diff --git a/.gitattributes b/.gitattributes index c4d6a593221524b092f8e053ef7a2a496de6c0f7..cedc60410c9ce6910fcd054127a092610c1b0ec1 100644 --- a/.gitattributes +++ b/.gitattributes @@ -3130,3 +3130,25 @@ neuronxcc-2.17.194.0+d312836f/MODULE_ec98086d86f184f276f1+165e9558/wrapped_neff. neuronxcc-2.17.194.0+d312836f/MODULE_01f5b55fd0ce0ced4fe2+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_e00ea95e26db168f8dea+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_e00ea95e26db168f8dea+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_0ae7505139b34db6da76+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_1657741ce6205314d0ed+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_332809dd3646c4e38d3f+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_5459a61db398caa4e50a+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_94ba84f59b341a98c066+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_a08fd8736783f45e5392+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_f91652bd1c46e6aebbc1+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/526b4f7540fab77e0309.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/526b4f7540fab77e0309.json new file mode 100644 index 0000000000000000000000000000000000000000..8d29d5d065953da8b1a66f487b7a0da965683c7b --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/526b4f7540fab77e0309.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": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev1", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/7d83e791f18e1cf05f15.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/7d83e791f18e1cf05f15.json new file mode 100644 index 0000000000000000000000000000000000000000..914d469169a1b3014f32447f7a5ff1b8ad828883 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/7d83e791f18e1cf05f15.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": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev1", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/f4b922640acf4c30ebd7.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/f4b922640acf4c30ebd7.json new file mode 100644 index 0000000000000000000000000000000000000000..9e19e2dc6133f68d4b0957ba860f633b9bc2b328 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/f4b922640acf4c30ebd7.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": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev1", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/Qwen/Qwen2.5-0.5B/03662df0c9fbf7869f7a.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/Qwen/Qwen2.5-0.5B/03662df0c9fbf7869f7a.json new file mode 100644 index 0000000000000000000000000000000000000000..a7ce5f3aa46218282cae7b557ff05939f91e0e17 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/Qwen/Qwen2.5-0.5B/03662df0c9fbf7869f7a.json @@ -0,0 +1,71 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "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": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev1", + "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": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/614847a759b7e4c0d109.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/614847a759b7e4c0d109.json new file mode 100644 index 0000000000000000000000000000000000000000..55dba8cf44d3792021fb65b5b6738f9d93dfdd30 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/614847a759b7e4c0d109.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": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev1", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/77e3fe0deaecdc3d0e6f.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/77e3fe0deaecdc3d0e6f.json new file mode 100644 index 0000000000000000000000000000000000000000..f1303476cb90a831d8ae1cf088463927fb91aa0e --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/77e3fe0deaecdc3d0e6f.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": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev1", + "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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/f75512f31db444015aeb.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/f75512f31db444015aeb.json new file mode 100644 index 0000000000000000000000000000000000000000..64ec37ab6358dceb8e1629a2a4107ee2bf304e85 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/yujiepan/qwen2.5-128k-tiny-random/f75512f31db444015aeb.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": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev1", + "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-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=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-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0062d5a4b2ea03dd3f80501f914187dea1a7a14c --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed95a9e2c38dbadd3e0a1e10fc4855c1050b806543453e35077e50c740d8351 +size 88830 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e6680280da9bf016161bab894ccbda09a2529cec --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e4c2fa5f8cc618cb6178a46af3b5804be0727115c0aaf6532f396ac8865c51 +size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..81b5d30ffc89748f29a213f72ba19a6c13eaa689 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d66316e616936a42d3d682321b2a7b1e3f4a4f7a8e3dac77e244e457c6da082 +size 247153 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0ae7505139b34db6da76+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0ae7505139b34db6da76+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0ae7505139b34db6da76+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0ae7505139b34db6da76+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0ae7505139b34db6da76+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0ae7505139b34db6da76+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0ae7505139b34db6da76+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c3a7c270212fbb1ac0677a10e0b928c00deed19c --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0ae7505139b34db6da76+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db938a12fb905ace1c1dcfb62bcbccf581b6da1f3fa17f5f9db9305aca5069e +size 46338 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0ae7505139b34db6da76+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0ae7505139b34db6da76+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..27caf82459e77b18b31bb769411da4c83a5362c5 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0ae7505139b34db6da76+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b660d33230d51488058809812bad7b6f1e4d5743c533cb3f76fb46f7256ed55 +size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.hlo_module.pb index 4f5abc24103823597c46ddb7f7f091d225b8730b..4a08364fe109800dab1491155901a04ce85edc69 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ca6707e24b81612b57e4fb439ffd77ed7a8e7464b09f782a6fbd4dd087ad261f +oid sha256:91c7887234520728a0b4296efbf0dc7438252652c8e6f92a1c81946e04b9e0f7 size 80975 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.neff index 6ff00fa0498fac5ea066d3ad1075e85845125509..bcce8648dfad5c9b78aa44d5fbcce26ec8561c91 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_152c4fbd51eb1f6f90ec+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8207cd1aa055aea2f4e9bcf0a1b677720683d9b6e210f9a2c47c19fe07c741ec +oid sha256:90b8d13ce16d5915187d63483a95ac66798f2a8ffdce18fad783ff30452cf1e5 size 226304 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff index f885cf9873bc7ddff376944030b7610ad18cd2d1..ad8fdac42af2f7beb1ffab6a37dcd220b22ed278 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:712cc0564a70d624be4585d9d0bf9e6da48ba2ab344aaa46b3bc2b69d0fb65b2 +oid sha256:f9447360dc9ced0684cbde35d92a3287a4b7f9b140c793bdcc5240d971ebe976 size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1657741ce6205314d0ed+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1657741ce6205314d0ed+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1657741ce6205314d0ed+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1657741ce6205314d0ed+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1657741ce6205314d0ed+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1657741ce6205314d0ed+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1657741ce6205314d0ed+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..35bd57d491c2031cae4984262331ad38d818f5ae --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1657741ce6205314d0ed+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12d33afbc0246bedcd17ef20f3faff63f780fba0ac45333cc1a1b1a7e485ca0b +size 87437 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1657741ce6205314d0ed+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1657741ce6205314d0ed+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c7f10256072afe50c82b2090bd7eccfee07e256b --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1657741ce6205314d0ed+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175bc2bce1fdfbda183f6a1887e32f793409fbf75e4e04ce6a98814b03201ca3 +size 246784 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff index f14ab1968f1fb291e455a031605932137664d35a..97d973c17308452bef12ef73a88ca4004b86ac13 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6ea7a800ae23210b77f9ca5af753770e7ce3f20cac52a5cbfb6308b2b316afc0 +oid sha256:ccd8e60a616162817b781abb8d9324467fe9ef1753a395eebce9fc2aca6fa197 size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff index b98543615d9c0a00a7e007c255fe706c3e7051d9..91573315800482b6abe5c2dd8c55e8c946a07041 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:209ce50c4ff21f9cccf11aa6c3c9fe8b56a458b85f915ae726b9e6e618bc10e3 +oid sha256:519a82ba54d005df23e18cbadf04c9aec44ec960d3596fbcfb7e0a8046ee5ff5 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff index 41b29e27051f96c51a056eed8081ce10519fc67c..7ad3d35973e6919bab3bdd38ffb3d068362a9781 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4a8e5a4b5ae9b7430b8f1d4af36247bdecb527e16b6e3522e7bf1f8d598bdce2 +oid sha256:bbc381718ac0b57d2e6bdd488053d01564eeeec344692713c5befefe33725b5e size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff index 4060fde18f308e6569f0819ade31d5c731fa0f30..7557e3eb3cb5b7bf7b0f261f2b525368e7b2b782 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:cdff629fd4875b4758c2e7689d06fbf4d3f6af10147990e2e59d23ae0306dc56 +oid sha256:7a46ac7bd4c0fa6e2487dad3e4edf3608f34064f514a513719f6edb30d025b60 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff index def3fca2ce82b0d8f6281184d86ed60ffe8a56ad..55f54628dae643790c04b116195c71a45d1086f1 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:abf956fe48036d70745811da6e26b78a5cd0d05da19e7d450650ad9e91afb527 +oid sha256:8c9d23329cbe45857f215901e58bec38621c10d6cf7b7abc30bc49ed573a120f size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff index b4d040f1504997b32cc9022b33a46e8a84d2d9b6..6758f3b0a7bd6d6a833e0266f12baa2814446952 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1d3b6d3a13fd959c5d03095ca331b2f52bb8e851678a6a6eff44dc1ac703dfed +oid sha256:ca8e4347a6bcd7003b09e112b2c0b2bbb8bfa27888c1a9f08e29ca8967febde9 size 257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo index 23058679daf1930378cefaacc3cf450ad3fc9064..7a901c9dcef5029cacf3efad4c454d1b8bc3988c 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:38efd1d0e95256e32d7c73e4e8b3c7bd98e9a56871c84699c620d5cd1920e304 +oid sha256:6c3f8980713ccd510d850507aca404deaf37e60db0d726fe2b1f01a18c781bcf size 268322 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff index ffda26c7b5537289a41a77f2b432c4f1743de6f0..72d60501bf86c89e4c066e866444027cb5c57d3e 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c11f49ac265b6a8d5857e4bec676fc5ac5254e40aa32cc36531aabc2aee91214 +oid sha256:35e1d10726f5e488be07bf3e0115705404e5067006659e4d99582da4547173c5 size 134144 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff index 499b39bc923d97772e11d9e6ac189d834808ad2b..9101d3ec3e2904e5733941f876b129387637180f 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:65de3b8fd9d7a5337eabaa7893537714a910ed599cb2ee67e59293f7a36da99e +oid sha256:f2fe5370194f978f86df6b1be1eacf770dbde11f3962fc49828c597dafbc17b9 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_331276a07386ee77d52e+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_331276a07386ee77d52e+431f5505/model.neff index bb97bc4b3c58b6124c84cbdf241f6baf403de2ac..e49542bcf296d78cb069bde0c8e08042f387aa8f 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_331276a07386ee77d52e+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_331276a07386ee77d52e+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_332809dd3646c4e38d3f+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_332809dd3646c4e38d3f+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_332809dd3646c4e38d3f+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_332809dd3646c4e38d3f+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_332809dd3646c4e38d3f+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_332809dd3646c4e38d3f+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_332809dd3646c4e38d3f+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..319da69d9e1a7db13686cb37ee9546b9a36c6d24 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_332809dd3646c4e38d3f+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc8b366751b8c761e38be280e38f653f383a4587cd99161f8e6bbf7bf7af8dc +size 80121 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_332809dd3646c4e38d3f+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_332809dd3646c4e38d3f+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1e6d456bf12eec67ef14debfaffb8ebf2a89533a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_332809dd3646c4e38d3f+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eea7efae8c93d034963fbe757f33d6f486ed1f7ef483a240c7252ee9a257247 +size 205824 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=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-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..13f43ed407242e763f1dc113f5f16df9bfb529e0 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a82a31247cb6ba3910f7cf9cbf53cb582bbf0612aa272762726d904f01adbebb +size 79134 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5cdccba4a40794e114d8ac28c8e6dbe2f9f0391e --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8e16a72ddcf52590a2d72852188ffca5ab3b2df96be716b98e5681743ede41 +size 216064 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ef89f7fa7dcdc38f12881ec4bfced77c0707a923 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa52be530fa4a06c057758daa7c44cb0b7dc3a7174ab4e169baef03b056931c1 +size 223770 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff index 36ddf6b089037114d17c28fcee3cc48ea65f17e0..e009103f6d67ec4e9fd7fdf1dc4548214ea2b872 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:af9bda725f1fb52ebbc3ccdb025ca435b68543fa8c8db4dfc4dc7550f56dcb40 +oid sha256:fb0dc5e60f5707655cd02d4dbcf296636479e643f3fbd59b2378163502e5c706 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=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-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b46dce1ecce458836e77abceaa808d8a5d9081eb --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73680a1e5d67702c27dc1ec55e62f35833d4a66ccae1a505b5ef8d608c39a4d3 +size 46239 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bea611cee386c775d6df209bd0045bd792bb0515 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef59413d75d9cdea01f4db5bd7a4f9a6e40d10eab93d8e6d962111fb2c98648e +size 2366464 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c3a116aca27e01b35c533c35d807fb2b8b85cf2a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_49c7199502b64c3c4f30+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92aba45e0270bddb26842459a49f49d8451c11ca03c0cb35d1916be1afb670dc +size 2374185 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_4b0ed59c6be672048dc3+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4b0ed59c6be672048dc3+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4b0ed59c6be672048dc3+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-2.18.121.0+9e31e41a/MODULE_4b0ed59c6be672048dc3+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4b0ed59c6be672048dc3+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_4b0ed59c6be672048dc3+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4b0ed59c6be672048dc3+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a5c6e420c8dc2abd59484217458d1ebd750892ea --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4b0ed59c6be672048dc3+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac612e25096c83782b4cc3de15fd519cadd414c7b094a76abf984bcbfbfc5ed3 +size 7011 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_4b0ed59c6be672048dc3+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4b0ed59c6be672048dc3+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..51c6900fb21117ae2009f70ad2d7ff1d787ae6d3 Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4b0ed59c6be672048dc3+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+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-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2cb9abfb8e1ee1c3a50d91035b5819017ac4f072 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cce13c2c8d6e621050c4f6d2a392fb09e41dd7942671696a8fe6a6738dfe181 +size 10362 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c409847aef6d8850ed49060795109fc080cf7acf Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.hlo_module.pb index e6f33a43c33a80533ae73b0063d60e0daa09d1e9..2b4d5eb66492cb388bc003d40b7e6fae48d87869 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2f60b69002d5b5cc2b0e7d9c2da141c97b7b52df0a75908b882ce4a26aa4de3d +oid sha256:019fd01bbaf29331c1fcbe55d995896d804e902516e801eed2bb9954dd08339d size 47194 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff index e925bac6777058475319c14ec24582e3fb1d868e..0360045a5ed0466b933fb4a54a7b86487ff67034 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a19a5a0a62270b6eab7786a803cdc5049f57c2bd5ffe8dbcb3e4f3206ca569de +oid sha256:4086c361b7e118c71d26c62d74db1d182a13e002a29187d4a2f53f86af1d9f40 size 246784 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5459a61db398caa4e50a+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5459a61db398caa4e50a+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5459a61db398caa4e50a+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-2.18.121.0+9e31e41a/MODULE_5459a61db398caa4e50a+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5459a61db398caa4e50a+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5459a61db398caa4e50a+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5459a61db398caa4e50a+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d78b0c6a1a09cde2b62d4bdbfdd4382574fe28d8 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5459a61db398caa4e50a+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:399ea0cecb79d737af165310850865468334bd30b7c44a83a8d0a6fc47ce961a +size 149919 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5459a61db398caa4e50a+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5459a61db398caa4e50a+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0c23dc0385eb016a83667c46da30e0e407501548 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5459a61db398caa4e50a+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5378029181a8a08a4fdd917188c9d9740300ce29050dad9b737db3fb3d0f0174 +size 594944 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.hlo_module.pb index 554172691e4746ec1d45d631383e57de7419ad66..6cf0c143b87228e4f84b11f93c3bc7dd272a4648 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:21cf5c027b34406011bdb0ac7ae8f0de44055c4bc5e4d2cecadbe543b63330e6 +oid sha256:4ea1fdade06a3258b2439292ed6d01d2fc09d48998608aa38486f5062ada2ad3 size 81317 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff index e564bb0f9aaa17ac3852aab59d9c39abebeda572..7b96eb29431181f1a23fef6ef133c2d29b3db9f3 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f8609cb1efa5b4602fd283d7f2c3813a455452a9159ffa9b3616cdacb0919c42 +oid sha256:5f1929d98e64005b02dab49493f5a698ee0565ea6cd2c542efefe293c26e9f4e size 359424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.hlo_module.pb index e3149e5049564e6472f7c5cafd04b6fe5dd62bfe..300c7dd597bab0003f84677b9b4687794a59d94f 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:14a0969992856b5db95988762f04fb2bc9bb54bc6255fb2d71cd6740b2db743a +oid sha256:1f07e0514bcc5a6c8d4753159bf5f386388fc2cc477e445254c81b6fe927fd54 size 81319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff index 05b66c17cd7adcd9473145d641ff3781bf26ca8b..096b493a52a899910ed13245912772043bc6e8fd 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:85bffa860c95571e7a070d4f956f9dd28b4b101676fc4316d73c4fe8be375606 +oid sha256:3a4c5b80dfe45a12744587cae089bbdefe58f3443bab9db3562b712d5c6ece2d size 359424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=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-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0e78c083288ffedb2748a366f7a6f1f37329515c --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:576b9fb591802690fdd968db77c6ebb13b0cf77a46fd55711e6febcd6f187dc7 +size 55929 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5e90b298c33e6417c52b3aecfc353cba80802d53 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ac8a7a2e0851ff3324a500a5a9c12e163bad675bf817c9111cf16315229066 +size 2407424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..537fbcf6fcb79c80fd3cfa9c62a2fc357ea21fd9 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_634439d56d5bb67e9812+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1a13b4d1830b0316e0c7059f6757e8bf6b25a5b56a9b3f721c749f20c53bc6 +size 2417707 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=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-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7570af83b5bbbd4393446fc1ba1a8a07a05d96ba --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9407444e4ac4007c8ec450817d409f7fc34a0fd0fbe2cafe41f84d579b6a351e +size 88830 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1de6f93faab0d5fa87aaf0cfec4a300be40de482 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf6e494d41b118fba9285a4f842815cfc149494d05be59378c37d00c04c3c4b3 +size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..10fe04ff1a6ccd8400afc780300a7bd4dbfd5bd7 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ddeb23328129a4b1d7e109ebe49b88d5f3a4db2e2fc1b553c4164db37c1c7e +size 247153 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.hlo_module.pb index 4db60a8b88042373b79cdd993f1f1a610c609a29..fd1041083eecbe5437acdfb2dc34b9e5beaecce0 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e13cd93afd9d1e18b9ce7df8249f5d7d9b950369a162e113a1fc0bd765a22bb6 +oid sha256:73b537100ccf46731971bab57d670557d32dfd05b46f0f08cecc10b6c7a45878 size 82168 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff index 29f06994f433f53e6a705abb326a6b1ca5e014f2..f89909194938a2d1de6124c4d5f22af7f4469ff6 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2032a8dc8a210e031f0abfcff0c1b170a94bd40cf549c20de09ac6211d1f3888 +oid sha256:8f280b7673b24f7fcfb07be80f6533256a10c974401436622f6dda807e38039c size 420864 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff index 0f2213af253814030b714c4488d79ce860044ca3..b411d8e0a5e6153530f8e9cc8498ef8206a1f9bc 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:422fe9682a9a014ee444b66f45e6863666481346558b956507344d5b6e122b51 +oid sha256:e0a357f8cedd200bcf835106e64e6fc20fe0b0cbe8a2afcdf81da7b21fab2f9a size 2386944 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo index 47eb1b43377c0c550b1c1c3047b9a85144fffbfd..9c3cc51e968411cfd8311578105f7470e6bbf64c 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:60bd55d6b3ed01569c8b1a01a8582321a55924ddcdac7f6da53906d5dde8d461 +oid sha256:4ec769d565300d1737683b607b09ea51ea7a29cd8668972431a5a0fb0fe0285b size 2394734 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_94ba84f59b341a98c066+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_94ba84f59b341a98c066+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_94ba84f59b341a98c066+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_94ba84f59b341a98c066+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_94ba84f59b341a98c066+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_94ba84f59b341a98c066+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_94ba84f59b341a98c066+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b750697d5bc4049fc882b1b1f6850e9397d44234 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_94ba84f59b341a98c066+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb02b8582c985830f71b8f467dcdd356f34f70a33fed4eaf5a9d28ec6eded5e9 +size 53519 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_94ba84f59b341a98c066+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_94ba84f59b341a98c066+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9aecd60bee9e664a27338d4ad0aa7bc27227b7c2 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_94ba84f59b341a98c066+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6518c6daeb1389a10bc72bcfff1172a8305c33992a46aeaeaed74002c6e57f70 +size 164864 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.neff index 8e3546cdd9c1b2e8cc07d24011e4672ae809ed7a..6f14c46c9f95363345efa8db6bb755a8fe2eb0b9 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_96404ade088398b2f3d5+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+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-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..47c37ed63a214364892fe16dbb18a26acb5c9542 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3bd2354b87e72d380a363cd1cfc99ba880da6cb454791b59fd1278345941946 +size 7011 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cef9f43a85a55abf6f57a4add6e83dec54eef399 Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=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-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..13eed6769750d503dae87eeba51542ed1cea571d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e956232f4929c428bc793d97581f836cfdc9ed3382e01ebbf816e1c7a2d8fb +size 79134 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..69b0d3c18f4732362bee2d4c3e10dffe9930b565 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00bf50ec90b33a0635ed7559d4add2f8c9c2e3d84d9381ead6dbf1643dc7a894 +size 216064 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..32df95c7507861d805ceeb43c573d0782db2255d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5022287288cb0d6b2c785d56848c3ebe9a14e111426d8c5f5fd8cd766595acc +size 223770 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1b1357d08f1dadf0ab785b26e107e5c254af6557 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4bb2fd6d46cb6897204c4c8641e2005c70f8ced561f1982a11c71628cc9dd6a +size 703084 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d86a6758aef5ae4589e527bef915459f19d0ac91 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9b6ac235ef3c9735ad0c+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ddeb5472f1aaa043b92459ac583c010976046b17bd5659fcba52cca4f23d9bc +size 20030464 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9c37025554da49ae454e+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9c37025554da49ae454e+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9c37025554da49ae454e+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-2.18.121.0+9e31e41a/MODULE_9c37025554da49ae454e+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9c37025554da49ae454e+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9c37025554da49ae454e+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9c37025554da49ae454e+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..170e46b40ac0b56c809e91059c3be6e81be09164 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9c37025554da49ae454e+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0116aa51c873801bce62eab5b30eedbeb02a12112baaecad8ff8960d50e370f +size 10013 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9c37025554da49ae454e+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9c37025554da49ae454e+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..47df37e825b66c6afdac5cafa5bb0957a98ad792 Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9c37025554da49ae454e+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a08fd8736783f45e5392+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a08fd8736783f45e5392+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a08fd8736783f45e5392+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a08fd8736783f45e5392+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a08fd8736783f45e5392+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a08fd8736783f45e5392+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a08fd8736783f45e5392+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0571595c1bbdf72d5d3be1f00d40c7c055a171f3 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a08fd8736783f45e5392+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84cd48e48dc3b764c4179611d54a6d9e63bbe84f782708fa6c93c04ab4c64fbc +size 80121 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a08fd8736783f45e5392+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a08fd8736783f45e5392+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..daaf896b4909674a9f7ed5e41f45019ef87c310f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a08fd8736783f45e5392+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e70e1383d030cbf2db85d417ec694f395bf24acb0cfed04857936eae65b4f4 +size 205824 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a669c4bb07e1a9435b7c+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a669c4bb07e1a9435b7c+431f5505/model.neff index d487e3cd98b07f93516e28c7c1d7ab1d32704e13..32eee7c19f64ade8b1fe323db19c1a747e7a3f86 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a669c4bb07e1a9435b7c+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a669c4bb07e1a9435b7c+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/model.neff index 84767cb126d6ebb6302198baaa171f4099e34df2..fc172fa5f5b6f300bd5988814efb2d7827d3708e 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:dd0b75b70d9b38f565d8a4420f0c58f16d2a12530bd9592f5df427dd96bc832d +oid sha256:b398a3795bb6de3b995759f2ded1341f87c16f2975df07b0ca2600047ad1cd32 size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/wrapped_neff.hlo index f928416bdf194c0e8acf27f0393b9d17eb8c5316..8424015245d7e84877eeb26cf963ccbb57cd9c2d 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a77b880fafe6f97b3d8e+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:51abd903bee527504afd2da5ed38f684860d8dda6d4ad0d10a46bb6bd5aab62c +oid sha256:63d36828a03ee73a7605a4dc2b48e605583fa21d62f495f7172e42ace7dfa42a size 244319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff index 13c6a73a721cefa16c913ab78dedfb34753e362c..680c179e93a924288c2b9a44cce7284569a99801 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f91acd2c97f470a43d376728262e11650397f0df0bd3e21b73cdabd31de30b73 +oid sha256:51799d154381581f8742a99ef6818b1681b9cc8e2158b0274458481602e90f94 size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/model.neff index 3621ee740d0efc707727424bf66cc5433227fc0b..bb4393826397f84581f5998a128295db2f9ec999 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:695b694bf51c1797551318aafa15e7dbec182256d41767cb48004bfcc52b15af +oid sha256:52460943beffa0d45460c50503b7beea15c01c2f13215404064b2b089578c914 size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/wrapped_neff.hlo index 0111eafd372f76d58cfd001be27ed5e0d2a82226..2c1507fa504c22165e5e0eb994efc35c692380d9 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ba6a6bbc03ee6dbd2e65+5be477de/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:580bbfbbd38852325a66d43538d4af9a56264def563723b17119f32394787f00 +oid sha256:6344a3e8066cca2bdfd3b28173abbddd6e3e572ca3a65b8335406f941a105a72 size 244319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff index 98539ac03b7cbff158fae6c250c86ffc3f482bb9..230a2fd324c701c04ac49b4d1f7a1f1c5ae8b17f 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:62f2bdd3465cf29486d8331f5b914df5f8480fb845a381006194ccb306b3ad3b +oid sha256:3751793c32ef6c290004703d6beb6b75b470e45bdc17f222c805775eb45da279 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+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-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..88035493eb87f34b119a4665d937e6a27e17a714 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e74f6e05b9bd84d59addc9f34ab7eef94e63734f2f1114b01407379ab01ac4 +size 7011 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..df5fbc484705bdfb1563c52976ecda70672b55d6 Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+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-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..22dcf0f8c79ea418cd5ca2568a4ae6f6315ccc56 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8919938a040060bd5077eef2dfa9d7707e8483b155a3cc2449f75b6e5ccf99f7 +size 10362 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..574285060a3ae6ea4007e3604c37e706a7779c34 Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff index 0044259d0c5316936c4b3976a90ccf69fa7b82b1..5ed956ea1330315d44ab7e74e746fc40e4762b08 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a31825e68b433f96b8f27a06b40d31873d844fc3b0ba5a7ddfa394c01522eb6b +oid sha256:ce588e67733744c633a8d905c0cd1c5f13138b3aae92a3743fb3af064def9d4e size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff index 0ce8006be97c9b7db1c0bdca2bb3e9b4ef5d4317..edb68d0d4ff7096e2fae7d94ee4bae085e317d5f 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f5506215ed2cf2e22610ae66b87ace9a58d74eb949e45de19d83175241aa0a5e +oid sha256:3bcc416318d7a66ebfeb385a3e05e241072005100776d2663d2c09192f429dad size 318464 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo index 3fd33b0a82dc0c41cb15fe38679cd93fe90dbd9a..ec7438798cee2bfa936ef683ba0e1214225ac6af 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5d5c629db0cd53a06d45bf70386a297e0e9590c758457bc6f5f5a7ae90093edf +oid sha256:f286d0a6d95d72f9cb3f4a0648efebb51b648ecfaf0fd2ba5774f5995261422e size 329762 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff index 95564f7a338335f8c542f116952a2593d9766888..51cc09e4c64320b51397c9d948a571c84042ab36 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2fe3ecf644c5d79afa79ee9a1bdea288092db86be7aa7b690f70a6e06fd6ca2b +oid sha256:73fbe9bfc245206612ba444363559c5eb32ed03c47c3326a495389d0ae2e5c64 size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff index e13e533343ad36f088f5e2d0fd3edd3808f6ce7b..a471863003e894d0ab40b1f58c47f32a5e954f73 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:49f1390a0d3f2d075f42832422d717eef5e2d74d352a8ef932e9239c315d4a04 +oid sha256:a3145fab2fcbc5a057d63dd09ece066daa5b2d2a73ee4c6015ce1051038a8025 size 257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo index 77cff746acd6612262e3f8f63669bd4c2b4ba299..270c42c20755b08617786f23baaadb0b323961aa 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0b59e4b13283beee396a66dee18720dd67878554a83c1ac8f7caf65f6e9b35b9 +oid sha256:ef7262fbcc70fad176e34ddec7810a2b52239508d9be3f162e87119ddba2d3d9 size 268322 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.hlo_module.pb index 1eb01c4127d118e9137ac87e4435772b3c8b8de2..cfbf049671c0a98cedb1b42b019501d2d00be739 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:49d0dc98323171b756ccd9fa5fe72295fb0aff8b4499f9f7e106fb2ed583a13d +oid sha256:f4b43f03cd2b715d17cd62b8d7dffbadc0e2154248d7b2a78d21159124fa62ab size 80975 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.neff index 8c29b1ec43b37f60798673e30fbee8fad45e89f9..6bee34e9edcde75cd9b5daacc5568114158b5d54 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e3e99dc2a67feb5066f9+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e8f9a1da4e087611a4b0c069434fbbf9438ae7baa36b4cc58f62bbc278c54eda +oid sha256:17019c5df994557d16915f679e0f3820d5bfa296bd9319ac111fd8aa36533a0d size 226304 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=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-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..467e60df5abb96391eb5a2ad77913834f125725d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf5cad1b745697f1fb0f0c418de6bf78b5d0096d41c2a898a797e4f9909ff8ba +size 580333 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e85b6d4f8e900f9892ceeb8e1079ef040d927808 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62faf97e82f111a90117c5b28e5970f1e76804e8fbc501281d832bcbb2be765e +size 3748864 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..61ffd69bed5be001a7a03ee8c554b7950390d6e5 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e5f864ff8f5ba3001616+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a46ae0d42bb4fa7788ea051a7c3737595e2852821d82cf48448bb4075ff854d1 +size 3893905 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff index 3158eaad3a6ea239bffccc8d4d3d713e54a5942d..1431e926a88c830e0c27cd296b0d650f3e952b11 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2ddfd03122e7b43c9e79c7760964b12c678a8313fbfe0c3150be9dfa05ccc531 +oid sha256:803d6058506b49dd1eee4cdd48a0353d6031f849d1ead977742a93c30224f70c size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91652bd1c46e6aebbc1+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91652bd1c46e6aebbc1+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91652bd1c46e6aebbc1+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91652bd1c46e6aebbc1+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91652bd1c46e6aebbc1+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91652bd1c46e6aebbc1+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91652bd1c46e6aebbc1+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9c9c9e73f78f9ed6aeb7a7f03bb9ebab095e7d94 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91652bd1c46e6aebbc1+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ea2586668ee140cd11dbb6523d32be5d63e4cf711287e64031c00f1107daa52 +size 87437 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91652bd1c46e6aebbc1+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91652bd1c46e6aebbc1+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..43c2b7105608ca80c49d79305183adbf9cf29a98 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f91652bd1c46e6aebbc1+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ac99b0f98cf3f91ee1c7dd06085cbc8ffa0f0d4e29912e3c7a286704c30427a +size 246784 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff index 4813a0c056e2bd7313ba1f1632797dcc8060e0f9..3d849e7b6d347f9f32dcfb90abf5f91759cf3291 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f662a0387436c1e5132ba5487e2f12440e0d367aa87b52ad845fa81d7de4e9c7 +oid sha256:facc37749d2f2cbab05ad8c157a6c348f8142dd63c095b61f11a5c06a0abbd05 size 134144