diff --git a/.gitattributes b/.gitattributes index fa4bd75efd645d7afcd5b881127232e9b6c13b02..9d09702214cde3e270dff9f7b0329392976502fa 100644 --- a/.gitattributes +++ b/.gitattributes @@ -3580,3 +3580,40 @@ neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/wrapped_neff. neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_237bde4d2878eab12406+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_4baf198a5deb7a7a74c1+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/a1fb8d68b1dd3a5e0343.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/a1fb8d68b1dd3a5e0343.json new file mode 100644 index 0000000000000000000000000000000000000000..a0eb0ff5d6852a1f63dbd1b8a57ffcb9f8a22360 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/a1fb8d68b1dd3a5e0343.json @@ -0,0 +1,73 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/b82c351a99f20f0e1bbf.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/b82c351a99f20f0e1bbf.json new file mode 100644 index 0000000000000000000000000000000000000000..674b2780fbd71be3d4968738fef71629a94a479f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/b82c351a99f20f0e1bbf.json @@ -0,0 +1,73 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/d7c97ece1c92f8d7a652.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/d7c97ece1c92f8d7a652.json new file mode 100644 index 0000000000000000000000000000000000000000..1bd2dc0afe86ddb3dfb40f664c982af231f63b4e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/d7c97ece1c92f8d7a652.json @@ -0,0 +1,73 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/22c113101ba3dd847853.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/22c113101ba3dd847853.json new file mode 100644 index 0000000000000000000000000000000000000000..213d68fd6d9c837633db2d2ca6345a61fe141515 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/22c113101ba3dd847853.json @@ -0,0 +1,77 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/518aedc9922077420652.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/518aedc9922077420652.json new file mode 100644 index 0000000000000000000000000000000000000000..4044b87aa423e2f6cd2ce6667226eda11efe171a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/518aedc9922077420652.json @@ -0,0 +1,77 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/8454e73316900083f7fa.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/8454e73316900083f7fa.json new file mode 100644 index 0000000000000000000000000000000000000000..a6adc4fa6b71b7ad06cb2c25099930005c5d21ac --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/8454e73316900083f7fa.json @@ -0,0 +1,77 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/unsloth/Llama-3.2-1B-Instruct/5a6fed2e49b22621d6f4.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/unsloth/Llama-3.2-1B-Instruct/5a6fed2e49b22621d6f4.json new file mode 100644 index 0000000000000000000000000000000000000000..d39316a74d69f46fecbbd84942c10aae3e1a9377 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/unsloth/Llama-3.2-1B-Instruct/5a6fed2e49b22621d6f4.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/mixtral/dacorvo/Mixtral-tiny/4a676afaa532a268c3e6.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/mixtral/dacorvo/Mixtral-tiny/4a676afaa532a268c3e6.json new file mode 100644 index 0000000000000000000000000000000000000000..da02eb184111321c09a244cb909ebfc8926c2b3a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/mixtral/dacorvo/Mixtral-tiny/4a676afaa532a268c3e6.json @@ -0,0 +1,73 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/mixtral/dacorvo/Mixtral-tiny/78d9bee465682e852b40.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/mixtral/dacorvo/Mixtral-tiny/78d9bee465682e852b40.json new file mode 100644 index 0000000000000000000000000000000000000000..f9a0cdcb5c2984ca612bdba0d5e8ca7b9ae71357 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/mixtral/dacorvo/Mixtral-tiny/78d9bee465682e852b40.json @@ -0,0 +1,73 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/mixtral/dacorvo/Mixtral-tiny/e36d1c42997d792858b2.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/mixtral/dacorvo/Mixtral-tiny/e36d1c42997d792858b2.json new file mode 100644 index 0000000000000000000000000000000000000000..ce6e5e374f25b4282cbc851e3c65aabc2c325df9 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/mixtral/dacorvo/Mixtral-tiny/e36d1c42997d792858b2.json @@ -0,0 +1,73 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/phi3/yujiepan/phi-4-tiny-random/43a72dc22254fc7fb0b8.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/phi3/yujiepan/phi-4-tiny-random/43a72dc22254fc7fb0b8.json new file mode 100644 index 0000000000000000000000000000000000000000..b031522b99419d905cb1281b5390357ca9e982cf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/phi3/yujiepan/phi-4-tiny-random/43a72dc22254fc7fb0b8.json @@ -0,0 +1,74 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/phi3/yujiepan/phi-4-tiny-random/d613d6ed413dfd8dbfb1.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/phi3/yujiepan/phi-4-tiny-random/d613d6ed413dfd8dbfb1.json new file mode 100644 index 0000000000000000000000000000000000000000..3a911e9b009e4bdccf9c35c784590981b67710fb --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/phi3/yujiepan/phi-4-tiny-random/d613d6ed413dfd8dbfb1.json @@ -0,0 +1,74 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/phi3/yujiepan/phi-4-tiny-random/dcbab2789a54457b8be7.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/phi3/yujiepan/phi-4-tiny-random/dcbab2789a54457b8be7.json new file mode 100644 index 0000000000000000000000000000000000000000..ec6c79433476afdbccae52f49b8bfbc63253afca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/phi3/yujiepan/phi-4-tiny-random/dcbab2789a54457b8be7.json @@ -0,0 +1,74 @@ +{ + "_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", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/yujiepan/qwen2.5-128k-tiny-random/3b0da6674ccbb4c54008.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/yujiepan/qwen2.5-128k-tiny-random/3b0da6674ccbb4c54008.json new file mode 100644 index 0000000000000000000000000000000000000000..73e0be8b28aaa945501701c6bb7cb1d376a38594 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/yujiepan/qwen2.5-128k-tiny-random/3b0da6674ccbb4c54008.json @@ -0,0 +1,75 @@ +{ + "_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, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/yujiepan/qwen2.5-128k-tiny-random/93cc982fd6a2f922386a.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/yujiepan/qwen2.5-128k-tiny-random/93cc982fd6a2f922386a.json new file mode 100644 index 0000000000000000000000000000000000000000..acfd5a54cdfcb27db6b607f403ad9cce6488acca --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/yujiepan/qwen2.5-128k-tiny-random/93cc982fd6a2f922386a.json @@ -0,0 +1,75 @@ +{ + "_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, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/yujiepan/qwen2.5-128k-tiny-random/f47139cbb86af2922de8.json b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/yujiepan/qwen2.5-128k-tiny-random/f47139cbb86af2922de8.json new file mode 100644 index 0000000000000000000000000000000000000000..6fc78386ec5a3c686243c785c38ac3ff56fd7d12 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/yujiepan/qwen2.5-128k-tiny-random/f47139cbb86af2922de8.json @@ -0,0 +1,75 @@ +{ + "_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, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.19.8089.0+8ab9f450", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "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": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+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-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1abfd69d452027c64f1ac9057179efe087107ad7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f6b638aefeadca99033ef7f839949202199f19011f1e61018e5bced90f26fab +size 81550 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..254d97e8ce6d9a429df4c32129e0160bfe7bd155 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b67b02c17d5b839e9a712ad7f5382ae0b26a3f5493de6a8453ab4db4c8e0f94c +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a9bca880aecb81f1b1f865c55db5478797e37d67 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_0589868b7472c4335f2c+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5e0b9a22c7f437d85b83d3a9286597532f7725b112874c84476572d619d3955 +size 244319 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0a45ac96b068b4f734e5b95c5c1a70e2b0421b53 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:952dfdff0640134652e8907767e25827418409d6741f69a15c42ced982ac907f +size 7099 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cbd01d3a8919a3450bb4cd68477c1288634fd8c2 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_12b331fade64f568227d+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9a2e980aff2440a892cc8caef0bb1b2f04dc4b43 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90460a3951fb3fb92f159e322d4410d84c975043323d8ddf47fb66e109cc0c52 +size 10362 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..00fdf259179ef3de49e6b997ac0a5c69f83acb47 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c13182ad393459c74b0+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0d91665327b337c8d1017ac4178f914b2ff7653f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02be5680d6270885d87aa35ad959e4e5c8554a8c16f2d5c658c46496b154b7a +size 69728 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8c166ee82d3843d9c9274d4140f1e0847c742241 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9fb38fc267f76592b0cc0e53b7575113377601ba3679375e3d8941bbcc00b2f +size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..108050fa3b5132803d82e0a7be02e6cfa8d397b6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e6502638c15da1920c2+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6432d0d654792167705df4312b66c54d0a792a710094d837584bc5e0a312021 +size 258114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+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-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7b09a1b5945c04edd50d854098e0642f2885f6f3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2cfa8e742c4893766c3b63b6971e73469c20ed6ed959007a32f73a5d6e66751 +size 81550 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5350f4d9d85715e5849cee40a51dccbfb0429c3f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:401307ae3203b370c828266d75d96845cb5ee7a8988eda91aa86ce3035185037 +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ba124c0a6e5a7dd745b067357da7466c1b4c6ab5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2180fcda61d340fd5708+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bf4929dcc550a9521cfab337a0026ec344a203367c3323d5688c4e82e90a11c +size 244319 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_237bde4d2878eab12406+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_237bde4d2878eab12406+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_237bde4d2878eab12406+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_237bde4d2878eab12406+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_237bde4d2878eab12406+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_237bde4d2878eab12406+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_237bde4d2878eab12406+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..33f3e64cd35923a4735c566cdbb6929bbdd207db --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_237bde4d2878eab12406+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:473ef849b689cef7f622335bba72ee17735fb02e8f815b62a5be88e899c550c5 +size 69044 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_237bde4d2878eab12406+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_237bde4d2878eab12406+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7a42a5a7d93f0c79c765c68b7906dde212e0afa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_237bde4d2878eab12406+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1708d409752cd64b49f4c9e2d0be37aaedc8d7cbde6c7084717e26eccf3ef5d4 +size 1168384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f7ccada5ef9e273d60c3d5fc097d8849b3bab5b6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a2a64d32b54877e99711d708a1d9c0c4b04b1ecb41005b90452a866373db9a5 +size 69730 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2008c7edbd29aeb650e695cf6c7ffcd9c75f88cf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4558eb2841329755701439cc56f8f98132224b959955389ff78c2e65a7a2236 +size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4f2ac3a551c758eab2edb2c8bcb913ffd075e7dc --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_23a2b8e835dd2021c6b3+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab5759b967302c6e1b1c73c853c73ac5dcbc4e9cb1ad8b9df837c6b81700ddb6 +size 258114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27e5ae17ee04d727b902+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27e5ae17ee04d727b902+ed72d204/model.hlo_module.pb index d6bc145619e7d3818b296c4609b46a75925444ab..45ee47a0fd1cc9019b908d100b207865729389a6 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27e5ae17ee04d727b902+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27e5ae17ee04d727b902+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c06725bd2042fed010c50b53918d8f294a9cea48d97b263e0840e696ac9ce14e +oid sha256:c7ca3f3dc28ab9661ce68d04223e968d1d910e9d823910ab2fce90101db70768 size 50076 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27e5ae17ee04d727b902+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27e5ae17ee04d727b902+ed72d204/model.neff index 58b770ab1159cd724b9a814480db41cca8150994..094f3c51be1ac9e0270660cda70db18cec025215 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27e5ae17ee04d727b902+ed72d204/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_27e5ae17ee04d727b902+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:09f0cb529806e5acd60ea4b7c58d0c67c7dd3ada403951ec1808264d6828fdbd +oid sha256:4501b6f9c48a244f63044f46181245ab9d4e247b079feb72ed78f239cc141d72 size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.hlo_module.pb index 462273a2a60849ea544c44d25afca25348feac45..c06426bf7fedce358f3844db832b9281562979e5 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:93b0fd92c6202310912a9cb64b922c8be5341156ea81522b27cae72148f0fd1f +oid sha256:9eca1f65c2409e5c7a7339ab1bcaa6b4fc78811995c18934532894fd3e6ecbe0 size 83920 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.neff index 9e7a30782b8d7b5f5c1126587be18a18c9f882bf..2949d9a7828007c5a01ceff35efa8a5cdf144bf8 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2a9a2536c0daf08da8a9+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1ea832bd8b8e4526981ee7cc60aeb883f2ce84cfe7554ae907e6e920b56e1510 +oid sha256:b2fba19c77e65c25692f52fd49b05880af3a3215113b393603abad25dfaf536c size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+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-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8f7c940b12c00697b4370cb273d06e0d47e1b510 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c760a15fa5b85a7326e0c2ca00c2da04cc5168201b44a9785b02f46bd053b8 +size 84033 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..57f58e98326baa3bd7c1e4427dd0b6f6e59414b5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7835c0daa36730c8dbcb274ebc984c2359c81880f8dc46b26f52a3f5053c2353 +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9a2a852f1325762b43f907b31eba0ea407ac6f3a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2c3f8d60681c3a37a82f+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1471ce3bec6d72c41e69a9a6f2bf1f1913342b80657ed89cadc5747e3831c84 +size 193114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+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-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fc29a02567413824ef764722147eab2ec927a1dc --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7fc55dce818e0018a135c932b7585ba00223394472dad7d9aee08b6abadd281 +size 84033 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5e41f2a1bf2ebbe5a4aaf9ac54ea6cd180202cfa --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d888ee8c853c08d07390153bb047d048af2442b3931da0f0f08684431bf045e +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..02bee3ee1a54e8086b0a738a706648fa022273f8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3422142ebef7a787c200+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f060c0a30fba95285880a636c97af4a51e3592f2f855a27cee90bf86c4d3b030 +size 193114 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.hlo_module.pb index e2e17a63b234f9a62e4658ee5f543bea74fe33f3..e28a6e8167a0feb2378b28c10356e68066b28a9d 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c7595f06bbe9f42f0bba889bddce0306037d6ded93ad7001267dbaf56db587c4 +oid sha256:b6b40c626e53ffc9327082ddb3776b7766fa1dbb2e0ef93d244b1f006326da86 size 82573 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.neff index 999b4dd629c9042945694939fc575c1e5fcbe4cb..d7f967ba87cbc2d68769ccf60b32e5d7fbd77f2c 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_3829e8e6510db07ee7eb+c2248236/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:aa7239fb49c7eea6134940e1d8ba9571b714754c6ec34d80f0137beeffb067ee +oid sha256:cd8d159e065774217cf0992712721727e6a04be6c04a42a75876a5a4b1bb47c9 size 359424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+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-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..dfc58cbb09f7504b3f06e77395a7f879c43fed31 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a07b079173e59dab3646d1db7df971e18692f3f815f155e0dc1e4d6006dec2d +size 89438 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e47d2020e9c4d661fbfc36b24bafd59cc36c2831 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47c060724055e4ba09c1bf8b7371714445e138adf8defcc86da6469ae8163d39 +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e6b9e98026a2797479e1e591804cbb1742b853d8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4298565bf741752d31de+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b325437e1ba4b0058522204955031bced899ff95c17c9776bccf6f22a126af09 +size 247153 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+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-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4e87dbccd446f95a6290b493e397c985ab5d8263 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d8145fd956affb7211805cb337a58ab53054ac6095986abe305e7007d28d295 +size 89438 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8a7afed0ae1cfe954480994106688789c5fbd69e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b21c91c8484bba6f5ef79c5c4db0e560daef1e964908a75f9581761a2d57b8a9 +size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e011f36a378a4dec77225cb783a9bb51889ab959 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_445ff816d483a8457b1f+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2835fc17c9eba831425648f0e4b6d0d2d925ad2900218f29ec0e49b73eb77d4c +size 247153 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.hlo_module.pb index 808424327e5feaff22433a70a7c09f23e9c408ce..4eb2209ad8d31ec421f764c59c676dcb6880fefa 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3b968d71c1fcaf65482dea413934cf7ef804b64cde4775c7c3d6ed231620ddb2 +oid sha256:b3175e0119359ea0b2bb2b615f5a09d6822743674b887235b564464f8a4578c3 size 81323 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.neff index a5087ab93309d8efacad64e626d2d6b7ad62da3f..cb22c09b04ce6841074003a20834b094aee7ba4a 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_44b3dad90bfddb867dbb+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e8f7e13d7afa406962dc053976bb2f2a044b8707c1c001f31ca6a91e900c9d36 +oid sha256:23ff45f78dfe130cf79956975ef433a207f471cfd30abbd235e82850f37ec06f size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+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-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a9027b4afa94507aba2fb54d692bbdb0286130c7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111dc037490d38c7f3357aa15dcaf0032d3767e945d8581ed586399663a99398 +size 44602 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fd38d11c65ddd7eaf74c2928c37acbb8e17dd76c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:329c67e6a948df31fe6dc76a11d3dfaf4c1eed5a5893a0eadcf7bb04052000c6 +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7a8d8c36d46debe586f4e89ff5aceaf40d8da002 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_47de5610a11c29da3d0a+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f1ed9aabbf81fa9ce05d1636d7510a3d5c7e56ec4529d5ded67f2c829bb39b +size 193010 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..47fc059ae1997876c549a6eb37b1b0ec42b1ffdf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16531d760e00ccb36e70a9a77d23a377a0deec739a0cb0616c3f449d7352a90f +size 7106 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..be740bca0b3446d7446afcecd63b988b86315357 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_487ea60b2ecc168e7006+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4baf198a5deb7a7a74c1+ed72d204/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4baf198a5deb7a7a74c1+ed72d204/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1569eac18fc7f34b3fe66166f2d7a4a59dbc5aa4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4baf198a5deb7a7a74c1+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-2.19.8089.0+8ab9f450/MODULE_4baf198a5deb7a7a74c1+ed72d204/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4baf198a5deb7a7a74c1+ed72d204/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4baf198a5deb7a7a74c1+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4baf198a5deb7a7a74c1+ed72d204/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..70136d3b1c4145d412c4fb9fe136191d1918f04d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4baf198a5deb7a7a74c1+ed72d204/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81044aab38705b7cffeab3b5e7fb58c5fa25ec6408ec676e2c5f089cc2e1c7a1 +size 459151 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4baf198a5deb7a7a74c1+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4baf198a5deb7a7a74c1+ed72d204/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a1d57540a31c4e780923d3fece81e72308ce6239 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_4baf198a5deb7a7a74c1+ed72d204/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872bdb2cd0e119fd71cd4f60cdce96e866920149161c01ca78e52c545d002061 +size 31386624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.hlo_module.pb index a3a200aef44fba926109ceb8fd8a8f7f753a9c44..5548a48916d9425b1da36a5c4d5417a67d0a2caf 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c8446f48899dfc1759c761c8a739560cb58ff1f1970658faf7cf41c2ced3f03b +oid sha256:03b7c8bb73a84684e848a4401b656d46c0a39c5489b2d092bc0e77cbbdbd4945 size 83920 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.neff index a8992515655a6d9d64849971935da5d74ce14fa2..bc620a1a9471520af30c48674e09ab56adefced0 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_569380bce0f73e129472+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:201aa492f14e9446bd4f427aa6cd80c5942ff42f265691e064a1f81b8c428497 +oid sha256:4b0311ce7dfeafd52060fdff8847e1efd73583aeac078ded8001926826f160af size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+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-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2ab1b66a51eccd51c31cc6223a75993cc51fd2e8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f485cb980af8eb06bf9bd6d1d0fc701876fddc366b7c80ce12a397983d90f765 +size 42794 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a61e3dd724beedecc839344ac11c444178d2172d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bc2861cd485ce499b4549941246cf8114a52eb73437d9e880e6f908ecd56f89 +size 164864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..dbfee3682249c969e06f296c06773568849d062d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_578b48b49a6ec9721dad+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93c5c5554991bacf43c236241fab884c74ccd09fcd54fba0bc2f3011fac21696 +size 172461 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.hlo_module.pb index 5cf330468d4b5c50555d342f05aef81c04c1410f..d83153eb8459dfb5e53cce80d1c080439901763a 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f68bb36b600d4c4d7a0424ad8d685e9f79339ad43aa1512c087b819d0f3853bd +oid sha256:35bb527b959dc8645a02b0119a39f0f5c6a148be922d2261a4e4106937f361fe size 80469 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.neff index be2e0e137033467f227c7a4d2a7645d1a18eb1e6..429440a8a611ff67cbf708f0d2efea484d7e1b72 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_63c2c34c7243bf28abca+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5c402deab454fc45a976e64613c87f09357903d64c79a51361f1fb0a09f475f8 +oid sha256:ef15b2e097ff580b6706978dd45a7d13eb102727e94bba630d1358ba9bab5397 size 205824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3aa2c6d2460378fdc36300bb97f79cc5a352cf62 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:555ed7df9d1c4c5f365542c32a00dc280894a42667f29162c9476643ee32aa05 +size 11227 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8afbdf953d8007264b537b5f7b087ca30d31fac8 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_65cc17d5daa2b60921f9+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76fd1a54684e4de0e33c5c6fe998a5d44c2c6d175964847950891d4abc39c2f5 +size 103424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8508b0621281903c9e232c5a5e5db55139cf2c83 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0f79e1d9744e31374274c65877eb1317f14db8f679e3c660305986a7cf9f00b +size 7011 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7e04b243f71359a4fc6d3f7b9234d96cddf57a2d Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6a7765cdd7439b14659e+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+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-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fffb2ab53ca99af62fc6b83f25e2c4e2ed89d45a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:674721df9cbdfd7626ef37d99799faed0a97b3c54588c48c76e730430176069c +size 379307 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..92bfa07d85d8582df767f0399c5c9c5d7a163953 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d8b442a8d15142515acee49731d436cc7db29f389c9a05b9d6213dedf1ace8a +size 2161664 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1a7bf517319184f67d53c12d72e7fc0764e76bdf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_6afbeaf80204294c4ce5+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e6ecbd0084e8c0c5eb0b271cc5393d0351113896946d1bb265391b4231ae918 +size 2231293 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ebf1162d47543a5959+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ebf1162d47543a5959+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ebf1162d47543a5959+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ebf1162d47543a5959+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ebf1162d47543a5959+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ebf1162d47543a5959+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ebf1162d47543a5959+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4c24819b94fde6cd3121fe0bf486a93e0d0f4c7c --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ebf1162d47543a5959+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5b28fd9884c0b11c64f335207fe25a5b8f8f716556bbbbd00ac38d177998703 +size 7092 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ebf1162d47543a5959+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ebf1162d47543a5959+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8dd0a5baa793481fe32b27a982cd4bfd6ef9cf0d Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_70ebf1162d47543a5959+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..052975b660072477eb170d23ebb856fb58700421 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51af21491caf08ac635a76a5019451599de63757b45aa41bfa9d12e59df183a8 +size 11227 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..298e48adf0ff09c106d8db9955afb84be80a8d1d --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7361e4b296923179e6ad+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df9cfe9507d1e9536868c59fe942611a67eb5b0dc0f96286850201e568d5c043 +size 103424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.hlo_module.pb index 8a2a70b48527bcb45d6a852d4b1332886ddd901e..bfac9baacc8cdcde95c3bec9b95c589cd1098421 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bb60cf733d16905fb7c8564c3968830a389767a8adfefd4e1d4e33edfa904605 +oid sha256:2dbb95034e1f21fa440a68f2a7cc4cd38547a04023591a5979d30bcd1df2edc9 size 81323 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.neff index 9a3ccd49ccedf171150fecad18f19c22d949a3f8..e2e69a6281d7c6f646c0dc220ae4b22f8c97c7d3 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_76b0c22f7fc8c9e2ff54+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1ffaa234005543b00009bfc891c285f0fff7e252e5c721144125fa01cf64f88c +oid sha256:28797dc1c22a809dd208abf09354c73035cbe53ee67b8fe50dc0cb7a783397ad size 236544 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.hlo_module.pb index f8ecb1dd990f612eb2d2e0e4d9544e6090a0fc11..622bff51d13f329dc284d05878dc118dd62c4acb 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1dfeccf30eca8afc20bf126f1b9ca79e8d426d67d8cd236f5a73eebf586a8cef +oid sha256:b417c1a79652c021712e8b1ce0bc8f488787e35cafaaf89ad5c171095bfb95e0 size 83368 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.neff index 070d638e7f402a47b08412fd2d35e76fe5639e68..2e90b0dfb8c81e8b99f48d516d525a3d62a04b06 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_7d84a4cdb76e9616c2a7+c2248236/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:07b5ad00e3e63d480361f70a965c505084db5c4f412744023324d78dea7295d5 +oid sha256:b6a7b5a13bb1e789ce246203796e582a184252f8b27b7b7de1b702154a009b91 size 420864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.hlo_module.pb index cc78e894116903518376d74cb0c2681ebde51964..09c4c7f968fbc62dbb03121bb20e68249ee6f4c6 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:eee28e808cd58c46e311c231b79f73f1990016c626e84ac179f1cc2c8172a20a +oid sha256:a29918a4399e6877e79cbf4b468d296db7df97b52d711acdc377ad211ff19288 size 80469 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.neff index 025f67cf71e88275254371ebd7e8c0dfb5dd24e7..d8652bcde0f91c64589a6ed037ff4a045c9b75c0 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e06e2fcd26e59afdf55+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8c0a9589d793d195a4a84d231e081876056635f70e1b415ed97f1cf9c6191616 +oid sha256:4038d8cbf74d8bdde2bccf41f68a76a37afaee957c1fe586e399a9b54f61d769 size 205824 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b46a0202f2245ea5d0eb7edf578867ffc2dfc5dd --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c454b59206e26963451e0e80eca796c697e09f26206f2b7e9bec24b30d02beb1 +size 7106 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d7c6b894a68f0cbdfa33f9631ffafb12bdffc671 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_8e8abd5578389b547eb1+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.hlo_module.pb index 9439ee27ed659242b9574b9d07eb8b4dfc0e635c..29fcf313b76335170c8731014d03169d8b802e91 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:aad0d56f1f5428aac097e8ce7fa618086e913063f45dd431d0df75bdb3ba5993 +oid sha256:b7d5210fab785124b9ab8d06a915c493f640b321cbb85aff1c64299256a82615 size 82571 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.neff index 6f61093a1d21917e0682c1fbbefb5ed9a89d5cb2..ea98c38056c422add13ada0349c303bf6c98bbfe 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_9bef1303fb9e21c6cb66+c2248236/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6fc9e1a586a46b36db426026053355a0471ed7ac21501368bd9b6605b09a90c3 +oid sha256:3c731f5d2383d114e307a24f12575f6cd4587dcb100e08b3d6d56c65b6c85f60 size 359424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+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-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..69ccfc824a97c482c974cba9b762ff92ff0539e6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c20214be14b45d3ae65e244419ab7e22a52d7d52645cd7c0957277e09fd3a09f +size 47085 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..21c166c86559b71827b950e56ae9f3ac91b0f09f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43614c22065e3c48448a50af9610d90fd01d32032a246cdb38a2925fb0523e00 +size 154624 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fd64e4646aab3a6a29b8a4de69746bb389805aba --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6c1828b39503b3a7ff5+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af3f2cf3bfd4d4d67a172c8913542b5919da1a959a597332d7dca3aa937099ec +size 162285 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+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-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8ad318adeea5245c4996f34feeb996e730d73860 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7892682093f8c05f27aa5252a5e0acadab1182cd93f390fa41e36d04fe2abf8b +size 79742 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..330a47c0112dac994a062c5936987133d14a3cad --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b8b287afcf205604ed84eb06106e654306e4d0cbc97ddd6c223232550270bb +size 216064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f97f21bf273a7acd2a898ed316238465a252a3b1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_a6e9c9e9fe59e3f8911d+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afd8d80164615db21657136abe59509ac27d835311e0e90bcc677ddd0a38432b +size 223770 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aebeca1c20769fb44546+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aebeca1c20769fb44546+ed72d204/model.hlo_module.pb index 6a005dd295e22b823b655f9eb0b783f052c900f7..24fe0bb4a1fa255904e0611aee6b775344806a5d 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aebeca1c20769fb44546+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aebeca1c20769fb44546+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:686c812765c7d3de3e0c88a63acc709b305f5fa22b8c12022c6ba884999d8ce9 +oid sha256:486294d3828b646e221d622e4d5e3aa369b902c256521495d5ebef7b6dbdf1bb size 47478 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aebeca1c20769fb44546+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aebeca1c20769fb44546+ed72d204/model.neff index d43ed71f6109cc04bfdc75879b3a0218e88fd986..b5e9eb9fee486d5892fadcb96306cff9636b1cc8 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aebeca1c20769fb44546+ed72d204/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aebeca1c20769fb44546+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1a7d66dcc64fec8aa2cb75a41cbbe775e6d5856bb8d47e44b6c355d613f9eeb5 +oid sha256:5505fcdab9af53b5acd6fad67f2e49796bac67fe4147da29c88bf2dbf6a33a75 size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aeed50ec3233ddd900a2+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aeed50ec3233ddd900a2+ed72d204/model.hlo_module.pb index 484f028ec86e4b6e76b175ba38e91beaa26fb377..aecb98900ca053c57de6f7cc88cc4512b226b45c 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aeed50ec3233ddd900a2+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aeed50ec3233ddd900a2+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:137d6f53f4de2fc08d9f82e0d699a7f2be1751d8051ebc60e654a1e8ac2d5a73 +oid sha256:27c10efa677eabe35e43b13078e6009ef3f6b67bb1ebc675bcfa0e0d3ed4b81d size 46622 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aeed50ec3233ddd900a2+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aeed50ec3233ddd900a2+ed72d204/model.neff index 174ab760da0725248e394bc9ffade32f5e814bfd..89fcff2d2b560c49030285958ad2e76b97d615e9 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aeed50ec3233ddd900a2+ed72d204/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_aeed50ec3233ddd900a2+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0c84d092f4bfd3edb4bbe849532b317ac6679991a289f8d2f668ca1a84f4c611 +oid sha256:1ddca82193c3012c589a8d758834b547e2f2cc1c157a500211285226fad6067d size 144384 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+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-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0abb03e6ba3f71a70a8824f68651776088c5d896 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5b9644aac04a3d73164009caaa0f9efa04f8817148b75a22e9702911e0e6b0 +size 52490 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f8af59c271c0bd105da10d1e361c1ca8985d06e6 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44357f16a7dd99d76dee8483d6707094002c36c492f2ce9c3cc3eb807d9c6dfc +size 185344 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..186ee52156ace5377ad9ee85d3098f6c22e68d51 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_b092b55c6af9d765923b+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02f81e258f77b643879267d4871842fbbd3bb329999a788eba90107cb883006d +size 195507 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b6bdc9b3f6c2cb319581f335e4fc003bfe1552f1 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e822cc0103b48f977d51f21735919ceff3c97ad01acc5e6b5736a90686d2b0a +size 7099 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0b9cd7c7f9aabe16fcc0e7e6943b2f4b0b2276af Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_be719fc3eedb7c9c2b8e+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.hlo_module.pb index 7a2caf25c06ba04c4c388bf74f09d00dd26f0ccb..4fc6023cc6db078be047bc888b78282f056f919f 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3a2413bb8bb9f6d06c3b18476fb98db4eb46a098345ce5db2b308c84bdf6c972 +oid sha256:ebe92eb5497f90051be9cadfb0d46b40993bb33aae28f61450e5acf136838714 size 87785 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.neff index 13dffaaeff8907e7f3f2ecd6636afdcacd26cbb3..af1a8ebff41f63e9c9576b931dfef200dc825f2c 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c0f9814a59c53c4073d6+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:73b2600876ec6cc1cdbde0953ef86cf837972fe0bb335b1e407acf106d622090 +oid sha256:807d4588e8cd6ad96175aabd13435e363d34494d95ea577a3d1a528a6950a9d6 size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2d4efb6a62361bb4fca80ece8c5e3b792ea9bfd3 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69ec8adc0e62d42819e2e31a593d500e4ecc872b5b66fad58c6413dcecc02964 +size 10362 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5b68a01fa55404103be7ca3e7cb31f679ce18bbe Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_c6dd950c4bf878ea25a4+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8046a8a7f9ad6384031b0159e58fb02705b802e7 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53bfea1678237d2b5924073b1efd75949c3c18177e09b3ebb6df681d339534fc +size 11183 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f983018cfe5151ca39532a8e81de87d342c6d507 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ca3a3e74bfb61306abb5+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197d100c7c6024f083c0f4ac967a28a3df1910117a3e13b8bb12c62c984cb902 +size 103424 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..786cd81e8f21bf78f9abce1ea47eaa8ab4fec8b5 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2beccd1fd50dfadce7099ef6bcb49aacb763e7a46f7a2c08985eb849212a2398 +size 80877 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..257ddafd69f6112ba034c020b277d8dabc2decdf --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b8c3787962c8ae038b5ebb3eb977f4e4e932afd7b263eddfee1ca0fa2e1d482 +size 308224 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ff749f8e568914ed6ec2b10bf7a6d94ba968368a --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_d691ea3e06f5d7d31edf+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27bded8fc55a51d3c4e7306bbfcacc9383665a1458e9d971fe7ee453dbaea654 +size 319522 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..68aa30e43cfbef54a9968bc017dc327c2d7d2bce --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee70ecbac589b9d810beecbc33403025e0a508fbd6e1da5a4a39e153dae8c79 +size 10010 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2c6b3266b2e7acd94b09d3828dcd3a011518f25a Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_e3a13b85dcb5dcea901d+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..34675115220079309bfad2d45680c478c378a3c0 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+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-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b0c85d9696dec1152ed8b6226f220ef5f04e99dc --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f24cf0e2fd4165cbc72aaa296d6ddbe5aa7a5fc2932438037e6e6756d17c79 +size 79742 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bab19e68fc80010008d90e09a263262014d949d4 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967b8a97c2de0ec209bb34045a8c7e1cd0b8e32bc51f741f3a812e414520f61b +size 216064 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/wrapped_neff.hlo b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..86ff072661c07fa2acfb0a7a757eda9bc36f63e2 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ea75f74c78af49a980d6+a9d440f5/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c36dd1718f1fab840b9a0f088edcb4e7cd07c80f3fe0be4f8abe41f02fba8c70 +size 223770 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f3190a8210cd76cb727d+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f3190a8210cd76cb727d+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f3190a8210cd76cb727d+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f3190a8210cd76cb727d+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f3190a8210cd76cb727d+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f3190a8210cd76cb727d+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f3190a8210cd76cb727d+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b216ce499b8af5a1eb8f75a1edfdab80ed6e8422 --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f3190a8210cd76cb727d+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84d98c42dd7ffb260ec806f4b7b8555e0ebf2dbb04f8672f74e1536ebd18d015 +size 7004 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f3190a8210cd76cb727d+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f3190a8210cd76cb727d+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..177b460c6fd919828d676c040361ef1fc8fc702d Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f3190a8210cd76cb727d+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.hlo_module.pb index db81daa260a041446629ce26bd8e27e755928973..3e67af97faed625915a174b2d6cfe532b1a06db7 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5c6e202fd9c4da6fe3d9100bdf9b5097d471b82cb81b20b5cfaeac0a5259df76 +oid sha256:c5d3df36f2bba9a77067a695cad9c8cab7eb6d221e7924ce2e6aec5601887c58 size 53803 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.neff index 5030040cd23c93e1dd9abd3269c9f273e595f530..8ca2562fd0922736b3a991f6f5c73ba82bb9230a 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_f6fe1f7719e8a4b503de+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bf6382591df2b3bdbf40af61df28ca8d5d37a23f7d82bd07ede418bd0b5929f5 +oid sha256:f632a9386b3efed9d5286089a72a063e59f1d951fd21b9a2e0276e29f9be4e06 size 164864 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c1ab58f32c71f1d32dee441b486f37f11dc3898e --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9301197ab622d6cf7fc9b997b77ddb90e143075decfbd981455569f9c3a19328 +size 7011 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3d1560bf1e8d557ae4b3c4567ba443379be1f620 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fbaa5b03f774dfaa214b+431f5505/model.neff differ diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.hlo_module.pb index d4ab03241436966ccf60ab226e78749650402a19..d71298b835f140fdb114dc66878f57078d8f2dbd 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.hlo_module.pb +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b3f5a6790607705ea6e5b0057cf86a3bcff2eedeff6cc95f57de7912dbb6a182 +oid sha256:9ffb3452c2107fddfa65b7a94d75c1f37eb08f601c66dead00e01aa5c390b67d size 87785 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.neff index 2b06f7f9a91ccb98fb4b29125989c186d1888c42..92a112a036821a9adaa941b535e1cf3381add5de 100644 --- a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.neff +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fc1c3fb8409b31c4cc3d+ed72d204/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:577798c8645258c2e92832b753b71bdf59474bf2cf03c1f5ca637a9efecfb1af +oid sha256:020673615b14e3f3406e47e7e085ec5b6835ff5056790616b235a99b8ec3e6ce size 246784 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe133c639498de98451c+431f5505/compile_flags.json b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe133c639498de98451c+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe133c639498de98451c+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe133c639498de98451c+431f5505/model.done b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe133c639498de98451c+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe133c639498de98451c+431f5505/model.hlo_module.pb b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe133c639498de98451c+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6a0a4f937d94032d399d70349c6539c191afa62b --- /dev/null +++ b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe133c639498de98451c+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a50e4117b6f427995112cac31c1d8e68e7a13034369fb2e98d5edbcd6e7fbec7 +size 7099 diff --git a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe133c639498de98451c+431f5505/model.neff b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe133c639498de98451c+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9dfae7aabe4c69dbf9972f80f6db483ce20c29c4 Binary files /dev/null and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_fe133c639498de98451c+431f5505/model.neff differ