diff --git a/.gitattributes b/.gitattributes index da852e9fdab84861258d02718f0c66fa1b82671c..a6e20e284e6989d69d501e7188b842d38dc7533a 100644 --- a/.gitattributes +++ b/.gitattributes @@ -5739,3 +5739,30 @@ neuronxcc-2.21.33363.0+82129205/MODULE_fd44e24d672157f0bc14+a02c3a36/model.neff neuronxcc-2.21.33363.0+82129205/MODULE_fd44e24d672157f0bc14+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_ecafd5c328f53085c3ac+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_ecafd5c328f53085c3ac+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/822b61c3a021502bf290.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/822b61c3a021502bf290.json new file mode 100644 index 0000000000000000000000000000000000000000..953b4852a148dbf9c10eca4aeb1d5038a06e96a3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/822b61c3a021502bf290.json @@ -0,0 +1,59 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "dtype": "float32", + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama/llamafactory/tiny-random-Llama-3/9587f75fe03d32199424.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama/llamafactory/tiny-random-Llama-3/9587f75fe03d32199424.json new file mode 100644 index 0000000000000000000000000000000000000000..5c414e0515e4652370454d3942e3ee7b2bc1a2d8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama/llamafactory/tiny-random-Llama-3/9587f75fe03d32199424.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama4_text/tiny-random/llama-4/663adc121ad6f0bf6c41.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama4_text/tiny-random/llama-4/663adc121ad6f0bf6c41.json new file mode 100644 index 0000000000000000000000000000000000000000..4c08759982b036f55f8dde88b082e3ea0236d4ac --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/llama4_text/tiny-random/llama-4/663adc121ad6f0bf6c41.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "tiny-random/llama-4", + "_task": "text-generation", + "attention_bias": false, + "attention_chunk_size": 128, + "attention_dropout": 0.0, + "attn_scale": 0.1, + "attn_temperature_tuning": 4, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "floor_scale": 8192, + "for_llm_compressor": false, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "interleave_moe_layer_step": 2, + "intermediate_size": 64, + "intermediate_size_mlp": 128, + "layer_types": [ + "chunked_attention", + "chunked_attention", + "chunked_attention", + "full_attention" + ], + "max_position_embeddings": 1048576, + "model_type": "llama4_text", + "moe_layers": [ + 1, + 3 + ], + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "tiny-random/llama-4", + "checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layers": [ + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 1, + "num_experts_per_tok": 1, + "num_hidden_layers": 4, + "num_key_value_heads": 1, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "tie_word_embeddings": true, + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 202048 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/mixtral/dacorvo/Mixtral-tiny/2115b9307dea032bae46.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/mixtral/dacorvo/Mixtral-tiny/2115b9307dea032bae46.json new file mode 100644 index 0000000000000000000000000000000000000000..2618688721dbf26e95a54b4080c355d4a2d418a2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/mixtral/dacorvo/Mixtral-tiny/2115b9307dea032bae46.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": "0.4.3.dev3", + "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/0.4.3.dev3/mixtral/dacorvo/Mixtral-tiny/6c78d4e7067fedb8c6d8.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/mixtral/dacorvo/Mixtral-tiny/6c78d4e7067fedb8c6d8.json new file mode 100644 index 0000000000000000000000000000000000000000..6531218cdfc5fcfd5f3ea2c92614d4d5a0e1ccb5 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/mixtral/dacorvo/Mixtral-tiny/6c78d4e7067fedb8c6d8.json @@ -0,0 +1,59 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.3.dev3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/phi3/yujiepan/phi-4-tiny-random/9830c1de6c2e8faed0c8.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/phi3/yujiepan/phi-4-tiny-random/9830c1de6c2e8faed0c8.json new file mode 100644 index 0000000000000000000000000000000000000000..6eb10d1cf9056c8c5895ea3b4365ba6c8d7a40ab --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/phi3/yujiepan/phi-4-tiny-random/9830c1de6c2e8faed0c8.json @@ -0,0 +1,60 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "dtype": "bfloat16", + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/d2ffa119e8a8f246f65e.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/d2ffa119e8a8f246f65e.json new file mode 100644 index 0000000000000000000000000000000000000000..5ffa20032c4158f27561ddc4b2d5ceed0ad2a415 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/qwen2/yujiepan/qwen2.5-128k-tiny-random/d2ffa119e8a8f246f65e.json @@ -0,0 +1,65 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/35684b74302809c36482.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/35684b74302809c36482.json new file mode 100644 index 0000000000000000000000000000000000000000..f9c23f3f9471ee957c95e9178095bf9a849cc358 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/35684b74302809c36482.json @@ -0,0 +1,66 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "_task": "text-generation", + "architectures": [ + "Qwen3MoeForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "decoder_sparse_step": 2, + "dtype": "float32", + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 128, + "max_position_embeddings": 40960, + "max_window_layers": 1, + "mlp_only_layers": [], + "model_type": "qwen3_moe", + "moe_intermediate_size": 128, + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "norm_topk_prob": true, + "num_attention_heads": 2, + "num_experts": 8, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "output_router_logits": false, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/smollm3/HuggingFaceTB/SmolLM3-3B/9a47a3a9f135594c847d.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/smollm3/HuggingFaceTB/SmolLM3-3B/9a47a3a9f135594c847d.json new file mode 100644 index 0000000000000000000000000000000000000000..7f62300262e7600b998c6e2f2367f65a901d70ff --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev3/smollm3/HuggingFaceTB/SmolLM3-3B/9a47a3a9f135594c847d.json @@ -0,0 +1,135 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev3", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9b76c8559ff823b3cfa98e5db0d486cd2c6d8b90 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "-O1", "--lnc=1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--internal-enable-dge-levels=vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..910fb21ca78c9b5103637fe5ba28e6ecd2162ea9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a7be97d2012aa41b5f56bf5bf86357a0dae77fd27821fa3e0737aba2fe5521e +size 97794 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..887c66d40f263958cddbd9115ba918fa59003dbf --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_01328268a19023ed0f24+f8e6d902/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff6c1f2a8f76328f3ffd5cd9cbb7ad62552ac54af96be0b68b754f3e79f2c6e +size 410624 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+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_137f98143cdeb07dab7d+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a1b84944bd41f36506ece4afd68096d3271335d8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c3af8ccf676bfc9035f2832be64f2c64d4fb71e544ed4a55e45823227860db7 +size 863008 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..97145496307759fbce4f0e9df7fb9b2fc8e29687 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db55af8b240e22fd8c6947d7fcf77d9db9951d7a854022ea5e1bcdc69b2e9e8c +size 5039104 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1fd2fea9c23be1fc4e3259abc8b7f7fc32c29fbc --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_137f98143cdeb07dab7d+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d12b0bd6935e99c2317788a98c688f30bccd28bc264c3e8886100cb709dfc68 +size 5205771 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+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_1d4bedf0c37a53b47737+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3b28dfdd4b213537b2dea5c6bcc967e9c9762156 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d61ac2165fde7772e8d3035b0f89b50beec5e0d305548cbacc624eefa9452d3 +size 82753 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..775f26b82b7b93dbbc4a2485d6d80f45279f1955 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46ba68c0aadd4763eb642e9c19a4cc1d146805bf9f246e0e641bb2e390e292dc +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..89b50330d84cc96c864680444f956454d55a1fd9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_1d4bedf0c37a53b47737+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bc467900543a33abd00bdb0231e3abf9d59ce0ee85e2dc7dda90fe7684a866d +size 285854 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a151e0db66c9936e4eb4c88ec4b2d7c748e10e2d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b6486a12378501e2484cf81b9f6885eabca76a7d817e3e2041c1736bac16d7 +size 82772 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cb31650fc005c2de4ee977a846b33ff3a5fb7cb3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_2672b897bf6327bea9e4+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c65b6b3a5f7c34ae231694981cf76347fb89393c25990695cd4f921f3d243e3 +size 267264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5a228a7a4cc7c7df9e8b4887d22dcd862c2f60f3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "-O1", "--lnc=1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--internal-enable-dge-levels=vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..034b3692dbedbb2c3dc57e51f7235a13ff251cc9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061213de218a73c7d090fd093562e9c08718438de6287e6a332372c8f7906930 +size 70276 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0f74f5d3bf8893db7c6f48efe0d992d770b23b52 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e64780612d32c890d4c7d297248e064089d8ef4f8a9f9d5a9a1c169c6421ec29 +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0d9c94e8f0f71749a41037666f977c6ef332a510 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+bafdbdde/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54d1ec39550a8bb2e6e192265b3fed7b4a12065b0c8d82456a918f7a5be1e4ae +size 289571 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+da15b874/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+da15b874/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..c3fb8c073852fb04e7ae88fd2592978716b60eeb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+da15b874/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "-O1--lnc=1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--internal-enable-dge-levels=vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+da15b874/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+da15b874/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2117dab3e3ed8caad749b8256ab430c591d3b72a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+da15b874/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-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+da15b874/model.log b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+da15b874/model.log new file mode 100644 index 0000000000000000000000000000000000000000..f25bdb6bbd823e002119a606100d83dd796b7d08 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_31e31b6f47afb89b553b+da15b874/model.log @@ -0,0 +1,5 @@ +Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/token_generation/_tp0_bk0/model.MODULE_31e31b6f47afb89b553b+da15b874.hlo_module.pb', '--output', '/tmp/nxd_model/token_generation/_tp0_bk0/model.MODULE_31e31b6f47afb89b553b+da15b874.neff', '--target=trn1', '--auto-cast=none', '--model-type=transformer', '--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2', '-O1--lnc=1', '--enable-saturate-infinity', '--enable-mixed-precision-accumulation', '--internal-enable-dge-levels=vector_dynamic_offsets', '--internal-hlo2tensorizer-options=--verify-hlo=true', '--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt', '--enable-internal-neff-wrapper', '--verbose=35']: neuronx-cc compile: argument --optlevel/-O: invalid choice: 1--lnc=1 (choose from 1, 2, 3) +usage: neuronx-cc compile --framework {XLA} --target {trn1,inf2,trn1n,trn2,trn2n} [--logical-nc-config {1,2}] [--enable-fast-loading-neuron-binaries] [--enable-fast-context-switch] + [--auto-cast ] [--auto-cast-type {fp16,bf16,tf32,fp8_e4m3}] [--output ] [--optlevel {1,2,3}] [--help] + [--model-type {transformer,unet-inference,generic}] [--distribution-strategy {fsdp,nemo,llm-training,generic}] [--enable-dge] + [--verbose {debug|info|warning|user|off}] [--logfile ] [--logfile-verbose {debug|info|warning|user}] diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+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_4247663625e2eaeb4fab+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fde266f24753492d595dbb2d9fbc88c2a3fa7f78 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c908a5ddbf03970315b73168cfd6d3b14f39328f2b700c5d1e9c4144323034 +size 91147 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..971ceabb2f757196d864f73d5bfed5da56e21f81 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad22d482746dc393d9343d9b7855e8da2352e083b60b8627da2f1291a7ba960f +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a7c5e47b3cb90370430f202ccedb2dc411e99f54 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_4247663625e2eaeb4fab+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d64528a98e0b9f958208d4b0fa5e55a5cd5026e6c04a9d2d5ee1e01bfcec393 +size 289031 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..96b0b9d0aac667bdfb4b89f452b77fd0695d787e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76c10df9f9fadac3ce5fee74c4470b2cdade440cf97718b4545a4e3de7fc54aa +size 694128 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ea50519fb23dc2dea11f1fddc04774675adc6431 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_5960bdedd7549bfacf7a+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f816d25661f62f7f838c0800cb426bb2a2a552c974bc9c93181f83780ef36d8 +size 625664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5a228a7a4cc7c7df9e8b4887d22dcd862c2f60f3 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "-O1", "--lnc=1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--internal-enable-dge-levels=vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..727fe2caac58854e2f659732c11b6b5473ac4505 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6596d3769509c9146ae4a3975d1c70c2eb236f1527bf8cab5cf9306c4300289f +size 89555 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..32fa287e2e4418c7c9002af355c7461d85f9f4bb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e6305d96ffce7a09ffe9fbe739daef69c503eceaa33e7181c52bb69f8e669d +size 369664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..cd4155aa997fa356903eb273926c2869086276d2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+bafdbdde/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0093375c250feaa10fa7e89832496ea173e63ca7c802ed01d0f81aca0be48912 +size 379362 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+da15b874/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+da15b874/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..c3fb8c073852fb04e7ae88fd2592978716b60eeb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+da15b874/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "-O1--lnc=1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--internal-enable-dge-levels=vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+da15b874/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+da15b874/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..727fe2caac58854e2f659732c11b6b5473ac4505 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+da15b874/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6596d3769509c9146ae4a3975d1c70c2eb236f1527bf8cab5cf9306c4300289f +size 89555 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+da15b874/model.log b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+da15b874/model.log new file mode 100644 index 0000000000000000000000000000000000000000..f5a382588428b9da47b14342f226d3a77768d5eb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_73021bd2bcd85d0ae281+da15b874/model.log @@ -0,0 +1,5 @@ +Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/token_generation/_tp0_bk0/model.MODULE_73021bd2bcd85d0ae281+da15b874.hlo_module.pb', '--output', '/tmp/nxd_model/token_generation/_tp0_bk0/model.MODULE_73021bd2bcd85d0ae281+da15b874.neff', '--target=trn1', '--auto-cast=none', '--model-type=transformer', '--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2', '-O1--lnc=1', '--enable-saturate-infinity', '--enable-mixed-precision-accumulation', '--internal-enable-dge-levels=vector_dynamic_offsets', '--internal-hlo2tensorizer-options=--verify-hlo=true', '--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt', '--enable-internal-neff-wrapper', '--verbose=35']: neuronx-cc compile: argument --optlevel/-O: invalid choice: 1--lnc=1 (choose from 1, 2, 3) +usage: neuronx-cc compile --framework {XLA} --target {trn1,inf2,trn1n,trn2,trn2n} [--logical-nc-config {1,2}] [--enable-fast-loading-neuron-binaries] [--enable-fast-context-switch] + [--auto-cast ] [--auto-cast-type {fp16,bf16,tf32,fp8_e4m3}] [--output ] [--optlevel {1,2,3}] [--help] + [--model-type {transformer,unet-inference,generic}] [--distribution-strategy {fsdp,nemo,llm-training,generic}] [--enable-dge] + [--verbose {debug|info|warning|user|off}] [--logfile ] [--logfile-verbose {debug|info|warning|user}] diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+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_8f63e2da128b2efd447e+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..be8215e4db02a98e7c7d9a9b026367f5b42a91ea --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ed0858162f8fc2c58bc4c23d0925dbeda5897dae0889f87758206676394f4e +size 81843 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..99c7d655cddbc1912973cc04fe157dafa9859f50 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9cd8bc061981baceefabdaa5ca287e1e48f591b569eaeb4ce05b5fa636e1d8c +size 246784 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..21acafea44333656b4673e656ada71c9c58748d8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8f63e2da128b2efd447e+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee6b0533aa9da5b3c8273ba009014b88e974e7ede3f77b3afd82c665bb13389 +size 255104 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..78b5cc8665d05cb8f7c7db976481945ecb1bb354 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18debfa97c09c988925a1aaaa8b9c0f8f4cd2b025cbeb08d7ef3bfc4ec9a865f +size 509380 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c410473e6bd09ffec233ea46ca33324c0cddd158 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9bc06d024b9ce47e5f56+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:693b83d4f6771c87b8387a60f6b448121dd1c389524ed32f8e1e427f5e1aaacd +size 41585664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9b76c8559ff823b3cfa98e5db0d486cd2c6d8b90 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "-O1", "--lnc=1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--internal-enable-dge-levels=vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..41b34a9f77fe802ab1aff5378e888ec8b792fe46 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75aa20ad640c40319a599827de7275b4989637937e69b4c859e53b00a8bc9b3f +size 84807 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c64a91bd3edecb0e67429d35330d7e0c16e8b16f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_9d52760610a001af812a+f8e6d902/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e884a06795f3dbe019d77779bf01db493d426ba8ec0ef1f7465464fa9d361a12 +size 646144 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b928c9a2f728815784f9ace1a24d0c5aa729fc33 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f1d26ab78f5dcdc49abcc6e752412007c6cc8d21445bfa1a0078c7ec9c8d610 +size 761066 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..10acb8f92e98f282b39955520db7d6e3a2c0ba7d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ad7c8ac474ec4bdeae52+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d76b90151b45d3386d3374c30a864e389e6223be192d8cc711f967ba42673f +size 12504064 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+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_b0d91b1607c7df83fc7f+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7e9d26beec0f977cbffadaa07e072b813d5c384c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3d672c3848f8e54a8c124e63aef9b6c46e8501de480a8030d8cf09134de5c5b +size 418223 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..25ea89c3f2b0853afe69b2448b7885064f574ce7 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f47aecd094b3b8cb82df7c967651758b567bcccf097b29eba650557745c3e60e +size 3093504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..22e5f487b5c845a3f3f69935816d6a80430a4d35 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b0d91b1607c7df83fc7f+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:265f665976eca094764e237dff906e3564a680b7bd52746a2d9e2c0bdcb992b7 +size 3167748 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2490c1fe7fef9d747c24ae4daa81eb948a183fc1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba30bac1303e4d846c40c65f8e4d8a644794b6964038372ff73e155714762bdc +size 83504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3612ae764be895e726e58f5ca7f02b1d988c5d24 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c26856b929d58ebddc23+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ba77eb824772e994518cb8cae28e31fdb69af6393a0fac70a28fb9d3d5f6d51 +size 328704 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bc9cfc879012a007d2e0baa000a3b24812f240e8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:488ac1572ce8e1b1ff2d6254afaf39e40218d5b117f226473da52d9ac7929c91 +size 81516 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..340e7cce3851d2abdb5ee14285f6645d1dbe5088 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cb6b880fc977b7ae4bda+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50269c93a4f89b9cfe1a88721a71f9262fee57c37777da36ef0127d536e4c0ee +size 267264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+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_cbda8a59038c9c5ffc17+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..64028cc78541c1833466a343e251d2e19d025203 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e70386c0d4c7acaf312dfe4908f119fe46d817ab3d82394d549c5ed84707d551 +size 80382 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9f774c385f737da46e6a63322211a66d9bb89832 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a582473554f7c0b0ebb4a0e019ca598c2fa03deecb64203e0d069bbbe3f4ec90 +size 216064 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..08f24903a066f359551b07369d33b83b641effb7 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cbda8a59038c9c5ffc17+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b553f35aae2cec12206bcc2a8f472dfbef4f963b3c195462d31f6246f0eaed +size 224412 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c8e158507cef0abd568e18481672a47be580132b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbee7375c8021657bbb337b137190e79d46ae75cf40db4df9597daa481da9e5c +size 90382 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..638d8a898464a976db0604cd8306a7f0af1c1262 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_e899b698a237c528bb16+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30550222149aae50b173e32adaeec5e384280fdc8f3e65aa0d0a6c4ee049106d +size 359424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+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_fcaa5220788f46dccc4f+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f9aac85f572373187ed5932ede47f59a7a91323f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0902b9467e36affd529236be99c466bb326eb59e56e6b6414b2bde17d7913ac8 +size 676474 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ca2edeaff7a5a773737bb772667d191baf73e8b1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a52f43c55d8c3cf96000b769db5b872074d525da0914de6733490c2db2b389d7 +size 543744 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..feb6b50c11b4c69e433bda628b73c5ad8fc4fab1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fcaa5220788f46dccc4f+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a388ff10768fbb20c3c5dcc430ea96cc9974eeddebc8b8cd62a491f1328eab55 +size 563380