diff --git a/.gitattributes b/.gitattributes index 1d200797be9eaece23e6bfbd72ff88f96a176799..c30f2d75bb8536e69648fab3a7feba45038e2d10 100644 --- a/.gitattributes +++ b/.gitattributes @@ -2950,3 +2950,12 @@ neuronxcc-2.17.194.0+d312836f/MODULE_a57600b672ea2ee05d8c+165e9558/model.neff fi neuronxcc-2.17.194.0+d312836f/MODULE_a57600b672ea2ee05d8c+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_c3dda8a57464a1f8b5f3+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_f55bef5a76fbf9bf2649+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/5c73888c2d99ebb0b3e1.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/5c73888c2d99ebb0b3e1.json new file mode 100644 index 0000000000000000000000000000000000000000..9c662e7f6431c6ee025f99669ed9cd05c2d2c633 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/5c73888c2d99ebb0b3e1.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": "2.17.194.0+d312836f", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev1", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/abd6677f389d97d11f17.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/abd6677f389d97d11f17.json new file mode 100644 index 0000000000000000000000000000000000000000..8eba278808509a2dc037eb73859008d0c6252394 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/abd6677f389d97d11f17.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": "2.17.194.0+d312836f", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev1", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/b6730030a303f82cd988.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/b6730030a303f82cd988.json new file mode 100644 index 0000000000000000000000000000000000000000..1cad249d6ab680321b83d4ea8fbd2397bb301438 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/b6730030a303f82cd988.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": "2.17.194.0+d312836f", + "num_cores_per_group": 1, + "on_device_sampling": true, + "optimum_neuron_version": "0.3.0.dev1", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "float16", + "sequence_length": 100, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "float16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/compile_flags.json @@ -0,0 +1 @@ +"--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-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2a7c4adfcca535440b626954a183451b54713dad --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:420421421ec2ed25ab59cedcabb75239718dd95a65fce87c6ac7ee15dbb3d966 +size 46338 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4f4341e75632a3aad87dbd09992ca4ad199e1472 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e56b5d7c2db9fb8c69e95577e2a50985f6505fcc7e8205acbf14e08a4127be01 +size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/compile_flags.json @@ -0,0 +1 @@ +"--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-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7c5631d9ada3d386fba791fdf02c3a0cbbe4bd82 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d922733ac53b1bed4307a23435511e01894abdfc31f5bc4e5d103cd3b3be0287 +size 79977 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2e1c82a4c87e500ece894edf5ee0b51189cd5125 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2ccad53a5652e6cad951ba99f5ef63025da28dade925b45bc62fc497f4f5ee8 +size 205824 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/compile_flags.json @@ -0,0 +1 @@ +"--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-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..54b7057ccd301e9210c423611531592819e641b4 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9732c88c01c966a633fb52000f3d9cfb6072c98be0e1ceb8a05f6fd748eec8e1 +size 79977 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4448428140fb3645215e851f775e43f63c0b83ad --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dee73b9482011a5b7b35e46d2af298c666dbafe0992bffdb4859687a5e3dcfb +size 205824 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/compile_flags.json @@ -0,0 +1 @@ +"--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-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..43262dc024984618c8c285957aa60897f1f5517b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:141f375c5586877c1c3685fd59fde284897f258fed49a5a0efc338f61fc75c07 +size 46239 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..49d5f17630e474134aa4bd50b8b5a8e0fae6e3b8 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dd9828e87d7c1cead4fa9792f396ee54881c9acac6621e11d1a017e1b40f429 +size 2325504 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3b0e7028d4de3c4654ac7bad180e2460cacfd719 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8871a77c65f3f73ccbc6c280a13c9670a3098c36da90766954f545a9610139 +size 2333225 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a5c6e420c8dc2abd59484217458d1ebd750892ea --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac612e25096c83782b4cc3de15fd519cadd414c7b094a76abf984bcbfbfc5ed3 +size 7011 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a75ad4be648a76af52cf055a07ada21a44f103e7 Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4c948ba1d275cea9b124+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_4c948ba1d275cea9b124+431f5505/model.neff index 8a131482b172f4d5bcdd500e7c733b18c4dab230..46a7954c8f4f8b2eca889425c07d746a4aabf088 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_4c948ba1d275cea9b124+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_4c948ba1d275cea9b124+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/model.hlo_module.pb index c1fb56e7082598b8366ecc1e26e3508fca8b84f7..07935414d1e3ce2c723a754081409a8229fca5a5 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6ac7b363ad14391ea6e90f95eff1d88a5146cc28af5699413964e7fc4febe0b2 +oid sha256:0384e950c159f99f387bcd7e341cd971c78baa2f71054e129b8520d91191a573 size 55929 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/model.neff index 26c75f37364b760d300715130cda08963aed7d99..37e97d37015608ca6d439e86ac1b64a60f808a44 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:82e85e7c33a12ba1aded0285eb00c9631d44713a2e29c7e17268dcf5109dce34 +oid sha256:b17db9e4117da233e198a40f12f7754bba35691e400b4f0d747ac2da39a44c41 size 2366464 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/wrapped_neff.hlo index f4e89d7da3b61b35b25092ea0c2d9f009c71afa8..a37a1ff52a2a629b0b67ab7a24e2271ca6514577 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f4acd67a4467ef3a0cb39e5f4ff6d7234573efbd930e665c2631b471c1a2ab93 +oid sha256:428e8a01715cad356ec351df6548de386af3aa071db0736d1cd99bd99e02876a size 2376747 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/model.hlo_module.pb index cee68abee60c0300cdc0f7363612aae53fb136c5..d98da315c81323a96f2bd42048e29df4812962d1 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f3de47ddfe9c2dd2dd851b262ed8e72f81d7bd5088bd4c866e33eccb1235c731 +oid sha256:0359b0c9c36a286960b432bbc0cb0b06644300e11afc7076414cd0d5c064de15 size 88686 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/model.neff index d714cc233ea87d3373db30b3e4342fb76028267e..7ccf2c5665d65fda0f9fd1f8889a6ecc2493cbe3 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:670eb5f6e43393459448f206825777f42128ddb80a24d3859cee614b17f37054 +oid sha256:4c05973c4cf690b1269392650ca42a01ababa6fc00297ffba78bcc98b8615e3e size 236544 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/wrapped_neff.hlo index 2d298b31a325d9db281b468fc86d636891ed5277..fde39653f327d9413bf9facdd1756acdcc3c4384 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e79163920afe05ec7bb4285c4a6cc84559fbbf3b4fde58c15eccb5c8001b019c +oid sha256:e5287abba715b09dddfc465058bc5a94319e69c10c963ee4b299f1b45b2ca0b2 size 247153 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/model.hlo_module.pb index 3ca90971c7cb3ce9400fca9bcac1cb70f8bc0979..c931e6150e3f9a33fa6d5a14753fee51810243cd 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9ef04c56dfa88ba3744238690dd27414699ab135700c99f5f366574da1704460 +oid sha256:b90de1c616407583866f0da434943516bb3f67d42e167f7ca0fa4e6051802e5d size 88686 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/model.neff index 07fa907695665cdeecb55ac97dbf2ce42d5b2634..60e0af4f03abe16cbaabb0b8d32008d7e312bfa6 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0b96ecdcfc5ff6f5c8bb2c6c748d4dc4fea4c4013f221ee4cbce75c1367605cc +oid sha256:b1e7c43dba8d70242622d3ad45ec0c5da34a8d40426e2ae538b373d076bab4b8 size 236544 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/wrapped_neff.hlo index 3e7bd1f1570a3261c3e5a4f83bfbb316c9dd5358..337cd233dc5aab17f9295effe30a5f8f5cf34efb 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3a96e164632fabab7abd4e40b82d9ffddbb90bbb3261ddde437c1e7bebddcb01 +oid sha256:0aecb2930882f0b972a954bb1d9687f17e624d7e9255f4e69df1b08c43acfb88 size 247153 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_94ba84f59b341a98c066+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_94ba84f59b341a98c066+bfe5714b/model.hlo_module.pb index d71f3b29f54c7c04856a9c56a09ce9e0b18d7373..0006166ba20d5fc1448344008240072e80142a65 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_94ba84f59b341a98c066+bfe5714b/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_94ba84f59b341a98c066+bfe5714b/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4ba65d5335646539f3aa28ede06c54054cea89d33efa6900bb95e22d5e9aeb0f +oid sha256:b23db7233e6261400ebd48aabab17a3fe541c4c354db141c216bc13ef992b639 size 53519 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_94ba84f59b341a98c066+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_94ba84f59b341a98c066+bfe5714b/model.neff index 61226b4a0a42b21eb979000d4f07fd00ffa9323b..0d45c0c5376bcef50807fa1483d9b405e38020ba 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_94ba84f59b341a98c066+bfe5714b/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_94ba84f59b341a98c066+bfe5714b/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:39b3c90fdb13ea980144897c0236d2d8432d49c31695db60316c9665c66bcd39 +oid sha256:55e8a59c82e50fe6a46ba496fd83d9a149307cdd5e722f9e14d3e5a4dc1478dc size 164864 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..47c37ed63a214364892fe16dbb18a26acb5c9542 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3bd2354b87e72d380a363cd1cfc99ba880da6cb454791b59fd1278345941946 +size 7011 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..88e17170ac8d587c435015e8f3079aa4ca6eb541 Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9c37025554da49ae454e+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_9c37025554da49ae454e+431f5505/model.neff index 02f2a5b21b9a8d34f2f484c9e3b6eadd815239f4..628f27c7a9546e63324b216f368d9da8d685ccb6 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_9c37025554da49ae454e+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_9c37025554da49ae454e+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/compile_flags.json @@ -0,0 +1 @@ +"--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-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..029edd4234c1a0685978c00124ba6e13428ad3bf --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c3b2a028e2d014aaf7892d0bcc43fdb6fdc54b9e2a6cc6734f1aab2e849f5b +size 78990 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..865ff37dc0b3c421d47f0c54c1b21522c38a5c44 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d82234a95635967ad91440355281fe9cc8e724ce0905f541466256d47e7fcba2 +size 216064 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2296a6264e8708211a1d8438d8bd0a81eb9b50bc --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ee5b42bf7243226b1f3ce2a062d6a6575c0eb0880f785438604d7bd129392e8 +size 223770 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/compile_flags.json @@ -0,0 +1 @@ +"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt" \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..88035493eb87f34b119a4665d937e6a27e17a714 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e74f6e05b9bd84d59addc9f34ab7eef94e63734f2f1114b01407379ab01ac4 +size 7011 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7796346494f0daa40b39f887fa7b25c8c133eab7 Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff index 73a459f32b950bf6b4ddb88c31cdf7d77951cc00..815ebb51d661df4ccc35791f01d24f3a6b04b7cc 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_cbd29f12a931a6034fdc+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d3986b7b5efee5f065f4+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_d3986b7b5efee5f065f4+bfe5714b/model.hlo_module.pb index 61f4fa8fa48ba12cb1cb5e77fb6d5ce569a19424..60621bb34d98fea7b9d0f1ff2257b936462d13c2 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_d3986b7b5efee5f065f4+bfe5714b/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_d3986b7b5efee5f065f4+bfe5714b/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2d3490ad3f154cf17e30d467065e0d249bfda6d6ad064598f06cefb0c4ca4072 +oid sha256:38774033332bc0fcb61b838976e56ba7cffff1105f75aac7c4ee85aaf391013b size 87293 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d3986b7b5efee5f065f4+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_d3986b7b5efee5f065f4+bfe5714b/model.neff index a19bcbbb0e4b6ec579b7ed7dc97048bff8e8b442..34124c2dc9c7285e2e99f4dccf6c86cec4714fa1 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_d3986b7b5efee5f065f4+bfe5714b/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_d3986b7b5efee5f065f4+bfe5714b/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1276d19ea2012e1c74fbd66b9b7fb2c4f116c5d75822dc9365bda22b1d6bac7e +oid sha256:e35b61bb34d78e72e217c7ace495b5b5925d1f5704402263be476d2a871aeb11 size 246784 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/compile_flags.json @@ -0,0 +1 @@ +"--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-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fa70968da4d692a7e0d7676041fad8404622687a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3402b54f241dd4e1370e41572fa09d811e73496a1bd57f8effcbba618b7c7527 +size 78990 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7c87e2c310a1babc6ad409b4baf7f314a454a23c --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63e40e132d4558f7cc1d896a9b85bf79a72e644a20a8837e72406afac0d49d94 +size 216064 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9ecb2ccb7e353ba739f9d18a33a7c25d388a75ae --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c466ed135b00bf2c31e8b379119211775ecaad81d50d7b29a18e1740ee664316 +size 223770 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_f84068611c70eb3c41a2+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_f84068611c70eb3c41a2+bfe5714b/model.hlo_module.pb index 351d209f0561d87d2ac91522986a3bc10e886f94..ffcd0f53400012a42935ece21d0c58bd22628325 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_f84068611c70eb3c41a2+bfe5714b/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_f84068611c70eb3c41a2+bfe5714b/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6b4aeec679a69511a8128b7836f1aa52b284c380397507732dcacb0e8d540385 +oid sha256:27cea0001c03931d667299352661b5c828af3cd219744f523e7e2e92313de533 size 87293 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_f84068611c70eb3c41a2+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_f84068611c70eb3c41a2+bfe5714b/model.neff index 203864cade35b10c1fcd74c241aa4e5960548946..df16b4c8113f07a0d2b32b40ef8d8f5496e56766 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_f84068611c70eb3c41a2+bfe5714b/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_f84068611c70eb3c41a2+bfe5714b/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:753350d9678f5d9a3a7a205fed3e4aa3f6a0cb0273310fc36b07edf138c09299 +oid sha256:43f46e166441496208c28bad004c2881d8dc636a52cae19d31773795ed7a6a0d size 246784