a15332c+a92b0e80/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6748a4382c808a15332c+a92b0e80/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1c214dd890d33e770bd220743ee9f01f4438aeaf --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6748a4382c808a15332c+a92b0e80/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbf0d010bd40980b5de3124e90ba62d96c7cf71e759ae8f817ac1d38dc3010c8 +size 4168704 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..a556a0c3f8e6705ba4eeae0523a3af763396f569 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a73032aa62b64f59904c864d3e40e18fb14afe33 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b999ea9ba89a487255da2b130a2bdbb271cf57445eb26ac94e78bd297c00b1c +size 1365236 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6c42fce619fd78f2dc8bcd76417cf7d36fec4426 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_6d90bc000559d461c79f+564b7b5b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efe57e6c82ac454d00dff3baccae6b36d5841c3b369aa030a6414bb8d4e02a9d +size 687104 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..02ae92ab4cffd1ba2eadff4b8fa4c61b55bc9814 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70331c41379ce148ce2c076897cf20af388ca739cf08aee414ca106812279bc9 +size 503997 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8f738bce3ccd31f0fe5016648e78b25d4344f077 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9a2485c38b26e6e506310e9c9b6a2bbed38a3cb72992525373b63f008ddc95d +size 33629184 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_728c3b7e3ec5305504a4+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_728c3b7e3ec5305504a4+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_728c3b7e3ec5305504a4+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_728c3b7e3ec5305504a4+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_728c3b7e3ec5305504a4+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_728c3b7e3ec5305504a4+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_728c3b7e3ec5305504a4+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..80740da9491ad5feab525d30ebbb7c009d99e926 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_728c3b7e3ec5305504a4+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:514df2ffdcd1f8df0cad620bce6580e12e9dbe9c4185083808ac537f0594c7c2 +size 1647819 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_728c3b7e3ec5305504a4+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_728c3b7e3ec5305504a4+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d2b1832b3c090c0931f8349b998b9258a313bb43 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_728c3b7e3ec5305504a4+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e8d51fbe38f1a8c8cc90c54dd57c3f90819186142d8e373ced1e672fa83dee7 +size 18320384 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a0aa4dc52ab243ea73ff56bfd246ec338fb4b71c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77782fdab9f56144e7d5c218eb8e23aa06187b6bfbc1434af59c8ae366258595 +size 1302867 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5889efeec95f6f117f1e5ee67a2e5982fe934b2b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7387ca39d94080c41e25+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf9faefa6276b0561549b3f3ab9f7cb04fe7d6b312259195c30c152c84578139 +size 646144 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_75c9a7a4c810a6349cce+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_75c9a7a4c810a6349cce+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_75c9a7a4c810a6349cce+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_75c9a7a4c810a6349cce+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_75c9a7a4c810a6349cce+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_75c9a7a4c810a6349cce+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_75c9a7a4c810a6349cce+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..30bf4eb8e0874b185e13c94004d8fc798a15fad2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_75c9a7a4c810a6349cce+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e11615c205c78a7a77a12a35f7e7295030cfd3d4416bcb04a2b3754a8dd1a0bd +size 2081052 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_75c9a7a4c810a6349cce+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_75c9a7a4c810a6349cce+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f2a544192775e541ddcfe7413cf38731d0e60b24 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_75c9a7a4c810a6349cce+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:187afadd078b759d8a9d622822f0b389dcc89ed246eaf3ed8c8b8b7461a293a9 +size 1045504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ca464b6493043cf678f53773a5bd63a040150627 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff67764ebfa3ebdbac09a4ccb11d65676fa72cebf0e1fe8fa2a0145f74bf85a +size 503855 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4883e1c3fe2b53b42fc1ba9000a51dcc921ff5bc --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7857c254fa9a7edf3a37+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5434c7f88d9f24515b7ae4986696dfc8828e10aa976f311bb3a474ebfeeff6ab +size 17972224 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..90a0b36272beca28ea907b55fb62d14744874c3b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee4d5ebca4732581ccc5392f3c3130051c9b01dc4710efd3ec99ce56f613df40 +size 1280147 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..238a9dd012f5b2be0ab28d7b1db130c32e4d1269 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfbe9cc8894d956087bc7c3317a0df313f6e8e4b49e74b38669803c9d2120b03 +size 594944 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7986443fdcfd240582fe074ba0a3bc9b64f766bf --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7af2912e9b351fcd249a+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2d8671898a565e03f8068814a8d8637b8ca58e9839847b9f7268e52f5c7a6ca +size 602863 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..facdc7ebde9f335b53f32ab5035719092c602bb9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_c1269219-9671-4c14-9da1-4397b35e378f/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8496781848c02ecd308b5b2c5a3c342b702425e7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e79a5cc325f9a317d158d931d75ec73ae1cfb16a4d83343a2593edd95d0044 +size 8979 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b07fff09ef6cac6461c39181cc76418133817af7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce4188259ebeabb332ffe619985d7daaf343f25e4649408ac88e022cd2e0a3ae +size 277504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f50d96e7f7d63fb5a82203ad4b3e976b339ee7cb --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7c1663040965c8138539+313ee46c/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5187b88130966d0ada116d44c427f93585ca2c0ac12359a54ad0efe396e843 +size 280328 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3294677bec31eb347e80e2304482f7df3d25170f --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_ae531703-b646-4045-9538-20d3cc66a585/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8496781848c02ecd308b5b2c5a3c342b702425e7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e79a5cc325f9a317d158d931d75ec73ae1cfb16a4d83343a2593edd95d0044 +size 8979 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..147869ef4c840c5698472bb75e9e65395c99fc5a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bff8f3b30de36289956dde05bbd405147b7bcd64f20487cd8a747e9bd8c6e57 +size 277504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d2589e9b8b843e5960b1a153f688ee1e50429951 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_7f69a178350d6371c2e1+854ba76a/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb2b0005eebd8ac8a5bede1e6141c0ff0e3993a54c455dc4b276a36c260a9a4 +size 280328 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..59897bd765036ef87720c3a1d1544b79efa0dc19 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1928e5c07070a76467a961aefb5ab2da3f28b01b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44486bf335774a55d3ac735cf214f8b8727280862f8f4afb69b47eb6aa3371f1 +size 1343681 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9dfcc07089c09f6c320ca46b2da92ce24c9f413a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8276ed7562ea388112863f2a152abfb220fab2ad3835fb71c280f1189e08893d +size 646144 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b8b73344e8159c244d3e02b688f4603212e5535c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_838a440f0ba94b475b9a+d0d57c8a/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:514ae49ce22a00aad23127ed8d1f2d2d543398d886758adbff2c092b2d987425 +size 655842 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..622ee518e00a28a5314ff644b43e530c85df2a43 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6685e55222420bdae9612c35aa0f9b0fcecc455a7cdf4b502700f9a7d5dfb57b +size 1917069 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f6acddd3f699a3da5d12096cc9bca4faa34a8f3d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9b4d8785add128c5f75ccb31c74d9cbffcfcce5b8e5b66192c5f65cc93504cd +size 7896064 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e7f135db2d173b45c3bcb53d6d57256366be362c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_84431448df98b280d5a4+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27f0dd026e86cae8682a6612fc3967e9aeb1e3aa62d942ad025ad94118f6b931 +size 8044350 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..681f3ef082ada704c81c158ae9d18f97da44f804 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a05d55a3ba9ed1af510844c9797965d4cf4c24eb231b3e0e25021c14e5d55ed +size 588406 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7ef0965973422aa8d5b44ed5638cc94988306cd5 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b0f264fb42d12b5916bcbf73cd0e6b0189dad48d343359923f289414870bdf +size 2305024 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..92fc6b56e5fc7dd08eb2294f474208e619d0bd05 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b813129942113c15e66cf44ac3729e7efa743c3b5fb837929016cf014a5f7a7 +size 2461361 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ecf3321018998eea75a+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ecf3321018998eea75a+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ecf3321018998eea75a+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ecf3321018998eea75a+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ecf3321018998eea75a+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ecf3321018998eea75a+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ecf3321018998eea75a+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6646097ff2bd65c0df62882cd1755500164760cd --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ecf3321018998eea75a+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17acb24a9fcbbe4aba036a9daf80302334a9a097f6949e59c37137c8985e0a2e +size 1357130 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ecf3321018998eea75a+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ecf3321018998eea75a+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8849bb5117a35a59f7e38b080b698337bcfb5d72 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ecf3321018998eea75a+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1b8f53bbe5e8f801e0d178e735b629a035385ab5c25e006b1163a21aa168baa +size 605184 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_920c248c8c17f5746461+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_920c248c8c17f5746461+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_920c248c8c17f5746461+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_920c248c8c17f5746461+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_920c248c8c17f5746461+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_920c248c8c17f5746461+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_920c248c8c17f5746461+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5f296e4dea7d3faf83b7d0fc48ab8730b457cb34 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_920c248c8c17f5746461+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c04bb3d9543faeeda59c2fbdf50be9fac8a4744cb61efe2f4027814d261a353 +size 1129037 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_920c248c8c17f5746461+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_920c248c8c17f5746461+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..19959108fa98e73f1ff3ec004097f95e0affbc4c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_920c248c8c17f5746461+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dfe3c519be9fb32b48b52eafad32bd30fd39f31a9e8a66e8ca8fc1e64f2f983 +size 431104 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..90c01de768b0367611f9e5f8ef3e4aeca45cbb1a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f40b0ee45aca1c7e21a0aa6a6a8e59e2571d9f35 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1702ec62daf7053b2dbd068c167f1422d1e605d7623be441ed8ed851d95cf57f +size 70278 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b96ed436580ebae617b461695d0acda5208f11f6 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671c0f3928be702cefb85f184aa726dbbf9efce9a249032939fe47bd952e4205 +size 431104 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6292190ce253dc94723b50dc14ef7e9a6e7d7cc0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+0b01cb42/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a8afec2169e22653ed984477ea526178db2309fe0697c0e7b371cad8e8ee2cd +size 443199 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5c62298d8a08d196e9705a2dd5985a702ec26668 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7b903d94040e120e0b411edbe0e71ac2ed6b07253e5156968451f84d12dd938 +size 380010 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bc79ea140e142504feacf0cbddb2ef5c4bb20bce --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bd81a8e5684112475107c9f06fb4c2a7a5545f9a7b31161ba72a6f7e231076e +size 2714624 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2a6e35c50072a936d92f53b5cc950d2b3b17a63d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40610a3632e30b4a2d184ef4cf6acce6b5cf1af439bf4fce15ad875c13bbd2fa +size 2808688 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_999e22b80b6484bfea64+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_999e22b80b6484bfea64+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_999e22b80b6484bfea64+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_999e22b80b6484bfea64+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_999e22b80b6484bfea64+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_999e22b80b6484bfea64+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_999e22b80b6484bfea64+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..22d97fdc0a65db8c1a685388b4917d7bef772d33 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_999e22b80b6484bfea64+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58dfb75bf8fedcdc2e7a19bfaa54517ce8e5b6549064ed04be47d7873fd2e346 +size 1970671 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_999e22b80b6484bfea64+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_999e22b80b6484bfea64+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..56aad521acd82cf726468e487210ac4f413c84a2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_999e22b80b6484bfea64+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca800f5e087b190f8ce6523ca4532071d44980e4228de8329953c5d5c48adb4a +size 13804544 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..025227540bd096d9965b95e87bc46773da88219f --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:221d9900764dc5760a3d695ae2053b499329036623d488849574309e9e92bbc9 +size 1875753 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9e28d451bac5ecb7590b322c66c0b8802fb6de59 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc6f75477819607337d0653d6d131f3dd4722cfdc986bdf65b7adeb56fc6b9a7 +size 2294784 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..85f6ae8aea65611d9f4115be4e9a7407a5d171fb --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e80bfad5095c3f6a5ac472d4d43b2bc2a685e8502357bead47768e21139ff49a +size 2451236 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..00bc32d086d98a21804c160bbb6a724b8d3ae9b4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_fc8e4646-569f-4184-bf6b-d8e0eb33849c/compiler_workdir/AttentionModelWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a11cc062167102b0f4faa9fdf16388d72d9e0015 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4590b82eb167fd46963abdbb717cc18cb9511961a3393d100eeacdbdc45b0243 +size 11280 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d9cc39146274cda18187d8fba545d989a263aacf --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431e4e5ff922d6a474980bd9387beef3e5706cee848cb766ec7579d640b9b872 +size 1342464 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1e1f5dc341ea777102a6aad4dc1bbb0c3f076e9c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a87943be1c24879a03e7+aa7059d7/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2488bfac557f30118c56f44c7f30a606b473ac1f03ed7afbdec2aab8fd4d846a +size 1345445 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa028c0ea0061525edc0+be13b572/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa028c0ea0061525edc0+be13b572/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..4d0177bae4087c9af0cb9aa0b256577127345e01 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa028c0ea0061525edc0+be13b572/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa028c0ea0061525edc0+be13b572/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa028c0ea0061525edc0+be13b572/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa028c0ea0061525edc0+be13b572/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa028c0ea0061525edc0+be13b572/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fff44d7eda1714de5aa1698174259cd223360a13 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa028c0ea0061525edc0+be13b572/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f15529732da69bc4f0b0dafd6aec35139c40308cb34857d82f399c6e3cc8a5b3 +size 103199 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa028c0ea0061525edc0+be13b572/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa028c0ea0061525edc0+be13b572/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3f13f1cb330bc0d23f34702e54fa7283222483df --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa028c0ea0061525edc0+be13b572/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:392cd9748eb7c65da03b8f4f2b38ca84f71c637e51a06f0d7548b977f564cae7 +size 809984 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..55b3d25c9df3b57bf9cdbda0f91f94c2de57c0cf --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba77bfe1a58678015961b0cc297841494243fe73291e0b07eb8c2dc21dbd60fd +size 380078 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e30394f0c272a42115ceb62199121777a82fd31c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:207c81533912f192810c241f23e5ea7d4f4c4ccb654ad8dcd145a1f6dce340f6 +size 1618944 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..30f443925570df7cda116bc12156509d1a41f53b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_abe45f36284191617cd9+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fcf360b6c528e071bf1851948b8195fcecb45caadf27633a71f04cf37b441a9 +size 1713356 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a8c1be83beee7433214c7c8731e56bea2e35c542 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22f4eb30408fd25e6bbcca19151491656a2d760c06ed4d3e24d02ac5963158a9 +size 2025142 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b0a7e7784d7e4b8b7142a805b52f89b0f1953d25 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_be17c36b8b167d6848d2+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d30f876eca1099f092e6bb1cf6b35c7f783856a8b70985e70e72f347d09c4638 +size 55297024 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0c112df305a44ecae4165b9ac42d37465f6cb0ad --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9055335c2580e196d735081b0fded88162b24529feb85279b2685e5411ada9d +size 2018688 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..03851124aba3e90ec2ff7f310afc57040f4f5df9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c831c878efbfbe7a9c25+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d863a77cefbafdfdad8b7a79ec057f93db8a7c62b5c253b6df9ff1584ff2ab8f +size 44114944 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ef8a601275b9be321010398a0dc7ee50b8260794 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c6d0294b4b484456f583aa50139e32bb4c6bdf4bb65ac23356842f44962cab6 +size 453326 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..95aa4098efb5dcf49613cefc87e51c1817db0330 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ed11ed03c107828528f86c204512297210faa9c208f809a1c8055fa46b15119 +size 35154944 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ec02fd199834ea0a773adb77719273938b72936c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48e2ee6b950bfa3400e3b5a8c05d6257832092b337036fd44961b079ce5a9887 +size 1284382 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..156dab2990c56d3bdf721968075188796f659047 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be57fc082672bc63645da219807a53a9d988bd4cac2176ee3bae166008ad9269 +size 584704 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..990a490b7498aa39f587407cdf71e434b41714d2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_ceeb2de518f3f121f9df+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79c97f9e4a4ce5b4143c8d8e4f2c8d86cc30cc0de3698feafc7d01afb5534483 +size 592623 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ff3d96a769d52452e08461be11a555c3d969511d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_4ab2217c-aac3-4953-8de6-d843947f737e/compiler_workdir/NeuronRMSNorm/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6a2752c25c9f7e1092e2b55c010694e168610ce3 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c774c6626fc91684e924b843c1fe807dadbbac6d8a8e19443663b43c13eac35 +size 1165 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3ed35d94499edd1c2ae0ec678c36a1534331812b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b85d4f3d45bbf9651ceada23cba6ae77d4a907c00d9f0ef79ef8be0434d784e7 +size 123904 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b353b128866f90419371859c28162890032cca25 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d58f5bc208060e00240a+350ce682/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:115d0e758f7e3fb2e73697320baac54b1a8369da68c946247f521193e076d1b9 +size 124800 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6802045328bd9b6d8961e2a6419d2267910bd2c7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1b6b54d951e8a43cd63536d5313f26c83a415d06a3aaf93318400650ddbdd7 +size 2028423 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9af46f6501138edbe7953471bf12abe40ee1756f --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff1d349681481cb17b8cc209da22e5198bc29b6b3ea50187ad43957bfc388efe +size 2591744 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..489639195aa6027fbcb69ff5b57b013f629896e7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_d961fefa73e341c88838+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826bf1713de252bac8a561c62de3797b147aee00dd4e1f991e635563681c94e0 +size 2667330 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_dcfbae5d14fe3d7bc51b+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_dcfbae5d14fe3d7bc51b+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_dcfbae5d14fe3d7bc51b+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_dcfbae5d14fe3d7bc51b+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_dcfbae5d14fe3d7bc51b+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_dcfbae5d14fe3d7bc51b+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_dcfbae5d14fe3d7bc51b+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4a43f09508ae060eb93c4bfa6206984f185c784d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_dcfbae5d14fe3d7bc51b+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad877d221e77c482ec00869bd498b86ce5419f11ab4d404d89ddba6d62314c9c +size 1970479 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_dcfbae5d14fe3d7bc51b+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_dcfbae5d14fe3d7bc51b+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b51505c63e63db58e32c8c4886ab0d875134c90c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_dcfbae5d14fe3d7bc51b+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:353b28af52a19db72de3a6a68ae4d4342f7ae6bc2fe473fb46b747a1808844be +size 13814784 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cba84732b1e7e93bad19fad9be97c5218899542c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a07bea70618b7c85062b5f863e8305e402aec7e81a469b15e5593077ecaf2052 +size 2332276 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..620f3995fbf8683fa4ca8f0dba07ceaab378baf6 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e74223b8376879006703aee1e12c373a2810f556bccaa383676dd723d264aa9b +size 2735104 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9b4cf97e5646b3609d3b210be6572d7fae20179b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e4fc31a8d9c144896bd0+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc3cfb9a90fd94549996cd66e9ad9298954cad5a364cb83c53246df3fa75192c +size 2891556 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4c18bf4179e6d0313fbf2eb32d0ed1ad310bca60 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:337addba1531c5577d5f4e7ddba5378c9fed5362e83a4eef93553a3d75d9d0f2 +size 1123231 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..767bb7e5cced77df0e9a57da1f647c1eaaf034e7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23c8a2383c3a8af60cf85132748bb0d667926755ad35b00b8d7f6373516cbcf3 +size 390144 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..695c3c5eb317b6818c252c2b34d97caf4c223450 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f20adcf25e6f9d0f0500+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c26282b81f43b210a03de8a607abcf9620bbea248ff13ead214503186e8e3db +size 398499 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2fb0427ce4a33addb5a2fb0a033c62eba07d155d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e99eec1c44bd444e4b8d60de8a8f8657c659b80439364799cae72b731d849a7e +size 2111671 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6ba8a9a635ac776657824cbbdb093c604c8c53d4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f3262465b016a562f84b+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca533b51dcc91cd56a104003ab6bc7bc407a36b4afd05e53adb28e120f10cdf1 +size 15719424 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f52103be87a16d51075f+564b7b5b/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f52103be87a16d51075f+564b7b5b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..a556a0c3f8e6705ba4eeae0523a3af763396f569 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f52103be87a16d51075f+564b7b5b/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f52103be87a16d51075f+564b7b5b/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f52103be87a16d51075f+564b7b5b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f52103be87a16d51075f+564b7b5b/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f52103be87a16d51075f+564b7b5b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..08334a05f8bd43bb172dd09e84e6b2318e1e3226 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f52103be87a16d51075f+564b7b5b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e507196b5ab6487f7528313ae6b6d0ebb2e58214331bc634996f01749fdc080 +size 1371142 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f52103be87a16d51075f+564b7b5b/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f52103be87a16d51075f+564b7b5b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0d346fb6d3fb5110bf5ddd7dbdfdf39aec757cb2 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f52103be87a16d51075f+564b7b5b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8f72ffe3700724329cba725d22c2a33d3d0d6dde5391553c35c247625789bd +size 687104 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..fc27c67e0f3bd30aba010defcc6c2d0646e87b83 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d2c4315750ac64782d0228cbbe0f2223034d7025 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d7502da5f9e5ac9b655d42c31d3a2011172032815df62a2c7dbf5cd4e75c88 +size 1878426 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8d99df54d4d07d47848bcc32110cdde4f530ff5b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_f9260d832dabcf299e0e+877608f3/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:690514bb979276f1dd2bd20877682262fe3f2fc331ef4459c801c17abc72099f +size 14173184 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..4d0177bae4087c9af0cb9aa0b256577127345e01 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d092b3b4dbfc63819770a5c31fc1a4d23c68c36c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fa05b05dfd56c54c2f0dc084e7f6338cefc15e4f1795bee00d22202e4f2b99b +size 103181 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..75ae0f8b8a6fe502d092124dd1572d9cd5a69fc6 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fccf2ddf2bf73205ff5e+be13b572/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aa4e36eb1ba437a5fc4badc1129d56d094ba89ec9aaf22d06e28d000d77b10a +size 789504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8da50ffdebbe4b136d67d64bb87ac42d154163d7 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..697bf29040f369ad05a7edc19f413577c9dd93cc --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c1d93c70855cb7094e613180d32b90192444e9a900b453ae28170f823782df1 +size 1227664 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..700636e815afe4ee15fd39120d986b6e2cf868e4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc90e2ca15c6787a332988fad327e0fb5ab14857fcf5bd1e771ea61d89d5992a +size 461824 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..cde6e513a2c98cc10b5fedd548f5d1f298ba0c2b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fe41e7d06c2497a6f69b+747527b0/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48094e734ba250efe2a39756946731518d3027abd1057ce6e190af7decbfadbf +size 470151