diff --git a/.gitattributes b/.gitattributes index f30d487e1b15b4aae1676d77f15b6d45d5361801..cd4259c5b21fbfdcdeab33db249f7b4a24b89893 100644 --- a/.gitattributes +++ b/.gitattributes @@ -6136,3 +6136,34 @@ neuronxcc-2.21.33363.0+82129205/MODULE_eb36f973e5afaf932d84+a02c3a36/wrapped_nef neuronxcc-2.21.33363.0+82129205/MODULE_3c3275e8a9f242f022a5+24129607/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_f20c2d825c9eea3ef8d8+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_f20c2d825c9eea3ef8d8+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_05584a522a6853ba0eb4+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_09cd9547033302db1d02+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4183d5be6001030603fd+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4386b9df6b20120d67ef+677eeb9d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_6f75af6a30babfcdd019+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_833bb585fe5b0b130f37+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_a8fc2fc4fb9affdb3f34+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_aa0c40e8632cc47ef550+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d12c75d4a55a1f29a67c+283df001/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ebab4b006fd93fdc9f5b+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/c70db4c7be1d872d4380.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/c70db4c7be1d872d4380.json new file mode 100644 index 0000000000000000000000000000000000000000..9ef0acc109fb18b45d0d8b59f21f14424323989f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/c70db4c7be1d872d4380.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, + "dtype": "float32", + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/llamafactory/tiny-random-Llama-3/29c1f48affaff8ffcfac.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/llamafactory/tiny-random-Llama-3/29c1f48affaff8ffcfac.json new file mode 100644 index 0000000000000000000000000000000000000000..697842c760a3f27d9d4eea86278075e368f5e58e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/llamafactory/tiny-random-Llama-3/29c1f48affaff8ffcfac.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, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/unsloth/Llama-3.2-1B-Instruct/218ac2136121c43bdfd6.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/unsloth/Llama-3.2-1B-Instruct/218ac2136121c43bdfd6.json new file mode 100644 index 0000000000000000000000000000000000000000..6136073dd6cb8b3b5be9c5a5f9f3e517e25069b8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/unsloth/Llama-3.2-1B-Instruct/218ac2136121c43bdfd6.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 5, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama4_text/tiny-random/llama-4/6f976ae1dd1306830cee.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama4_text/tiny-random/llama-4/6f976ae1dd1306830cee.json new file mode 100644 index 0000000000000000000000000000000000000000..f465fe3135497f788419c67d550e0601f3c67ccd --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama4_text/tiny-random/llama-4/6f976ae1dd1306830cee.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", + "dtype": "bfloat16", + "floor_scale": 8192, + "for_llm_compressor": false, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "interleave_moe_layer_step": 2, + "intermediate_size": 64, + "intermediate_size_mlp": 128, + "layer_types": [ + "chunked_attention", + "chunked_attention", + "chunked_attention", + "full_attention" + ], + "max_position_embeddings": 1048576, + "model_type": "llama4_text", + "moe_layers": [ + 1, + 3 + ], + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "tiny-random/llama-4", + "checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layers": [ + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 1, + "num_experts_per_tok": 1, + "num_hidden_layers": 4, + "num_key_value_heads": 1, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "tie_word_embeddings": true, + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 202048 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/mixtral/dacorvo/Mixtral-tiny/3c7054d9dc66bd2bac24.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/mixtral/dacorvo/Mixtral-tiny/3c7054d9dc66bd2bac24.json new file mode 100644 index 0000000000000000000000000000000000000000..a47d631eb8de36fae0833dfa44c3adf36de4900a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/mixtral/dacorvo/Mixtral-tiny/3c7054d9dc66bd2bac24.json @@ -0,0 +1,58 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/phi3/yujiepan/phi-4-tiny-random/24920d8a9e6a1b9184a3.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/phi3/yujiepan/phi-4-tiny-random/24920d8a9e6a1b9184a3.json new file mode 100644 index 0000000000000000000000000000000000000000..c79805940bab072d8a65b0eeca23f96943261a74 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/phi3/yujiepan/phi-4-tiny-random/24920d8a9e6a1b9184a3.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": {}, + "dtype": "bfloat16", + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/1e7190a04a0a96096a6e.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/1e7190a04a0a96096a6e.json new file mode 100644 index 0000000000000000000000000000000000000000..40a777835cea9bbf035a79e5389bd171e522dc56 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/1e7190a04a0a96096a6e.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, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/177ef8d3b7a3fa2f05ba.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/177ef8d3b7a3fa2f05ba.json new file mode 100644 index 0000000000000000000000000000000000000000..9b0c991a99cc6abd18acf3690c8ff8cc68d79d6c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/177ef8d3b7a3fa2f05ba.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, + "dtype": "float32", + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 128, + "max_position_embeddings": 40960, + "max_window_layers": 1, + "mlp_only_layers": [], + "model_type": "qwen3_moe", + "moe_intermediate_size": 128, + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "norm_topk_prob": true, + "num_attention_heads": 2, + "num_experts": 8, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "output_router_logits": false, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/smollm3/HuggingFaceTB/SmolLM3-3B/ef66b0455dece5e18231.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/smollm3/HuggingFaceTB/SmolLM3-3B/ef66b0455dece5e18231.json new file mode 100644 index 0000000000000000000000000000000000000000..249cbfbb0a552950d47afcc5eb081a3d8f7cac22 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/smollm3/HuggingFaceTB/SmolLM3-3B/ef66b0455dece5e18231.json @@ -0,0 +1,134 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.4.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b64123213be94737cf87ecb9f29f0124f502c2c0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f2b999a60c82d86979d0f6b90a6c682dbc9539e64ebe06b9bb34e9f8065e04 +size 84114 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7f0008e69692af5905c91702b5801170977bb81a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6e2652844332eca1427cae990960fd98ac25eb584d577d01490580abbd0b034 +size 246784 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7bef34ffdb2b9dd11501cb4c581b75b5835de43c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_04605cea463a0181e7ad+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8771520a6caf1dc15ded687cdf16046be2d5b5d7e47d134e71deb34a171b7214 +size 254967 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_05584a522a6853ba0eb4+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_05584a522a6853ba0eb4+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_05584a522a6853ba0eb4+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_05584a522a6853ba0eb4+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_05584a522a6853ba0eb4+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_05584a522a6853ba0eb4+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_05584a522a6853ba0eb4+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8d267f32871c35f7db69ac7ac2c8e0d9240bd449 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_05584a522a6853ba0eb4+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2cde5baa98a83cf7d1f88fa3ed4d8421e81f106a689511fb8b313bf33c45b9e +size 761066 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_05584a522a6853ba0eb4+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_05584a522a6853ba0eb4+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..182bb57743e00af84228605f6ad173f3cb8e948b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_05584a522a6853ba0eb4+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c38cf073637de93c6a4c9bbd5b9773fcb49d5bc61b2e8b9ca9a78f59e54a29c +size 12493824 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_089479b62bff8cacc87f+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_089479b62bff8cacc87f+a02c3a36/model.neff index 9f49ffcc31382c8e622be4afb9f08f158a44e1fb..bd1bf0790388455e95d965c0476777472051835f 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_089479b62bff8cacc87f+a02c3a36/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_089479b62bff8cacc87f+a02c3a36/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:352e1f4fa5879bbce960062200136f1973ec4bd426e9b8f640627b514922673d +oid sha256:f21f6bbda57bf7e070cdc973f3fa7c2644644fbf240be8541b7065349c8dcef8 size 6933504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_089479b62bff8cacc87f+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_089479b62bff8cacc87f+a02c3a36/wrapped_neff.hlo index 2d832871fd2f98f70e2392155d8cf4dcf8aa358a..8276e9897e2ab3b46c5bb702f34be69723c31645 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_089479b62bff8cacc87f+a02c3a36/wrapped_neff.hlo +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_089479b62bff8cacc87f+a02c3a36/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:488a4589cff192212f11c47d203f5f3d182e50a7b1f35eda5e8da1e15717747c +oid sha256:10393c2cab5611ae66184955d37e5ee955eb6f40016323dcc12ac2c8d4bcc491 size 7117697 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_09cd9547033302db1d02+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_09cd9547033302db1d02+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_09cd9547033302db1d02+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_09cd9547033302db1d02+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_09cd9547033302db1d02+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_09cd9547033302db1d02+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_09cd9547033302db1d02+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..06610e1476d74d2bec672bc3678be13a7baa0541 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_09cd9547033302db1d02+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07bcaf8a1f374dbd37d11df8fc015c6a3bdfe5ec169e15b6c6167b0561ac31cc +size 694128 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_09cd9547033302db1d02+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_09cd9547033302db1d02+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7c45b00a78f51d94e9c539ce3f04af1c060a05e0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_09cd9547033302db1d02+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a294f59751c68c5fc320e02c16ca0a4998a63238dc675c81a4f6328db0682542 +size 625664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4e86b88673a4962826d93c5a9e15dca102112d11 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a50160f95d4d88b8d0cb2caaeac0d394a6e3c316c2be404ff978c1b367431dfd +size 82653 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9e78ab8f78b3ac72a67a9474c37513acbf6f12cd --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:560e291c18ae0e13cd4c74b809ac9c0a69eed02b93b829f21b8bb430cad3976e +size 216064 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d284d01b66e3616addaa0656ef82903494594189 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_127de87388b95258c57e+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ed4c789494bda7c4193add75974fc27cbd033f8f3e6705fba96ed38f97e0714 +size 224275 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_16c5142e54049280b3a6+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_16c5142e54049280b3a6+24129607/model.neff index 4d48d39cbed9c1233b72178058b4ca7bb046766d..22de0cbcbee8d593dbd11487eac85677832da974 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_16c5142e54049280b3a6+24129607/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_16c5142e54049280b3a6+24129607/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6d47b2099e1f344db8cd4f2ae01b0eac58d96d14b340a38c9c1ae4ff07ff5939 +oid sha256:68389367bb30af25de76a4c417e2d0c446b2562faa97b2cbb36aa2a9256dae0d size 71302144 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..254e0ad688d163a671b1b57f5e44e86b76ceba7f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e63fca0f24dc0f69649248d5eac0c2f0cb77dde6f88efae6af8e063e9d3d06da +size 85024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..67b2192140936fa3ea765ac4f42a52768d890c16 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5beab2ee0ae183b40189a51d8ddd3b6bb09b599e6c594b717a8405394246ee94 +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4741e31cb840a44fc80c37d6db20d9238290d581 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_23ed678a33869816b749+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:190c8d1353e804bcd4c147b8c311dc08fef8d163541d05d980fd3a4e84492ae3 +size 285717 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3b37aff244c1128985f5+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_3b37aff244c1128985f5+24129607/model.neff index 99221054cdb4f412cae0502fc7088907df2cbd0c..2c0a7dd181362c7795a34c1cbea25275d4e3e95c 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_3b37aff244c1128985f5+24129607/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3b37aff244c1128985f5+24129607/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4f8f677cddb6c3b3649824eeaff9c19a705501d084bdb35edd86315ce5aa14ef +oid sha256:f8476d85cba12830b772ba3f157a569bb0c2cb2bbfd65c678b90251ba6f06ef5 size 14654464 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3c3275e8a9f242f022a5+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_3c3275e8a9f242f022a5+24129607/model.neff index a09bb255484c9e1ee1ddc2ec172df7e1c8782151..d722f0b2c894a8d68d25262e1a96476322a847d3 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_3c3275e8a9f242f022a5+24129607/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3c3275e8a9f242f022a5+24129607/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:86dfe31aa117b3ba760131dd7754daeed2565dd12faa2c506f3907c7043536ad +oid sha256:4982c2d39eebf629ec91e57f9a85da471cc907955a7ef0ae4523edeb97e47d82 size 22774784 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4183d5be6001030603fd+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4183d5be6001030603fd+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4183d5be6001030603fd+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4183d5be6001030603fd+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4183d5be6001030603fd+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4183d5be6001030603fd+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4183d5be6001030603fd+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..54aef1b9ff33e67fc81764152d7dc18fd2c3257e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4183d5be6001030603fd+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e85d3e2a3ebe4acab2722835a65a1e08488dc52ee22d8f328beef73f4d6686a +size 83504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4183d5be6001030603fd+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4183d5be6001030603fd+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fe935810cb0fb5bfe53619b1be12293ee9117c03 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4183d5be6001030603fd+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e59b6d51d41360d52fb68989fa190a7fb0d389f7376caa101bfb5012b5bc7c1 +size 328704 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4386b9df6b20120d67ef+677eeb9d/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4386b9df6b20120d67ef+677eeb9d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ae7e0c6790082c43cd145aae8cc7e3cc89e15ca8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4386b9df6b20120d67ef+677eeb9d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4386b9df6b20120d67ef+677eeb9d/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4386b9df6b20120d67ef+677eeb9d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4386b9df6b20120d67ef+677eeb9d/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4386b9df6b20120d67ef+677eeb9d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..98b365756a1477f30021f530c30076cd0f9b3cc1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4386b9df6b20120d67ef+677eeb9d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41cbbba5e64669f88f166e6e00ee0e0e5e2e400e85216c2a34abd2f7cf6b4d57 +size 423848 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4386b9df6b20120d67ef+677eeb9d/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4386b9df6b20120d67ef+677eeb9d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..984c8cc114b3d9daae4196e5ef658ea8e86f64f8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4386b9df6b20120d67ef+677eeb9d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac85e4ea5ce014b40fc0e2ef545793aedd869c02f834be33ff3b51e6f9112252 +size 3687424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/model.neff index 217b31e06410cf0cdd16744728ca6e2eacec2142..6a2eab235b95f8739ec984e0181a53ab11ac1ac7 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:207328f34dba9857a443d60be4f198217bf5a1274a6b5ab68e5ab3825ae589a0 +oid sha256:eb478847dd694f7ad0a83746a6410c240f0f462c807be9ac4197cd6e22395740 size 12411904 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/wrapped_neff.hlo index ec601859aed0046abd08ca0473fb2dd1173fc217..89944170f339c9a2f63698f8a85a2a910c272149 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/wrapped_neff.hlo +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5a2ed470eb752b572dc5+a02c3a36/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2167578e2fae7cdee29a618d3c0baa9bd0d1f1a2e508fb541a472284c509c026 +oid sha256:831569ad3797f3f05f180da2720fe57b55a1be452113afc66b7e4ee63b90a894 size 12558920 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/model.neff index ef77fbf3bef73b934c63f2db90766dcb02df471a..60c0b8e16111cb8eadae1efe1aec09c2a8f68d84 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a89dff9420bb47f469d7ea4e14bba33f5206564b8389652e4e96cb42807161cd +oid sha256:d98308e45ddd448ddbc8a54dfab20d673adb007ac2926d05dc406c8b88377fa0 size 5008384 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/wrapped_neff.hlo index 856804c8c1a5ec041a8ccc01ac635f0c278f6bea..3724400eb0dba1470ec262d286969d4842df2db3 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/wrapped_neff.hlo +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5a68e035d2f868ab14d1+a02c3a36/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:279c14778484f37804d09e1f38b623bd4aa47615e73ab0955fef78270710077c +oid sha256:96e00ca7c5c487cc4686abfa7e8f7ea115e132067590de051fbba1fb9db8d0ad size 5192563 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3d7d85cd3d975162683053faa369dcc6259604af --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..69703c783a5c5784dc6800dc7651dc774d0f568f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f13c85b13166643ce5e8a1a9ea9c9229e7ee61e288a3e0042e7067e4dff041 +size 72553 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..551c4f22ffdd6cbb1cdc2f9cbbb1b7ea64d2cf1a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae584337d3ac24c64d0ac46f5bed3bf0cc822cc12059f4677303ba14b016c09 +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..cb3057c8dc43d0cd9a8c1df803e132f1e9fbb8d3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5a95b2e154e7d24b16d2+80d05c3f/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a6e4eddb87d4eff1e83c77a564fc725b53c5725796e5ca9c3c3b03ba8a8661 +size 289434 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5c3f594ed06ee38231d9+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5c3f594ed06ee38231d9+a02c3a36/model.neff index da3e9472636c6b982e0008810049d207df5574f0..bc349a461e896af931c95bcddfef04231820cb51 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_5c3f594ed06ee38231d9+a02c3a36/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5c3f594ed06ee38231d9+a02c3a36/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:848ab7c3bb7d90d7377c118097d7d97d9d06466578852d0ca5ff1206fa5872cb +oid sha256:f5b8742701edea50e9b339241213eb9085d48bcdcd93cf3617bebb4be8188ba7 size 8920064 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5c3f594ed06ee38231d9+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_5c3f594ed06ee38231d9+a02c3a36/wrapped_neff.hlo index acd017bb25e33cdb4ab1f0e41adfcacf325d770b..a3a9450b1bc848b6a1701608580453ee13cd60c7 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_5c3f594ed06ee38231d9+a02c3a36/wrapped_neff.hlo +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5c3f594ed06ee38231d9+a02c3a36/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:095c5100aeccdfff039914b02b583af9ba9926a1ab10cc2fa9dc313954a11a7f +oid sha256:44c9cff6f5d47fc8f0ba776e3ea5e9665990cf3e7bd2ddaa4dbe27537b55e1c3 size 9067080 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bf0117c17d50244b7176c2a9924040b83a37180c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f140ea6362f69c0f98cfd36d894ca317980049d7f20a960c905db8b3d5c80ac3 +size 80789 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..94db693717eb1fadc21893938e754aa58c62aa46 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8edc1cf916a402a5b8dab3c6b57541b78116ba0eef5bdf1b4db0c6b78ecbf359 +size 287744 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6ca5b027e33ad7997c546c26a96a04839186ef4a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6436324b782a1664e4df+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa4cc246328ddd7b3c536dca9db723562c52cce7121d36a443b29727efd7342 +size 295957 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_682d61505f84109d4ee8+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_682d61505f84109d4ee8+24129607/model.neff index 674ee595f03ae230717331520a79834bd175d8ba..3feb97413d88d656506d60444ef3ad7cc6beaf84 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_682d61505f84109d4ee8+24129607/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_682d61505f84109d4ee8+24129607/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:419dc475ede583cf97c284612527688fb85752779ef36945a51da9f96bf2cd1d +oid sha256:069a9f7e8b5a964a42ea2a63eeb49d5f91bc7ad3c719ceca000a856c2285143f size 96881664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/model.neff index 19eb93a3e4b1f86be1cf5d83b4c08ad2278184c8..8ac3aa6fc96647edaf30019c7c3e309e1825eaf6 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_68dcd52f0ccb32584504+24129607/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:79b76a8716ef07579b94e882dc4bfd3c569860e25f374983e8ecdb0191a2d613 +oid sha256:c4a0679a4c53faef93dac15fbb16bfa557f58e1defa538f12df17745ea36b18b size 5223424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6f75af6a30babfcdd019+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_6f75af6a30babfcdd019+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6f75af6a30babfcdd019+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6f75af6a30babfcdd019+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_6f75af6a30babfcdd019+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6f75af6a30babfcdd019+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_6f75af6a30babfcdd019+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e6887fe6d72c31e33dca16aea68e9f1d508572cb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6f75af6a30babfcdd019+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:635244b46a2c44c27abc6001ec1aa8b610e50a18d6cbaeb483b6ffba745cadb6 +size 81516 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_6f75af6a30babfcdd019+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_6f75af6a30babfcdd019+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a1087283e6b03440319df546aca6a7bb93b08471 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_6f75af6a30babfcdd019+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586ba202665cba80c198053d13e47976ce4f8a15c28fbdf553586e8c56d70aa8 +size 267264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_833bb585fe5b0b130f37+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_833bb585fe5b0b130f37+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_833bb585fe5b0b130f37+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_833bb585fe5b0b130f37+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_833bb585fe5b0b130f37+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_833bb585fe5b0b130f37+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_833bb585fe5b0b130f37+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..27846074fdcb82c3a04bdc991b67f7ccd47fe2fa --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_833bb585fe5b0b130f37+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:167419b0c75579c95b0be519a753531e8e82602d6f6a8c9083f6bb6333a74b83 +size 90382 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_833bb585fe5b0b130f37+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_833bb585fe5b0b130f37+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1afb17d91c0e1afb68b53bdeead95eaca516f70a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_833bb585fe5b0b130f37+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c4f609a202d6d782c9d3e5e708f58d7466b43c85229ee127407686f8dc27297 +size 359424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_90390e7549d92b97c345+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_90390e7549d92b97c345+24129607/model.neff index f651022dc3040a08b6204698fe171610e474d8f9..df321e152a24cc3816b074d2aeac9bec7b76331d 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_90390e7549d92b97c345+24129607/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_90390e7549d92b97c345+24129607/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a0daf4da8adab3c0b5865740679cd4c0c72d19c0aa94dccc57f6da5d48839e51 +oid sha256:d6e45a60f784ba7390794b6f205163176c6ca03da0759d70392511c589f92c48 size 9473024 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_954404769badd1a9f817+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_954404769badd1a9f817+a02c3a36/model.neff index 814b0b4eb18ab8a2e6204964f64b19ca611162b1..c6316f5419f34fd342f220abe6c1634ef14b6fca 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_954404769badd1a9f817+a02c3a36/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_954404769badd1a9f817+a02c3a36/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:12f12524366415a3385fe3740f340d9bbc9c16fd397f6daf2c6dfcb7434b91ea +oid sha256:cecf5d714b53ef2932f727d5185a85bbc78ac68d1b93d17561782db7a84a9e8b size 2417664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_954404769badd1a9f817+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_954404769badd1a9f817+a02c3a36/wrapped_neff.hlo index 41f39ee0a7751152fd273265078aa5fa8820c248..d7a9d65dca5f94de4c6458a1ee659867b27e9173 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_954404769badd1a9f817+a02c3a36/wrapped_neff.hlo +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_954404769badd1a9f817+a02c3a36/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:30e7c0df55220513b7947be8f2c503c288dc68532748ed47e26c09566f54435f +oid sha256:6a250f3ee7e3279f384498e9d3238735700f721908e42b6dadfff1ed4b3c8239 size 2554832 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9a0e905d5e65f1efb152f143fe4d78385db0f8c0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8ed3a7af30ff497bf3aff279caf7ebba01abe920a8f32fc1d43ad70a6d42d3f +size 93425 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ba49d2e282677540fd6a44d99cba66f1ff3d3da4 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:debf2f445f2d91b3e81f6c561957e6da701f8d65a0b024362f96572ae01d281f +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3d89fcd47820fb14993805d6c3ba0a229b231cb1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_982078e41304be19b706+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02efe5da4c68467d9cc360f98fec2ae13a5d32bf0348dd70078941ef54c2ea20 +size 288898 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9f9007db4d17e6304d37+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9f9007db4d17e6304d37+24129607/model.neff index e9cd825c1883d1a8a1e52d391a3c3c5698446e2e..aff7f727669ce28818815adbf0551fac735838ed 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_9f9007db4d17e6304d37+24129607/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9f9007db4d17e6304d37+24129607/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8c529c90115ebe7145e01c9b005f6b51535f6098a74526fea010f6823973e99b +oid sha256:ffcfb99f9f1ba36ec425c2705ea0468686b78c8a9784066e20cb831aed4f5e7e size 12248064 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_a0f36ad51d6ea0dcdcbb+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_a0f36ad51d6ea0dcdcbb+24129607/model.neff index d0194dc065daa80ca5b940af9da01097e7e54d3b..fba945c99c3f55a1a404dda7aabd3fc9431ea2b4 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_a0f36ad51d6ea0dcdcbb+24129607/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_a0f36ad51d6ea0dcdcbb+24129607/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0c5ce4ad0d118a7625c8e4ac87af76d19f72cd57f0a4e156e36908d4e8f3c83d +oid sha256:1dfad88dded44abf213ec8d96d06594c888361b6e60c3df2af7cf59eb0b3ad5d size 5827584 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_a8fc2fc4fb9affdb3f34+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_a8fc2fc4fb9affdb3f34+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_a8fc2fc4fb9affdb3f34+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_a8fc2fc4fb9affdb3f34+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_a8fc2fc4fb9affdb3f34+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_a8fc2fc4fb9affdb3f34+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_a8fc2fc4fb9affdb3f34+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5775cb312c77a27a50fd184619cc77a58509f3e2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_a8fc2fc4fb9affdb3f34+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c9345a8bb967edd52fbc50aa196abd7bc0bf57d13ed08d31bad18a9d508c054 +size 392910 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_a8fc2fc4fb9affdb3f34+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_a8fc2fc4fb9affdb3f34+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..908f8a1116410e4d7ac2787b1281d665c2d01925 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_a8fc2fc4fb9affdb3f34+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:048cb04306b4c3bf3ef1cf3f5a1c6ee5e5acccd561f2a1820a6dd7af61fe6d68 +size 41626624 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_aa0c40e8632cc47ef550+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_aa0c40e8632cc47ef550+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_aa0c40e8632cc47ef550+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_aa0c40e8632cc47ef550+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_aa0c40e8632cc47ef550+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_aa0c40e8632cc47ef550+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_aa0c40e8632cc47ef550+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..84311613ed1b5d8453c9d3951ffaeaad7a2a0a77 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_aa0c40e8632cc47ef550+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb77460869c0ddc335ba996275900c00d7feb24c4a5a259af95cd10edae234ad +size 82772 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_aa0c40e8632cc47ef550+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_aa0c40e8632cc47ef550+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d175eb3c646edb2e59901e0077c028cd7c465dc6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_aa0c40e8632cc47ef550+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cdb1cc112745c708003f5471e792e2e337020deedf0687423bb22d0162cd810 +size 267264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bcbfbafeff377b2f5566+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_bcbfbafeff377b2f5566+a02c3a36/model.neff index cebb087d0eb6583d7d7b74954fd423a10af9e19a..81383be2dd8db4898cc335e47a302e9d2a8b24a4 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_bcbfbafeff377b2f5566+a02c3a36/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bcbfbafeff377b2f5566+a02c3a36/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8182ac1ce77047e9988d08414cb4d501647ae5e330d05427579ff4809e17c177 +oid sha256:c0f0db943bae305a68c80774a9fe26ed9f803348b9759982bd1bb945756f1787 size 1721344 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bcbfbafeff377b2f5566+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_bcbfbafeff377b2f5566+a02c3a36/wrapped_neff.hlo index 1eb10624158adbc291ef664506dcb892a0c0dfee..6154ef26974565b5fa8ad87c95bf7fa4a4c337ff 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_bcbfbafeff377b2f5566+a02c3a36/wrapped_neff.hlo +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bcbfbafeff377b2f5566+a02c3a36/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d647b453b48c25e6365291bcc24d360ce075c338a776de1588fefd0681f53ffb +oid sha256:c890850f31c43d590c8728eaa8097b04b52f04486c7c1b77efb67e947a11b328 size 1877650 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d12c75d4a55a1f29a67c+283df001/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_d12c75d4a55a1f29a67c+283df001/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..58fbf6b9366d9e28d7f19321e85acd4cd96c0614 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d12c75d4a55a1f29a67c+283df001/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d12c75d4a55a1f29a67c+283df001/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_d12c75d4a55a1f29a67c+283df001/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d12c75d4a55a1f29a67c+283df001/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_d12c75d4a55a1f29a67c+283df001/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bd6c5dc0d2fdfe20be8427817645687f659b8f36 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d12c75d4a55a1f29a67c+283df001/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7dc2328bcd74f31a28521edc69225b93c50143678e31d5fa49d480da8e4645 +size 97794 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d12c75d4a55a1f29a67c+283df001/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_d12c75d4a55a1f29a67c+283df001/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..db9a61ec2754323ee32c25390ece0d6f2a5a3004 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d12c75d4a55a1f29a67c+283df001/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c90cf80f09287116aefd1d77ef7ea52528f0ddd2e6b1fd9d7ea8464b77928ec9 +size 410624 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..57fac9aae75b84f85dff08aa7209d0def24bcc06 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f4a6e09f14b38a1ac74e900d600fe09e5ca3fbe1c2132c4f8e292ced22453a6 +size 865291 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..16be20755c09e6658c686efec098d0e462377968 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:790df002849d6ca576755ce6f33bc65f62ebffbfaaabd6164af828ee153409f8 +size 4967424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a2230a3e1a03aa90eaa1d481ba003021804970fa --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_d4b12c256e167655df02+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcd1389c27337f4d53fb2847871053a05393caa08bacc75278a0f872ef98107f +size 5133948 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..a7a40c022faf4beb0fb20246d9c1f9c8f32c6900 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b77cb4877256561d4ed203b0301061289d02c959 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef754d16b3e82aee5107d0a7fd0c7161d2e147bdd92f45baa8257134ee653eb6 +size 91833 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7a0c43b2ca4915f9b75e39938d61c10ebb577826 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:361e59022b7e709b6c5f88b5a15fbcaa9c77a1824f66879aaf0fbc1f83b74c5e +size 369664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a032e79974b30a8d1ebdd01e48e5aea203f16cf5 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e43fb6fc70d6ca48c81c+2dde74c7/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:911e9e986d71d6cc8d3868d91fd2f58501b68798b80fc7b9d515c2fd315d9ed8 +size 379225 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..27153f3e8773fa579a76b0e688b45e700c2714c0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d422cf1312c637124b44630251154b29d45c4dbbaa41c4d6bc53af9e4677223f +size 388429 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..81de4040e3f6a68fa065b4e7af59849774bff35c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f933585f9a633e59fe4ece9f5f4d9a86f1a6ce289abd0180f2b8e397f50abf3a +size 1936384 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..50d0e1490978a392fe41d64a53f201b81dd5e518 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_eab0a664432ada643aa8+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7490b7c71770dfd6efd79673a1cc0bdfd30a313ef7493dc2237e344a10bfcbf3 +size 2029297 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_eb36f973e5afaf932d84+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_eb36f973e5afaf932d84+a02c3a36/model.neff index 23dc668c82b6ffd8974a3764f6c1021ed5eda7bd..f16fb9a24463d53b7b503c4f53ee9fc7b2a71c3b 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_eb36f973e5afaf932d84+a02c3a36/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_eb36f973e5afaf932d84+a02c3a36/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1d19d4041e931d82413b85d1d48cb4098d5198f9e1a690331783e4d585518d68 +oid sha256:daa50c225710a6829ef2f0e3c1e4324f8ec72674cc6928d1201423de1b51b482 size 6759424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_eb36f973e5afaf932d84+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_eb36f973e5afaf932d84+a02c3a36/wrapped_neff.hlo index 1aa2c3adc8d97995bed762e829c10b093b729eb4..2466ad6f8964bb2d0026456d6977f291ce8d6fc9 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_eb36f973e5afaf932d84+a02c3a36/wrapped_neff.hlo +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_eb36f973e5afaf932d84+a02c3a36/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:aad429025acc513e456e196ea61db3068ed8595a0218594c02b0465c21bf403a +oid sha256:aabe48e3b479d5931aa6b6c2270733e726c6f54838c700f1d11c8ed518aad531 size 6925948 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ebab4b006fd93fdc9f5b+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ebab4b006fd93fdc9f5b+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ebab4b006fd93fdc9f5b+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ebab4b006fd93fdc9f5b+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ebab4b006fd93fdc9f5b+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ebab4b006fd93fdc9f5b+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ebab4b006fd93fdc9f5b+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f3db015845cbd0881016290d2f786a9405536138 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ebab4b006fd93fdc9f5b+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a42a79766caa96504c73e6408df9337f56988798c2f055dd5db56b9ac22473c +size 79552 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ebab4b006fd93fdc9f5b+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ebab4b006fd93fdc9f5b+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..943ec48654d1345336c67b5fd7f214073b0a1bdf --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ebab4b006fd93fdc9f5b+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0edf3b1cca13e3cfd49cf7a31cb94f254064ff9e1a748bd217ea31bbfec3fad3 +size 338944 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..2ad69cd01383a682715fed6c7faaf92a72533ca6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1c53d56b8553bcbd02baa7d92d8df9bfa2cde69b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd7b32223098a02834ecaddf6796f7ce5368e71063766f568fcac25c4afe050 +size 84807 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c90070311b5351f9aa3cc411fff388a737667724 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ecf84edc7dafa7cf47bc+6e4949b4/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:970168724305facf6604877b2fe3a6275a7ad171b1ae0a53b3738ea82da78efc +size 646144 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3370cbdef7ca31160808eea0d21fa3aeee228eea --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6413e5c53d8be274da5e0ec85af6c4b98681a6fc93d84f9308e07ced6e3a28d +size 678755 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e42943a9aa5761e0063c752f78f219025644a583 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4b7231e48802923ab8f7ffeb5c0e66bcd3320d2d528dc86c4e630ab744949b +size 533504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..379a488d7dc359166086b987559d6b4a350a6789 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f0c0b96c282628d572b0+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b3cff5f086187bf53e95651f652ae25c6a0ce5ebccfb1807f3ac19b025bd90c +size 553005 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f20c2d825c9eea3ef8d8+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_f20c2d825c9eea3ef8d8+a02c3a36/model.neff index c34323f4df86e8f5655230f2feb8a0c538755253..3feb93381330ae7a39f73eb4675270e9f0d89fb6 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_f20c2d825c9eea3ef8d8+a02c3a36/model.neff +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f20c2d825c9eea3ef8d8+a02c3a36/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fc83b3c776e9af35aafcb4b45af66cb75ba4dfeb0dc3c66ff571412d6000cc54 +oid sha256:2a86d7e4f0ee17fa765fa7f96c834982bcc574850fdb55b69fb75b5757a43cb0 size 5397504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f20c2d825c9eea3ef8d8+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_f20c2d825c9eea3ef8d8+a02c3a36/wrapped_neff.hlo index 5c46b403a3fde6d89ea255830bc12541902ec87f..f4b912ed4e55cb84ba8c82d82019ff75bb695a1a 100644 --- a/neuronxcc-2.21.33363.0+82129205/MODULE_f20c2d825c9eea3ef8d8+a02c3a36/wrapped_neff.hlo +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f20c2d825c9eea3ef8d8+a02c3a36/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5acace923c9fe687021857bedb9ac35690619dd0f21bcaef9c80ce9e9b527e52 +oid sha256:e442898a2c1f52e28a38a855473717df57346ad761f98d52d21cd68887c55980 size 5564028