diff --git a/.gitattributes b/.gitattributes index af0ac7849ab002f4000c569bdf4f35537f03fb64..1acf5bf579fc2effa667bbbcc5de22cc41ea1baa 100644 --- a/.gitattributes +++ b/.gitattributes @@ -5111,3 +5111,18 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_cbf256b61a3a1c5f1f7a+677eeb9d/model.neff neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.18209.0+043b1bf7/MODULE_f753c5295db2f87f81a1+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.18209.0+043b1bf7/MODULE_b29b6228ab434f989a80+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_607905c97e8a375ad8f1+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/79d6a2644c0fb994afba.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/79d6a2644c0fb994afba.json new file mode 100644 index 0000000000000000000000000000000000000000..c17ea8553c20d784d715838824cdaf8a63086014 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/79d6a2644c0fb994afba.json @@ -0,0 +1,58 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "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": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/19972825cc5b89209b02.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/19972825cc5b89209b02.json new file mode 100644 index 0000000000000000000000000000000000000000..d01f05b22ec785f59f533b7c5e467e0e9057ef70 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama/llamafactory/tiny-random-Llama-3/19972825cc5b89209b02.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "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": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama4_text/tiny-random/llama-4/4f6687486daab74bc033.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama4_text/tiny-random/llama-4/4f6687486daab74bc033.json new file mode 100644 index 0000000000000000000000000000000000000000..47e548f2be6e517dcaeb7219594b2b1f8b8dcfc8 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/llama4_text/tiny-random/llama-4/4f6687486daab74bc033.json @@ -0,0 +1,81 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "tiny-random/llama-4", + "_task": "text-generation", + "attention_bias": false, + "attention_chunk_size": 128, + "attention_dropout": 0.0, + "attn_scale": 0.1, + "attn_temperature_tuning": 4, + "cache_implementation": "hybrid", + "floor_scale": 8192, + "for_llm_compressor": false, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "interleave_moe_layer_step": 2, + "intermediate_size": 64, + "intermediate_size_mlp": 128, + "layer_types": [ + "chunked_attention", + "chunked_attention", + "chunked_attention", + "full_attention" + ], + "max_position_embeddings": 1048576, + "model_type": "llama4_text", + "moe_layers": [ + 1, + 3 + ], + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "tiny-random/llama-4", + "checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/mixtral/dacorvo/Mixtral-tiny/cb323601e0aa10c70f9c.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/mixtral/dacorvo/Mixtral-tiny/cb323601e0aa10c70f9c.json new file mode 100644 index 0000000000000000000000000000000000000000..72a746b4455b0a13e05fb0b6bc81c1b6d554268b --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/mixtral/dacorvo/Mixtral-tiny/cb323601e0aa10c70f9c.json @@ -0,0 +1,58 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.0.dev0", + "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": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/phi3/yujiepan/phi-4-tiny-random/5ff5bff574e21c1ee9b0.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/phi3/yujiepan/phi-4-tiny-random/5ff5bff574e21c1ee9b0.json new file mode 100644 index 0000000000000000000000000000000000000000..5a3bcfdaea190e8896601ebd8e71e1340c16f6d8 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/phi3/yujiepan/phi-4-tiny-random/5ff5bff574e21c1ee9b0.json @@ -0,0 +1,59 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/eac4336716688c682e8c.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/eac4336716688c682e8c.json new file mode 100644 index 0000000000000000000000000000000000000000..565a2f7f6543ae28a8fa4291f9e6f57df593a892 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/eac4336716688c682e8c.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "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-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/a6f02f34734d58205a85.json b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/a6f02f34734d58205a85.json new file mode 100644 index 0000000000000000000000000000000000000000..bc27517a928ad103d8b4272d8c70498714b8bf9f --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.0.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/a6f02f34734d58205a85.json @@ -0,0 +1,65 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "_task": "text-generation", + "architectures": [ + "Qwen3MoeForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "decoder_sparse_step": 2, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 128, + "max_position_embeddings": 40960, + "max_window_layers": 1, + "mlp_only_layers": [], + "model_type": "qwen3_moe", + "moe_intermediate_size": 128, + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.18209.0+043b1bf7", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.0.dev0", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "norm_topk_prob": true, + "num_attention_heads": 2, + "num_experts": 8, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "output_router_logits": false, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bdec493f40832baa10fc555004c701f519155d81 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23fff2222c80e609ede15fd7899202e3dcfec823c20d5693d35391a2f351de45 +size 82753 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cafe1cac829756a87728eee6b9d78c97155d9a92 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d5794197cc1c440a87ceb511f5c1be579e938e1804d40a69b8ef1de5520571 +size 277504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c8351239656605d9cc3c897b47e410351ce9da01 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_10d60f8fad55e1974521+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f620b1d7b37b2896c0fbf86202063926fb1a18d68cc3d20eecca1c10090bc877 +size 285854 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..be8215e4db02a98e7c7d9a9b026367f5b42a91ea --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/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-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..21f1b6663379fb7b1214e70d18510e19187eef80 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f08146dd5aa669a7a5ede165f2203a5a1d493ea0f8ffbada902aabcc925731 +size 246784 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..980e2e2fa11312505d6c5afa7bf2b467cc9a30db --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_13aa568fe38435861b30+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b9cd23cd69de2f90c806808492a0ba59374d106b61dc84a5da694f7eaa6544e +size 255104 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..23d9ed7b13907bbf64caba64247d36231561e554 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7da2288fa0065f5732bfc84bd11a1f2628bca9861071457605d3d1e2fe916a +size 90382 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b3d93dbdd2f24386114630df0dd742f6999f555a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e1261ac026ac7064c12+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c0b29e79eb8a89f0c7bd1af01320c2b64606cb55036efd8000daf55aad89acc +size 359424 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fe8375133f6593b390bfab95fa2f59a13fc1740c --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a30064c095e66d36b82f0f119f8c90e2d8f9250729a0fc969fdda597569500 +size 86123 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5179abd1f14e70aba29c809d736b9e9e99228984 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_585fd41ddb2ec3219380+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3b8f03e2bb9f3ae70c214bc950dea144994836574886708e96d52119507dd07 +size 257024 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_607905c97e8a375ad8f1+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_607905c97e8a375ad8f1+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_607905c97e8a375ad8f1+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_607905c97e8a375ad8f1+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_607905c97e8a375ad8f1+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_607905c97e8a375ad8f1+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_607905c97e8a375ad8f1+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3bc3f31495433a1c655de36b2b057c05dcd1e241 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_607905c97e8a375ad8f1+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24624bc45be46654efb5eb289cc62aae8e0818687d6378e93a7244553928e7d7 +size 83504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_607905c97e8a375ad8f1+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_607905c97e8a375ad8f1+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..86c7c778a8a47247adc5e252734eb9705415a758 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_607905c97e8a375ad8f1+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1def2aa1595ee48cf7ddf6dfa4a7d2c7ffa27f4a0ec104c45bce6bd29fc6238f +size 328704 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f9aac85f572373187ed5932ede47f59a7a91323f --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/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-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6da6e44e0e0803b7e142d1ee0acbb3244944ac69 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5fc99e7ec1985f69435ca23e19dce386cbd8c525fe8d2312b9868c81fae5716 +size 543744 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..43c5c589de99eb4f29e13bbdc8e0f741693336e5 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_a6ac71f9922f4f01abf5+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6d898c25998f845a5baa83037e9802318d822e4e70a3c4ecdfc708db5d74f19 +size 563380 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..71a45b2e71496cd9a4651b67356cd1c41ba41ef9 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db7ebbb9e2aa4d3c3d4667f098e18faa9ed0a231c9831e73c8118bfad21264ad +size 91147 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d8b816dbdba4e1362932aa0c572b8c652a48cf21 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ea59696b130915819c0ac02b7eb02b02772c1e64866eb6aa4ebf4398a3c5d1 +size 277504 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ad0e6a95c65d7f919c13c281597b7ae7e523ef4a --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_c0a2583211556c96a6a3+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:557828feb4ce2b868dc358d87c8adebb3fe5c6597abdd6a1f8788c3d40aa9f1c +size 289031 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7c28c36e23a61e75b8fe7b240f11da8c4476a486 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:833b82cfd5de929b110eae7f2597028fd2aba27feb903dc4a6389317ec3d4c73 +size 85236 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..487cd494702f7c405766d6929d1898ae0de37c61 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7107fd17fab62ea880b3fc40e65d9322170bdc32b2f0b47ee90bd468ca184858 +size 216064 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a67bdaf59d696be035e31a5e8d1cbf530d5dd553 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_e51f8e75d0439314e217+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38beb98efa2cceb12ac6bf7c5384bf134a28598bab758ba4a38b5ee0cab4d21b +size 224412 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b4b13b96059bc6850a627971631d2df47b7bba77 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb9d3c9ec74f1ca339872d2af14bf39e9ac08891d8cbb125730abe59da953421 +size 82772 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..140d8f190ed99496070b491d5fd6466d547785da --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fc37bb64f7e86324075c+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c40c4e13ba0555414340c531f5a55db4a6134efed627548ed0bf43d3f6680170 +size 267264 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/compile_flags.json b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.done b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9a666fb7edd787d28d1b5deb6caeb621029c656e --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff6a94245c9bea72d2373d0729aacead4e155f2103dfcf42ae314f7840755a60 +size 694128 diff --git a/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4c1b03a42303eba6b59580bac93c18af9891e81d --- /dev/null +++ b/neuronxcc-2.21.18209.0+043b1bf7/MODULE_fef991cead1748c4d101+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:740c162fc801efa2bd5a4dff99c3c1ea44415e0a353049f05eb8313ff86d1797 +size 625664