diff --git a/.gitattributes b/.gitattributes index 5e33ff3f1fe2adc3f322ffeee1bd55d9b7948669..77ca4d806fdbc05ed48be1e2216bc9334672ee98 100644 --- a/.gitattributes +++ b/.gitattributes @@ -5578,3 +5578,34 @@ neuronxcc-2.21.33363.0+82129205/MODULE_e7235732a32fbac73c61+24129607/model.neff neuronxcc-2.21.33363.0+82129205/MODULE_0efef6046521fed2cd76+24129607/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_7eab73a0314d91031486+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.21.33363.0+82129205/MODULE_7eab73a0314d91031486+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_3e60ddce17a65ac4ee68+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_410ef55a3aca5cd80fc8+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_733744f5680ca67f7ff9+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_75329916c4da1120954c+6e4949b4/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_7c590ab98f45f8a8dd15+283df001/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_8eedc4b0995b3a9b6f52+677eeb9d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_944763b36d810f4af582+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c30a746238d3804f9626+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_c4737893663f5ff66b53+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_ccd99eedd56f698b9cb3+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_f52fe8e88daf6dc9619a+24129607/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+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.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/97050f455a3dc7373088.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/97050f455a3dc7373088.json new file mode 100644 index 0000000000000000000000000000000000000000..6dd5ef3412c14fcebb3cfa3304eaa73cdfe664de --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/97050f455a3dc7373088.json @@ -0,0 +1,58 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "dtype": "float32", + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/llama/llamafactory/tiny-random-Llama-3/96f6efa1fe88a6a9d908.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/llama/llamafactory/tiny-random-Llama-3/96f6efa1fe88a6a9d908.json new file mode 100644 index 0000000000000000000000000000000000000000..d0996bfc053115757715fee53ce30523a45b2536 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/llama/llamafactory/tiny-random-Llama-3/96f6efa1fe88a6a9d908.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/llama/unsloth/Llama-3.2-1B-Instruct/7aa61ecee499b16d2a75.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/llama/unsloth/Llama-3.2-1B-Instruct/7aa61ecee499b16d2a75.json new file mode 100644 index 0000000000000000000000000000000000000000..365649267e500b737c017af64f6bc6f2e494e6e0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/llama/unsloth/Llama-3.2-1B-Instruct/7aa61ecee499b16d2a75.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.3.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 4096, + "speculation_length": 5, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/llama4_text/tiny-random/llama-4/c108820859fb593e97ef.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/llama4_text/tiny-random/llama-4/c108820859fb593e97ef.json new file mode 100644 index 0000000000000000000000000000000000000000..f1470855a1edbe2b92227af8b941b9cbd6703241 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/llama4_text/tiny-random/llama-4/c108820859fb593e97ef.json @@ -0,0 +1,81 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "tiny-random/llama-4", + "_task": "text-generation", + "attention_bias": false, + "attention_chunk_size": 128, + "attention_dropout": 0.0, + "attn_scale": 0.1, + "attn_temperature_tuning": 4, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "floor_scale": 8192, + "for_llm_compressor": false, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "interleave_moe_layer_step": 2, + "intermediate_size": 64, + "intermediate_size_mlp": 128, + "layer_types": [ + "chunked_attention", + "chunked_attention", + "chunked_attention", + "full_attention" + ], + "max_position_embeddings": 1048576, + "model_type": "llama4_text", + "moe_layers": [ + 1, + 3 + ], + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "tiny-random/llama-4", + "checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layers": [ + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 1, + "num_experts_per_tok": 1, + "num_hidden_layers": 4, + "num_key_value_heads": 1, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "tie_word_embeddings": true, + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 202048 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/mixtral/dacorvo/Mixtral-tiny/d27d3b7e6c219c39e0c6.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/mixtral/dacorvo/Mixtral-tiny/d27d3b7e6c219c39e0c6.json new file mode 100644 index 0000000000000000000000000000000000000000..82f80e95be27ce7759b523edefee82097dcb4255 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/mixtral/dacorvo/Mixtral-tiny/d27d3b7e6c219c39e0c6.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.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/phi3/yujiepan/phi-4-tiny-random/3211e8079a23f7cca17d.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/phi3/yujiepan/phi-4-tiny-random/3211e8079a23f7cca17d.json new file mode 100644 index 0000000000000000000000000000000000000000..d8352cff7bfd0fdcec509396f70dca23989f3f5d --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/phi3/yujiepan/phi-4-tiny-random/3211e8079a23f7cca17d.json @@ -0,0 +1,59 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "dtype": "bfloat16", + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/55d828b008dd8415c97f.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/55d828b008dd8415c97f.json new file mode 100644 index 0000000000000000000000000000000000000000..2f615d2a2f550c895e67a499fdeab14d6b68487f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/55d828b008dd8415c97f.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/c7cf2a4267f41d17facc.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/c7cf2a4267f41d17facc.json new file mode 100644 index 0000000000000000000000000000000000000000..d561d0d05134fb39e866ff52434c62674e2f20b0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/c7cf2a4267f41d17facc.json @@ -0,0 +1,65 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "_task": "text-generation", + "architectures": [ + "Qwen3MoeForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "decoder_sparse_step": 2, + "dtype": "float32", + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 128, + "max_position_embeddings": 40960, + "max_window_layers": 1, + "mlp_only_layers": [], + "model_type": "qwen3_moe", + "moe_intermediate_size": 128, + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "norm_topk_prob": true, + "num_attention_heads": 2, + "num_experts": 8, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "output_router_logits": false, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/smollm3/HuggingFaceTB/SmolLM3-3B/7a707f573aa21c74857f.json b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/smollm3/HuggingFaceTB/SmolLM3-3B/7a707f573aa21c74857f.json new file mode 100644 index 0000000000000000000000000000000000000000..f3e02df5420d3fdcd64eb1abcd907e7d897dcdbd --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.3.dev2/smollm3/HuggingFaceTB/SmolLM3-3B/7a707f573aa21c74857f.json @@ -0,0 +1,134 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.21.33363.0+82129205", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.3.dev2", + "output_logits": false, + "pp_degree": 1, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+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_0cdc152aff6a7cbf36f6+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fde266f24753492d595dbb2d9fbc88c2a3fa7f78 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+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_0cdc152aff6a7cbf36f6+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5ba2c3da07b97a350a710a7184b984d562c0ad63 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9022b1945dd2e7ef8b45eadbd2dc20dfb74b1add40ec7aad07e57bad2a500b25 +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e58784de0e96cbf62047851c390077bb0dca0874 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_0cdc152aff6a7cbf36f6+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95021fb9ec8e64ac096a6e7f993b7f066b620b290e2aa82be5be7695581db3f0 +size 289031 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3e60ddce17a65ac4ee68+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_3e60ddce17a65ac4ee68+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3e60ddce17a65ac4ee68+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_3e60ddce17a65ac4ee68+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_3e60ddce17a65ac4ee68+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3e60ddce17a65ac4ee68+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_3e60ddce17a65ac4ee68+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..173c0d402fe6d36863b25f882e44a2605ea6cc78 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3e60ddce17a65ac4ee68+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0521dc743c5def43a14f8f5399d0d10d714339f5aa52b30c5fbbb62c44e4c3fd +size 82772 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_3e60ddce17a65ac4ee68+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_3e60ddce17a65ac4ee68+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..14a6e249b3da640b5c72105d1d52a9e199c37612 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_3e60ddce17a65ac4ee68+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8abb284b0febb6fcb1a834297f3cfe6ddb22317e98d1faeeac315f7100acaf1 +size 267264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_410ef55a3aca5cd80fc8+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_410ef55a3aca5cd80fc8+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_410ef55a3aca5cd80fc8+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_410ef55a3aca5cd80fc8+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_410ef55a3aca5cd80fc8+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_410ef55a3aca5cd80fc8+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_410ef55a3aca5cd80fc8+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ca75a736a8da056a5f129d886ef1c22e930698eb --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_410ef55a3aca5cd80fc8+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0765bfed3b5fcacd120c7727039d8c0a03d993171191b174f937661338915219 +size 81516 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_410ef55a3aca5cd80fc8+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_410ef55a3aca5cd80fc8+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1bf30efb01576b9f3f24a262a0d54c3f6c6281e7 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_410ef55a3aca5cd80fc8+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c0279c42f9c2639ac0658462cee6c2a5f998dffbb6af5531bced1bc78eb4ca0 +size 267264 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+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_62abb2454c6da8d57ad5+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f9aac85f572373187ed5932ede47f59a7a91323f --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+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_62abb2454c6da8d57ad5+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..774aaf48504b9a9f183ba9f9d9881523a7b69ab1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df9d24a81ea41c0ab4c3985f07681ca39a0f3fdb753ec4888fc943456fc25e28 +size 543744 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3b33006655969f57c0d8be2a9e42aeda35b3e067 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_62abb2454c6da8d57ad5+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b012ac733123dfec9b6b8abb8cf8d3aa8db9f0517986a034029eb776bf6eeda +size 563380 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_733744f5680ca67f7ff9+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_733744f5680ca67f7ff9+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_733744f5680ca67f7ff9+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_733744f5680ca67f7ff9+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_733744f5680ca67f7ff9+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_733744f5680ca67f7ff9+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_733744f5680ca67f7ff9+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5957047362c05d7f5ee06bf34ec049d30799ca52 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_733744f5680ca67f7ff9+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bb37f55cab8ff3d3b874f0c874ddfe3e285f3ce353c7d9fa8633fdd649238d2 +size 79552 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_733744f5680ca67f7ff9+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_733744f5680ca67f7ff9+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2a94ec867b72b43bd0268f357c32db2d7974a899 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_733744f5680ca67f7ff9+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43d2f1739e32f2220ca67c037e6dfcd9119fc02026deac7022bb54f1f99a4182 +size 338944 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3d7d85cd3d975162683053faa369dcc6259604af --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2117dab3e3ed8caad749b8256ab430c591d3b72a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/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_73587bc7122ba5a81758+80d05c3f/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9877af2efc50998125da2b1f84188256908875b0 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffa6f4dc636f96abb0dd376b1c575b0834c28007b32ff438378700394e027534 +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7567beb57c057bcf68bbe3c5a651061a20f26da5 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_73587bc7122ba5a81758+80d05c3f/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f67862a2734e319ddcf8b33e4b30628b4007f180cbb64ba246613f85fb14b4 +size 289571 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_75329916c4da1120954c+6e4949b4/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_75329916c4da1120954c+6e4949b4/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..2ad69cd01383a682715fed6c7faaf92a72533ca6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_75329916c4da1120954c+6e4949b4/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_75329916c4da1120954c+6e4949b4/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_75329916c4da1120954c+6e4949b4/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_75329916c4da1120954c+6e4949b4/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_75329916c4da1120954c+6e4949b4/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2e4f6c42511f16c88bbe1d11dc8bf11ece0bfea6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_75329916c4da1120954c+6e4949b4/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56af014ec5c117cd494857cd1d5910a369f4f6419e5e954f894aeddc85084adc +size 84807 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_75329916c4da1120954c+6e4949b4/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_75329916c4da1120954c+6e4949b4/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..923a7970d627287e92260cc31eb765d91d8dbea6 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_75329916c4da1120954c+6e4949b4/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a598e90b8b150109443ac15797fd771ef0bc5045de809e5d026f6a601af91903 +size 646144 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7c590ab98f45f8a8dd15+283df001/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_7c590ab98f45f8a8dd15+283df001/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..58fbf6b9366d9e28d7f19321e85acd4cd96c0614 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7c590ab98f45f8a8dd15+283df001/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7c590ab98f45f8a8dd15+283df001/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_7c590ab98f45f8a8dd15+283df001/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7c590ab98f45f8a8dd15+283df001/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_7c590ab98f45f8a8dd15+283df001/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..498e5912b09a24a61484da310dae8412189d9ce2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7c590ab98f45f8a8dd15+283df001/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:548be96e8a05cb23bda5fe36b53f9d32fe3154b4396a1b8eb31fe0e07f0d01f1 +size 97794 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_7c590ab98f45f8a8dd15+283df001/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_7c590ab98f45f8a8dd15+283df001/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7a946419e61d99d1f71af289a7b30547d92bae1c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_7c590ab98f45f8a8dd15+283df001/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ee19ac9e438f0dee88f88c4e2a45a322abe7ca3275e1791bec7f5079284ee7 +size 410624 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8eedc4b0995b3a9b6f52+677eeb9d/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_8eedc4b0995b3a9b6f52+677eeb9d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ae7e0c6790082c43cd145aae8cc7e3cc89e15ca8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8eedc4b0995b3a9b6f52+677eeb9d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8eedc4b0995b3a9b6f52+677eeb9d/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_8eedc4b0995b3a9b6f52+677eeb9d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8eedc4b0995b3a9b6f52+677eeb9d/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_8eedc4b0995b3a9b6f52+677eeb9d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e1d47503a6147d6660f78d4a89f05f4657bfe8b7 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8eedc4b0995b3a9b6f52+677eeb9d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7707ed593b1cd987d6610a983e0d581ebae6f51eba46aec434d58c14dd2eec6 +size 415213 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_8eedc4b0995b3a9b6f52+677eeb9d/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_8eedc4b0995b3a9b6f52+677eeb9d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6ee014a8c4b3e3b8fc3b6520b47ce5d03b2b538e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_8eedc4b0995b3a9b6f52+677eeb9d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c1cf9badaca035baa91e9c89072c30c1001dc37bb2ac2fe6ba45b0691547c1b +size 3666944 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+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_913d465d9ff4ee2a67a8+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..865368aeb5392dacc65d7447ea7d08976866c347 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5264dcf05640a6c8c0216746b3264b441e596170c4280d6c3f2886d4ffefc72d +size 78518 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cb6f20b0f0f4497ef663ca26b0028de07ed53504 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:679532ef3907206364ffc4075b9bd9b797733619a0f66d340a77d48e8c302b5d +size 287744 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..bfe8f4205e28d6ea4d5d0686f230b8ec0f29b20a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_913d465d9ff4ee2a67a8+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b44ea7fbf7880a68b94879ff3163e8724e01f1a2890b5589c32dd40bf2d03892 +size 296094 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_944763b36d810f4af582+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_944763b36d810f4af582+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_944763b36d810f4af582+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_944763b36d810f4af582+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_944763b36d810f4af582+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_944763b36d810f4af582+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_944763b36d810f4af582+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7810def3e5acdc29639f32f432c3eca9a3559978 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_944763b36d810f4af582+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c0e98c9988e72644273f5293756a764ceb8eaea0b6def013d7e713100978816 +size 83504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_944763b36d810f4af582+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_944763b36d810f4af582+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0ac3bb0969d8b0271a39de96778126012a7f76d2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_944763b36d810f4af582+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ce8a9243670ecb6fd586ab212d0823ab38d6473d4e6cd57471a71c6a1f0e5d6 +size 328704 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+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_99a19dff67d566a541e8+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a1b84944bd41f36506ece4afd68096d3271335d8 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+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_99a19dff67d566a541e8+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..191cc7117a3ad0cdf3718873f26a50024e797365 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74884ec6c49f50bac46beacc95dededfba3fccd022f10f1dd0cee6c2c5fa9b89 +size 5039104 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2b1d723be3253af102015949af7a453a8a1557ed --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_99a19dff67d566a541e8+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b47434833803971910c8e8401b0e2d9b7d0fa47a451212544a58e0ed06a022b5 +size 5205771 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..a7a40c022faf4beb0fb20246d9c1f9c8f32c6900 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..727fe2caac58854e2f659732c11b6b5473ac4505 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/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_b23271513f9095bde4db+2dde74c7/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fe5d49a9b5442a5859aeac397aa16fe8581ddaf2 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f60181cf3c68e1b3dc052c5fe54def5ed78de4c7f3ae1a39b20c895211892d0e +size 369664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b6205cde99fee7b771daa851ed102610c9660b3c --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_b23271513f9095bde4db+2dde74c7/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:449f9d3ae1f580d794b8820448e760fc6f7fbbce97e4b3b0106a469e1238ce7c +size 379362 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+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_bdf25cde1a48d420319c+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..be8215e4db02a98e7c7d9a9b026367f5b42a91ea --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+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_bdf25cde1a48d420319c+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b427c1c8da9ea88fb01a77a0fbf6989713705fbe --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f86e10e71976f168a1698746972d300eaf66fdb730eebd874deb89bfa9f760e0 +size 246784 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e9ee519a90a487335b1cb8fb431ceeeb790d754b --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_bdf25cde1a48d420319c+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b82a2a8acef394d81a0744d5cec9542539b444c90a793ffa1e5691eb069810eb +size 255104 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c30a746238d3804f9626+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_c30a746238d3804f9626+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c30a746238d3804f9626+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_c30a746238d3804f9626+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_c30a746238d3804f9626+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c30a746238d3804f9626+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_c30a746238d3804f9626+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6600af26a067d11b72cf76c476091ff033467b77 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c30a746238d3804f9626+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cacf13484f9c208c8b918dde36511c2ab436fe32de68238d16eb3ab9b7cbe66d +size 761066 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c30a746238d3804f9626+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_c30a746238d3804f9626+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..756be979fb9e663dba5f8172ba7ff1b9da3767fa --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c30a746238d3804f9626+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:153d936cca317616d2598ffec1acb13a92cbecd14dfe6d230c49ed195eaa46f0 +size 12493824 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c4737893663f5ff66b53+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_c4737893663f5ff66b53+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c4737893663f5ff66b53+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_c4737893663f5ff66b53+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_c4737893663f5ff66b53+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c4737893663f5ff66b53+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_c4737893663f5ff66b53+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..845742fd11bf9b105c62bf2fbac28a0d36429702 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c4737893663f5ff66b53+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddde4113c4420f3b4b1554e465d9c437d44fc0c2edb12b75312b7e62f1869f5e +size 90382 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_c4737893663f5ff66b53+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_c4737893663f5ff66b53+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f658b5ff44838be87ceda04324f9c779846278af --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_c4737893663f5ff66b53+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5b2779d4d3e23a3bb3f22b686354d04a8a16992e2cd26baa4f9becfac1238c4 +size 359424 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+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_ccb75cdf21908f3399fe+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..61972ab77477b19dee312608af414e380c48b7e9 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:613e342a683da59642c46d2dc2e949301ad5e16ba24ad1cf98df935a5a3b8b2a +size 380010 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1171b70217c542c53230fa45c978f62decdf836e --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70fad6fccc6de9564ba5d099f3e834279be29e80c3f46cc05be29fa699037753 +size 1926144 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d87364ad1a47d97823f5defcfabb864d81a3cd53 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ccb75cdf21908f3399fe+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a51c3dab12fb31e38b9aa10eaad0b257ab4b5bc221155889bf0547d2e4f7d89 +size 2019200 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ccd99eedd56f698b9cb3+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_ccd99eedd56f698b9cb3+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ccd99eedd56f698b9cb3+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_ccd99eedd56f698b9cb3+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_ccd99eedd56f698b9cb3+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ccd99eedd56f698b9cb3+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_ccd99eedd56f698b9cb3+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c954f65885fbf67996673a116e3777ee791b82dc --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ccd99eedd56f698b9cb3+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d167b7fc9794adb3af4bedd335c8d928c11cd023681a9cc51494d42f7eba8fbe +size 392910 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_ccd99eedd56f698b9cb3+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_ccd99eedd56f698b9cb3+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..82a362687c2b618d3f51f6d354872dda317f5918 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_ccd99eedd56f698b9cb3+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45a8f9e0702d93f6de1aaa0c5e9474c22baa11b9ddb9491ec40d5802abce14ba +size 41626624 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+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_cde3417e6918fabff4a7+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3b28dfdd4b213537b2dea5c6bcc967e9c9762156 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+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_cde3417e6918fabff4a7+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..56189ef47f9b1bfb1b70c8aa863815eb1d840816 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ce8e1b54c019e0573c83dc0b5c84f406164a25298dcf48cb0413cf7d91568dc +size 277504 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..96b43960eedb3822f9df49dec6e7abd2d2db9a64 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_cde3417e6918fabff4a7+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ec2285f6c904c2f42cd69afd09ff293eb49a39e4095f48f71a2fe42337112ef +size 285854 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f52fe8e88daf6dc9619a+24129607/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_f52fe8e88daf6dc9619a+24129607/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..836724f44545ce0dedda1521fd4c623a6ea8ec72 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f52fe8e88daf6dc9619a+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_f52fe8e88daf6dc9619a+24129607/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_f52fe8e88daf6dc9619a+24129607/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f52fe8e88daf6dc9619a+24129607/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_f52fe8e88daf6dc9619a+24129607/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..92437f77b2f7f28ae473a0c78f88e1863c3046e7 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f52fe8e88daf6dc9619a+24129607/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:186b62018d8d8fda4a50931d42957f7af33277ea3825c8a8c27f7a3d980be1d3 +size 694128 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_f52fe8e88daf6dc9619a+24129607/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_f52fe8e88daf6dc9619a+24129607/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b6c6cf2ae24a2cafb56129650943175cd6e417d5 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_f52fe8e88daf6dc9619a+24129607/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445900336e67916e65a9603fba47560120a5241a0c4f5db8dee21fdd3bf90534 +size 625664 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+a02c3a36/compile_flags.json b/neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+a02c3a36/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..5726abc7d1d8c52fa95bc7919439a23a23fe3b9a --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+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_fef9240b8fbfaca895ba+a02c3a36/model.done b/neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+a02c3a36/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+a02c3a36/model.hlo_module.pb b/neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+a02c3a36/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..64028cc78541c1833466a343e251d2e19d025203 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+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_fef9240b8fbfaca895ba+a02c3a36/model.neff b/neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+a02c3a36/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e19098755010bbf0b694a7c77360dca81a54a4a1 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+a02c3a36/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1f4184d9c752b0198f17f98e29899a630772d5fe0b3439086b19b5be60f92be +size 216064 diff --git a/neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+a02c3a36/wrapped_neff.hlo b/neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+a02c3a36/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..13d7d3d6620d0aa6f3628cb1e3b521cfc1534b77 --- /dev/null +++ b/neuronxcc-2.21.33363.0+82129205/MODULE_fef9240b8fbfaca895ba+a02c3a36/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b97e1c44e22805335baa3cb6f91fdca1f979735c074498c3bd44dde3c21a5c +size 224412