diff --git a/.gitattributes b/.gitattributes index 204dfda76ada04965a910da881309241ae84ed83..29ca9dfa1ffdcf086fcc16e9fb7b91c68a84579b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -3203,3 +3203,39 @@ neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/wrapped_neff. neuronxcc-2.17.194.0+d312836f/MODULE_dea3fa0fa1232db56e94+26ac6be0/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_f3e8207126f92d912816+26ac6be0/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_1cadac86f33fc48d4ed3+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/509463403db38e0fee4e.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/509463403db38e0fee4e.json new file mode 100644 index 0000000000000000000000000000000000000000..bab8b7473ff1ca8003019e5e429f7692e54ba55f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/509463403db38e0fee4e.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/d31ad1959dd2765771c4.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/d31ad1959dd2765771c4.json new file mode 100644 index 0000000000000000000000000000000000000000..dfce150b695b01e198f5f6b2a94bdd00bd6375ce --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/d31ad1959dd2765771c4.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/e4aca6f4dcde393f9fd2.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/e4aca6f4dcde393f9fd2.json new file mode 100644 index 0000000000000000000000000000000000000000..b3d14440517074561074594b50a33079818bbbc8 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/e4aca6f4dcde393f9fd2.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/5968d5257cc3367062f1.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/5968d5257cc3367062f1.json new file mode 100644 index 0000000000000000000000000000000000000000..ed6468e74e0df936d03190371f9f93a563a87cd9 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/5968d5257cc3367062f1.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/78b0302cf20f0aaea136.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/78b0302cf20f0aaea136.json new file mode 100644 index 0000000000000000000000000000000000000000..c55d8ac265efb55c73360d9c0f42e0dc2f3986c1 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/78b0302cf20f0aaea136.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/dc140bf4a30b563525db.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/dc140bf4a30b563525db.json new file mode 100644 index 0000000000000000000000000000000000000000..0c251dff9764efc892b5892e267f605d68ebb5a0 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/dc140bf4a30b563525db.json @@ -0,0 +1,77 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.2-1B-Instruct/0c1a326b7a025a55c9b3.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.2-1B-Instruct/0c1a326b7a025a55c9b3.json new file mode 100644 index 0000000000000000000000000000000000000000..21f78f486fa89e7b78b899c4a39a68391e1fd640 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/llama/unsloth/Llama-3.2-1B-Instruct/0c1a326b7a025a55c9b3.json @@ -0,0 +1,78 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/06f279f394a1e3fbaf6f.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/06f279f394a1e3fbaf6f.json new file mode 100644 index 0000000000000000000000000000000000000000..8e2cbbbc09510f21550377c0248e5fecc46ebb74 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/06f279f394a1e3fbaf6f.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 2, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 2, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/6b80cf4267240f3f212b.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/6b80cf4267240f3f212b.json new file mode 100644 index 0000000000000000000000000000000000000000..09fc8dd0e5c68e4d050f2ea8207e9287f4dafc15 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/6b80cf4267240f3f212b.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/94cc933909cf5aea3d18.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/94cc933909cf5aea3d18.json new file mode 100644 index 0000000000000000000000000000000000000000..8e70c3c26bdda0b5b308db56725d3cec498712b9 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/mixtral/dacorvo/Mixtral-tiny/94cc933909cf5aea3d18.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": false, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 1, + "max_context_length": 100, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 100, + "neuronxcc_version": "2.18.121.0+9e31e41a", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev2", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/277152fa4a9b26bbac30.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/277152fa4a9b26bbac30.json new file mode 100644 index 0000000000000000000000000000000000000000..f9ba9209074bc751a9043303d1857f9ed745ab15 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/277152fa4a9b26bbac30.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.dev2", + "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.dev2/phi3/yujiepan/phi-4-tiny-random/8b02c02ae4bc0249d20c.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/8b02c02ae4bc0249d20c.json new file mode 100644 index 0000000000000000000000000000000000000000..7d4eff0e00307055f6588f87ffbf63892ac01b64 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/8b02c02ae4bc0249d20c.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.dev2", + "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.dev2/phi3/yujiepan/phi-4-tiny-random/dc26fd0754ce079f678e.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/dc26fd0754ce079f678e.json new file mode 100644 index 0000000000000000000000000000000000000000..0b81efd731014265e96d9a8b208c31f8a4eaec02 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/phi3/yujiepan/phi-4-tiny-random/dc26fd0754ce079f678e.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.dev2", + "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.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/23feb84373f0fa7bf154.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/23feb84373f0fa7bf154.json new file mode 100644 index 0000000000000000000000000000000000000000..2e98c11fdd294d861886ed7a1b11df4358ab76f7 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/23feb84373f0fa7bf154.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.dev2", + "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.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/5b1a5843da4e0e4184af.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/5b1a5843da4e0e4184af.json new file mode 100644 index 0000000000000000000000000000000000000000..0fa169ae7a572fe7ccc81c7b344a035086786ab4 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/5b1a5843da4e0e4184af.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.dev2", + "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/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/a037fcc35a84f45b912d.json b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/a037fcc35a84f45b912d.json new file mode 100644 index 0000000000000000000000000000000000000000..f3dc782e7cabf57ee9dd8f55449645ec7b17489a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev2/qwen2/yujiepan/qwen2.5-128k-tiny-random/a037fcc35a84f45b912d.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.dev2", + "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/MODULE_02f045f6902463c49bce+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+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_02f045f6902463c49bce+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7359325a0783ff9ad9034ae4e5dd8e62714d2b3d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0803cb5e5e23b32611e1d7a9f6868f512ce57b77d3a0a29c8f986b5cce743321 +size 46622 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..987d7ee6224ba9979b04f56f800dac38e4181d8d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_02f045f6902463c49bce+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5230dfb96ab51bf16cb02ac63f3e8ac41c847cb011db0f82f5001847f758f0e6 +size 144384 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 index e6680280da9bf016161bab894ccbda09a2529cec..b1018ef1f58be407d3c7a6e089c2d12cf7433613 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_046ebd86c77dc4a94c6c+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:11e4c2fa5f8cc618cb6178a46af3b5804be0727115c0aaf6532f396ac8865c51 +oid sha256:4b5cd54ec5279c4dde9e6475b7cfaeda2aab62e3e2a92fc242c1a56d05049874 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 index 81b5d30ffc89748f29a213f72ba19a6c13eaa689..30f7a3968098ae5ab53415125524bce923d92694 100644 --- 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 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0d66316e616936a42d3d682321b2a7b1e3f4a4f7a8e3dac77e244e457c6da082 +oid sha256:bc1dd826502c3a5e1b83a630e5959c0f82c6ac46c9977cc351feebcc5a0fe5c1 size 247153 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+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_0bbe60dde8eaacbc8218+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b3fbe0ee7a74fdb89244c0ba48b1b0fd820d80bd --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cec162b6f82a677bf5bad8a8984a403624ed7e7f8405ed1fd2b89ffb70ba3af5 +size 46541 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0b17cd8b1850886dd2143f1d37c70bf01c814d61 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60e93f84fcd9ed08889336789a60b971c3c21a507ccc034decf8161453cd443a +size 144384 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fbd0c7e303478f30c5082d31a770638d1fe91b9f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0bbe60dde8eaacbc8218+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:885b920ee07701ecbd3ad5016e0df8b9fda3c38ce8ee8418f9978ccc29609f40 +size 152045 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+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_0f88705903403514996d+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d082a2234e7eeaebd09433e05b15ab90d4839531 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0991e707bfd4b423cddb443d20b4f5aec4b1c262e379e65b64c27b13445ce083 +size 7099 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..15581b21867a193bc088421553f89f703d01f860 Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_0f88705903403514996d+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+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_1215feca19e3858f9ef6+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d480daeaf8214dab9142e56d41f296ff2d4e4dcb --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:527ff38e542de60af8633e078ec3c5c57fbadbe30d74ee1aac584834b1615288 +size 53803 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..78496818354281ef44d85c56c692a18fd9d98168 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_1215feca19e3858f9ef6+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6869ac00c3e40d1cf9945744471e75dd98b9e6b9571289427d0902e068456fc +size 164864 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 97d973c17308452bef12ef73a88ca4004b86ac13..6a964eedb9054da949df79ba9b697b3ccabe15e5 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:ccd8e60a616162817b781abb8d9324467fe9ef1753a395eebce9fc2aca6fa197 +oid sha256:ad2f90d77e4a5f3f591bd8b664f2daa39b197f27e7c946650e8776e7a9a5d0fc size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.hlo_module.pb index 6db9f5b59ec4c1cda75a3ec43e068a0497f00e1d..2f4073e68c06d04faec63596277fcb102043a1b5 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.hlo_module.pb +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f3ccb7b89f7123461216316af02734622aacbdaaf771430310b55142ec4a8f66 +oid sha256:b25c984cce04ac74df62cd1dc284c28470313957cf8e49fea854099b9378ffcf size 448722 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.neff index 4113f2364e8fbbec0126d65fb08060399256ce9c..ebb60816a5cefca38a717b70f287885efefb60f4 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_21d49e164d26352245e5+84f3e719/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f309ec2855b27f9f1c7e04499d51dc3a1acc033f86011ba5fa360d32b900575f +oid sha256:fafb376e0631f5d62079fe5c78eb54c9982815c07a92e4dd51e53e801f78048d size 32257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+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_30c8e5dffb371f5a2fc0+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..39fe4ac1b075f968dea881ec4d317033acea029f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2218fdfbf71bf29afa0ed05cbd601bd253eb224b8b68b012acc92cd349a9cfdb +size 42250 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f176c2ca8ad31d5e1e57cd552284527b16897e09 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08bd07117299b6a109bbdcc2de25721ecca088a812d7ccf82129137817b69a44 +size 164864 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..013c8d352f7ef365445fcc4ffbada708ed8e5ea9 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_30c8e5dffb371f5a2fc0+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2b61c4890b4861116cc151d02681a4e10deda4aaf1728a6a24853b73747001f +size 172461 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 e49542bcf296d78cb069bde0c8e08042f387aa8f..b8c17eab99386889e33629e9716c37f374ec4fc2 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_3688ee5eab5a3273c651+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+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_3688ee5eab5a3273c651+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a69f1c26eee3c0487ceecd3b0bfea313cd8db96f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a84e2c4df78dd443728551a6323c507c957175fc24244fad6ae2771ef852433 +size 83856 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..277cb370a8d96d6dc2226cffa217e5c4b7d40321 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3688ee5eab5a3273c651+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ba992580776ec3af728322a3b16baf4a7fc3238ff50b75431e123b378e170a0 +size 175104 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 index 5cdccba4a40794e114d8ac28c8e6dbe2f9f0391e..d672d6bbe05e2738399a31c6d821241b4954a185 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3a1bd8b5ecc619e49cdb+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:5f8e16a72ddcf52590a2d72852188ffca5ab3b2df96be716b98e5681743ede41 +oid sha256:e9c035847659ef48195627fa9b0edd5de00a79c72a7f9d5f84fa4ed48dd96e8a 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 index ef89f7fa7dcdc38f12881ec4bfced77c0707a923..90f45c9cc3fbb02effa1c8982c4f0ae1799e1b79 100644 --- 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 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fa52be530fa4a06c057758daa7c44cb0b7dc3a7174ab4e169baef03b056931c1 +oid sha256:508c3810dcee0650a55c552d9a1d20bc4b687866e5363fea46a5eb1eed230ee7 size 223770 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+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_3ddc835c8aaca5fb3605+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..199b4ffd2485b205312dc8d865182fdc52460b48 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e47f49ac892e885be490920dad61b26edcec9067ceecd3a32a0a409e6428becf +size 87721 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..13213f0c2c7c55c7beea7310170b37fe4361fcc1 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_3ddc835c8aaca5fb3605+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d54b77c463aabfc605a0f320223ce7eb30f740b6e5a316eedaa73118a4430ee +size 246784 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+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_46b9d2bfbdf1b2752484+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..619394612635f8be14b36ee82d229dc5bff4337f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccbb8991ce4c08190c00f2f5df8080b34521b6b52fc50a720b11ab9f0d4965e4 +size 69044 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c6ebd6ea9ef15cdd675d15bddb79faf6ced08a51 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_46b9d2bfbdf1b2752484+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8b7088016b28e05bc300a1c8ef5dafdcf09c8ace02575054444ebaa57baf00e +size 1158144 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 index c409847aef6d8850ed49060795109fc080cf7acf..8c3e72427faf20b1aba19087ed2603ecafc50c8c 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_4c948ba1d275cea9b124+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+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_53e7ea3b124fbe95f047+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b57745fc2d05b1e03261573c72bc2080b5fd9253 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db8a869bcc82627d232ef994835bbbfcaee6907910ffa4b8474e57b46c44aef +size 80405 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c7e11bc358d6dc36f09116d5522abc6a67378aa0 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_53e7ea3b124fbe95f047+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:838abe20817ce441de934d90c5006bcbcf7d7d57e68feb15129318c8051c2bd3 +size 205824 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e77d8983879f0776517469162cae6dcb38f8fc12 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:806a1385f651192b0303c2a58bef90450f99c6cfaae981eaa0ddba44f4a681c4 +size 68277 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9bff488e1b5e7955022730d26164acea287084dc --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c7db1459ef8bd7be49a3f56b30f1daddb6a4488d7940df1b2fef1c69dcd0aa6 +size 257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..056417c5ac1fba772856ae706548a0ca936866b8 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_57b107bd0499cc4986ac+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20493d9e2fde14fe06cfcee45e4a1f5f8c780d6e47c7df3996dc3ca1f6502849 +size 268322 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+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_5a10198534c5f2725fd7+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0411052cdfa95b344818a8811a935c496ce9e694 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e922a688c4f6359c90d7f7c743bf6bd312ba9ad617231becf02cec490eb8326d +size 51946 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..808d8e58f78e93e3b951f24df9f3e5793b47c062 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0746e9e3250dcf63f7996beed4c4ae2b68b9f338223f1e5a183772052e3318db +size 185344 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..018e51fc360c34c67b8dbb51bcb81f242ed0a95d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a10198534c5f2725fd7+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1de43537186c063d0753bca387178e708ea05ba20a821eb97f258f432886e849 +size 195507 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+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_5a81b67dd74f9d5520b3+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7a5044c13f006dd1ae02c79134534a26cf140642 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c2d00287788a0b9d6e0c88d71dab34ac8c0761305b268885fef9af66d2a9f76 +size 83425 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..201dd18af4cad2e17fceb960a1299f1a1665eb6c --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71149026777d06d0cc0885f4527aab8b53141395290e5f9ed57611de45157720 +size 185344 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..afe812a53d429d467f337cec936b2a01757de301 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_5a81b67dd74f9d5520b3+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2900d852844bc8462d53b0987336ecbb2619e53f461ab8eb4d54a0ecfc4ec0d9 +size 193114 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+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_61794b8717d8b5a8853d+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ec94b17abac5f40c669dd990e1d18231862b85bc --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cecb8b2e6d9a2ea5d80a7f910d95611058e25448a5765cc2bdf5e2d5a6465519 +size 7092 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8104a4b674a5d71eaf6edea1576f7e4f260d602f Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_61794b8717d8b5a8853d+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..86dbb720979c71489ac235e59ca0f77a86bc0680 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..96fdd50183be4741179a4272e8a282757a1527ef --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb65cf7fc2975320dabce897b5f50369c9bdb4062f74a252f32ca0418771b03f +size 82456 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5f295f9538b136b25cf1a49a06b87d1c679e711d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_64950c85776a119cdf83+c2248236/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd168a7d4d1fe94001bd9677413bc3309d5e07b232f1c1239b9907de94cb6f98 +size 420864 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 index 1de6f93faab0d5fa87aaf0cfec4a300be40de482..acd05c4c423a5fc8705984904f4b5e791eb1f912 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_69f077c26bda336334ac+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bf6e494d41b118fba9285a4f842815cfc149494d05be59378c37d00c04c3c4b3 +oid sha256:d6855df2ac066cb4d6a0f3b5dc367c0c68a20fdba555473ad35c98325e6c7086 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 index 10fe04ff1a6ccd8400afc780300a7bd4dbfd5bd7..f19b5602d37ca9ff6b5e90a6bd3d72b817cf4f2f 100644 --- 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 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:61ddeb23328129a4b1d7e109ebe49b88d5f3a4db2e2fc1b553c4164db37c1c7e +oid sha256:88391ded313760df6a080da418fe8f7755a5ad14197302b457aff09a4562e4b9 size 247153 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b6cfd1722ede57a0f9f38c450f8b71f0813eb6c0 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6edbc1f61aebd2bcfc907bf4a74354906dcc25824e201291622b0f1c912d4d +size 79431 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..45f0914398a88424578d7d94701bd1c6166f7c40 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9526127ece1c2fe911e0f7f40e043c8e4bf016adda4812373ff0a01ba0dc1927 +size 318464 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d8be7a670d157ba8bf9d8ee01cf73998e3602506 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_6bb5680c622866b3b45b+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:939ca9bb793aa9de3af13858f266ad4ce857c7f8ec589b4e403770a266726bed +size 329762 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+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_738e59bf5e3036394abc+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..983736ce70f0efd578e4e35e21d78f6df84226e0 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c422fa53242d548d1ed934ef136f4306c2fe868be8fa250e7fd1cb33f37528b +size 81259 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d26269d47ec2370d93f1772153e1e350f8e6d787 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_738e59bf5e3036394abc+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc9f8d3517880c1e3910a7aabc7c4217669e3dc94db594196469c9dcdeb2f9c +size 226304 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+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_7af318ed51d57f96cca6+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2457ab4c3579f2e12083b070f659d3dcda20c79e --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:570bfebad16e55f606a846e758130d43a744fd0a3e8f6fa0383c0386a7583e00 +size 47478 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b0f2fb71a56cf1e06521132f71c4df4bb53d8caa --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7af318ed51d57f96cca6+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ce1df856e2b1885249aa88be122283e80f946352a72cfdb595d52bb0cf358ba +size 246784 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+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_7c7c536a078a2c0f91a7+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2149c8b65934ee41538f0ff8bb1de51761e3f668 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec9dcc2d291a29395a7d3b0ecd3c329ac16dec5a55d463e1547fdacbbde664e4 +size 10010 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d97c220dc7da95d4b01469fe302f1734b3c3b48f Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_7c7c536a078a2c0f91a7+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+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_85a4070284ef318b7211+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ca4bf49cd2143b234b9c5e61c442e674f3bcaa82 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d07be97fa86bffd0b9d5b2cd5c17d02b4523838d7a6e300d15ea296c528a399a +size 87721 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..62b6fa21c9db8c884029f3af3e333f0543b76407 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_85a4070284ef318b7211+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d5a388f6f5f9faa0ac06b07f57fa96672ac68b4b7f88e389fffa06505e3de9f +size 246784 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..86dbb720979c71489ac235e59ca0f77a86bc0680 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5205dfeea18bf1cf496181949883f69c42096f8d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e14d263b8dd1b33d02b7774c9f93e3feaaf593c3d8faee15cc31218d64254487 +size 81609 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a98bb2d7db8804c48177d253c6219803142ac8af --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_92d7a6b8bc621dee02b9+c2248236/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d188a74cf47606fb51e0a0db14230a7e15e4319fcf899c86b85a9ec05bc6a843 +size 359424 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 index cef9f43a85a55abf6f57a4add6e83dec54eef399..c709404cd4b1e6c6b8a68dc8b48cd94870b43868 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..86dbb720979c71489ac235e59ca0f77a86bc0680 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8bbaf1482e339bb678062269adef7adbfb3a7486 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad9c9788c07b0106ea9b8b5510e9e1f32e73170c6b3d226518c963f73561f3ef +size 81607 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..46c36ad26dcea2d1d453135bfea9bca84562ccc5 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9a53db93d18e769ee7ea+c2248236/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4102af754aa30becd34f0428c25cb18aee8cbe9a64b4e419fc555dddedd15946 +size 359424 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 index 69b0d3c18f4732362bee2d4c3e10dffe9930b565..032023f077983bb869b0f7eb5d6a8114293c1514 100644 --- a/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.neff +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_9aee9a947045c8c3e338+5be477de/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:00bf50ec90b33a0635ed7559d4add2f8c9c2e3d84d9381ead6dbf1643dc7a894 +oid sha256:434cf82dae352fc7f13ff37a31ea63e6b103871c072ea3776455dd867ff3c062 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 index 32df95c7507861d805ceeb43c573d0782db2255d..25fccc225f1a8bf15a22e62e787a8bfe274053fc 100644 --- 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 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c5022287288cb0d6b2c785d56848c3ebe9a14e111426d8c5f5fd8cd766595acc +oid sha256:2de72f53fe6a8b97a6fa2db6a0041cf99fea43556787b65b69b9e8d82b861bd8 size 223770 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+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_a0119b05b11378eaad45+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b990f6f41b9ffe22eba92a7d7ffa5e6d75cbad8f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56600f1172894a3448f3ccdf32787794fefdf811f5733ade4489fa4a2db37800 +size 83856 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a9f4de062d84e7b0603a921353e5089727e7ef7f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a0119b05b11378eaad45+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5190ca06721070d96bf93dd2fbd4df4675ebaea3a183edd157be63390ab807 +size 175104 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+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_a24e3ed896dae389d4f2+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6b715038ef72dea23f7c5415a5754b27680c349b --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b76b2f95890dcac140043403bb20c0bf74aba7c28c4ea6c6c15cfc8f3264f926 +size 50076 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..492450bfcf917dc2663e74354210b25ca10b850a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a24e3ed896dae389d4f2+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6e0f7f0e41859d9bc51d2a44341d1ed158aaf09fb56414c948579ea33897f4 +size 236544 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+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_a5ba22f7ec35560de7f4+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..28bb1e35d423f79660d4ac4328525199963e9bcf --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:173daed04044c1c5e828763b7e0b96fb3c3ed36a3b5fcdefb225dd5cf7001e75 +size 83425 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a5c46157b74036f50f76f2308076c73457cf791d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8943a443de81c9a48f62d60326f7f361df9d7d02881d310f39b559a24ac67741 +size 185344 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..126fcc784af363dddef9b748e56f78ae5c31e01b --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a5ba22f7ec35560de7f4+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cd8008a48010fa2ebb5562edfc300e6ae9d15a4da602df96542f9d34df91aa6 +size 193114 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 32eee7c19f64ade8b1fe323db19c1a747e7a3f86..765da7a5a783d44d4dc68e543d3b9939a0b03b8b 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_a74277ce7a6cac60e3fd+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+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_a74277ce7a6cac60e3fd+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ad90a3e37251d3051e47f955932b35bdb1fae4d8 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9bdfa586e302eb86f47edba9519bc8c290973b14f4be2b802e0cfe37713c7dd +size 7099 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fe636e40cb8919c82a05ab1509fb3d6204a23f2e Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_a74277ce7a6cac60e3fd+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 fc172fa5f5b6f300bd5988814efb2d7827d3708e..b8f24d640364c3077dd395fd131cd32396928028 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:b398a3795bb6de3b995759f2ded1341f87c16f2975df07b0ca2600047ad1cd32 +oid sha256:09f15923d617ea3b6d706282e407e6c7021800985700d2ed3ef3e15674858df7 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 8424015245d7e84877eeb26cf963ccbb57cd9c2d..c3146cafe72505e8fbb492e2d19e15be582c5106 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 sha256:63d36828a03ee73a7605a4dc2b48e605583fa21d62f495f7172e42ace7dfa42a +oid sha256:576aa1375944182960b25392e1220e9c5b48e7f77a4dfd668fb4e2d88f0968d4 size 244319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0e0d09444ee244cb7c7eb47368ff8b4c36f641 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..22cbcd143c56d49b36da23fbe589299e253a298a --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2de5abdefab5cf8469996b59fa13f1d93f51f5a289c5af7e5121671dd2f7a721 +size 68279 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cbb9255d26275b2a8c00b45cf0b28cac9fd3d0b3 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33d9e47ee8c786bdf78acab98008da7248525740b8d2e6bde0f79cac2f95af96 +size 257024 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..6ab028e506d736152538e415663706df15ba3177 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ae5ca4b91afd03b04b25+ca355898/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a14e5f2388f3ace5ff619614bd3dd2109944b3251476a0131a5a93cf7ab8ec0 +size 268322 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 680c179e93a924288c2b9a44cce7284569a99801..fc65e7c35cfde71adc86794f2000527685c849b1 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 sha256:51799d154381581f8742a99ef6818b1681b9cc8e2158b0274458481602e90f94 +oid sha256:7cb3edeb207989258778ed70657636db6bbc288bc7ad9ae6d805328b27b64679 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 bb4393826397f84581f5998a128295db2f9ec999..7212786f56a569a0d6ea486b65c1085d2389a255 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 sha256:52460943beffa0d45460c50503b7beea15c01c2f13215404064b2b089578c914 +oid sha256:61518720f5c1a56264df8a0a25e057d2cd0e5babe0e9df301343aa3395553c99 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 2c1507fa504c22165e5e0eb994efc35c692380d9..01b57aa31cfb81dc28ae5c68013cabef3f7c2482 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 sha256:6344a3e8066cca2bdfd3b28173abbddd6e3e572ca3a65b8335406f941a105a72 +oid sha256:c61433f19c2c34b5b69640ce4fb66dd3e27b67648ab281ae8b82fa7f936f1dea size 244319 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+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_bc0dc6318052d18d4f59+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..92aab4de6e655e40a4edf39f10cf845d8a241029 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a3af38dc3759a0077763bc94bddf02381e1b81d210fb62517f722b06bfc5683 +size 44058 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7893b76dc5bf5b93abe2050e7ce0634eda60ceac --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffd5770b8b22036f0c2e824d9275a5fd7e7cc4e891fd30d8cbd0d66d3c527944 +size 175104 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0fa49fc13f899059fa8ed513b8d31ef782746808 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_bc0dc6318052d18d4f59+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c4c53821d30e4390bc04b9d4e0f98107209d051510fa7c921a9b807d1252973 +size 182770 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 index df5fbc484705bdfb1563c52976ecda70672b55d6..e1897c0800c20472800267f4afdf5c7e1db50d44 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff 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/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff index 574285060a3ae6ea4007e3604c37e706a7779c34..4eb3cf53217c7acb7542603ea635db879ab3800d 100644 Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff 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 5ed956ea1330315d44ab7e74e746fc40e4762b08..8f06af558ca98376c314dd06c11d94b11816b6d7 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:ce588e67733744c633a8d905c0cd1c5f13138b3aae92a3743fb3af064def9d4e +oid sha256:ff51b1e8f0089284c70d5ce0b95f0298dcfcea8dd1761176e4db4ff482f2ac26 size 103424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+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_d1e2c47cd5166e2d7503+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..352b248b21ba0cc47d619c4b1f971076cc4ae699 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf0ef62a7a0df517a79ae7d5279b1a01de6271c2e4d83fa8353180f2791492af +size 7099 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c3e477c36ff6cba08861d1302e38ff91316b5137 Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d1e2c47cd5166e2d7503+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e24f877fd3bd437b366557076d7c7d635759a2ca --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+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_d7e2548756fae2419754+5be477de/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5f147dd1be539b023212ad611bc29974c4c4e0fe --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa1f1c8aa58964fa1c21d32c9f6b27235496ca5a3c5b0971eef05f395e17244 +size 374859 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..605c70da69142f1ee75b893aa539c67fe25e780b --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd673a3965624937245ff5a02c3d3c5b9b119080bac8fdf5f1843f29fa180baa +size 2151424 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a43a34cdf93af84a74b1c39a219058b9e38375d6 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_d7e2548756fae2419754+5be477de/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73cb755bb80f3b339f8db03a1d6cd1e254d4c04863c9221950e93e3bece6d458 +size 2221053 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+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_ed6180267143dfea9183+431f5505/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7ac17f6035702ed025e259a4ab0b6a66e7b9dac1 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6adc0afbde64c61bc0c59d708742998d0ed8cacedd763d5b897f26939ef4e46 +size 7004 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5a604ae92498e8dc631c831f78f52478b20cc60e Binary files /dev/null and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_ed6180267143dfea9183+431f5505/model.neff differ diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+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_f5eb91ad26a03c048d3d+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..48aea0484012f1ee57870e47d4083c5621df850d --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b75ebf90847829cfc31c659cfac863e299f261af49baa91f6d38d37e0b46a5 +size 81259 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1b81195663b62a889c05aeee3a220c8382de6109 --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_f5eb91ad26a03c048d3d+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:835d001e67d90be9e65a5c8c653a2e799f0bc32d71a8f6b044fda23dfc194959 +size 226304 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/compile_flags.json b/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..60ddcc80e16080ded570954fe3fc17240221f2ab --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+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_faa4eb59c0e96cbc54b3+84f3e719/model.done b/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.hlo_module.pb b/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..932be66f5cb459fc34cf28df5d15aedaf1ee372e --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaec5af4b4cf4fd74b2e708127f3189f9e03fc023690c0af800c919028845578 +size 80405 diff --git a/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.neff b/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4e325ede650ea180e681cdb50db5624251a8c2fe --- /dev/null +++ b/neuronxcc-2.18.121.0+9e31e41a/MODULE_faa4eb59c0e96cbc54b3+84f3e719/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af0be1adc07ff75f1a32a1eda981e91ddd0305a961500bb331961273ef982ced +size 205824