diff --git a/.gitattributes b/.gitattributes index c92f0d73ad0a3698236782a66e8d29c20444fa58..cc9a5adaa6eb36bd159ecc47a08935283b2d94ce 100644 --- a/.gitattributes +++ b/.gitattributes @@ -3181,3 +3181,24 @@ neuronxcc-2.17.194.0+d312836f/MODULE_5a10198534c5f2725fd7+165e9558/wrapped_neff. neuronxcc-2.17.194.0+d312836f/MODULE_bc0dc6318052d18d4f59+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_bc0dc6318052d18d4f59+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_b73c22227b6353be7e03+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_014569533dcbafbc3ea9+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_02f045f6902463c49bce+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_1215feca19e3858f9ef6+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_1e78bd200a100a9daaf0+26ac6be0/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_26b84de33e6524d9507a+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_41612d58bf9ba6f268b0+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_7af318ed51d57f96cca6+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_7d17be30edb500bd0e79+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_804dc8509b11b248fd01+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_9840ca94af4106910064+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_a24e3ed896dae389d4f2+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_b5cb392eb50260fa24a3+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_c36623907d50079ba312+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +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 diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/3722d0e82203fbbe93fe.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/3722d0e82203fbbe93fe.json new file mode 100644 index 0000000000000000000000000000000000000000..3691c901541f069077de436fafb30a523f5cfab6 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/3722d0e82203fbbe93fe.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": "2.17.194.0+d312836f", + "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-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/a8be13be525f2d91669b.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/a8be13be525f2d91669b.json new file mode 100644 index 0000000000000000000000000000000000000000..a7a1b611044c6cb7a27610aaddfa11009c0e9f21 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/a8be13be525f2d91669b.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": "2.17.194.0+d312836f", + "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-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/ca40c0099b06c7de4aa6.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/ca40c0099b06c7de4aa6.json new file mode 100644 index 0000000000000000000000000000000000000000..9d5353428471822248dcf59e562f129da521aad1 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/ca40c0099b06c7de4aa6.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": "2.17.194.0+d312836f", + "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-2.17.194.0+d312836f/MODULE_014569533dcbafbc3ea9+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_014569533dcbafbc3ea9+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_014569533dcbafbc3ea9+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_014569533dcbafbc3ea9+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_014569533dcbafbc3ea9+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_014569533dcbafbc3ea9+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_014569533dcbafbc3ea9+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..72cd4b445ebea14ec63c3bd52a3bf74935a45d17 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_014569533dcbafbc3ea9+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d37a05e9076514bd247ba643d2dfb34bdca5f1924f390835ca6431fd5d60cf9 +size 80261 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_014569533dcbafbc3ea9+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_014569533dcbafbc3ea9+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f3ce3ac6393e06ea802e280cf8cf6cc6b1cdd9ba --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_014569533dcbafbc3ea9+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5670fe5126454249b42797df432aedae725b5486cb2d590368215780fceef68 +size 205824 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_02f045f6902463c49bce+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_02f045f6902463c49bce+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_02f045f6902463c49bce+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_02f045f6902463c49bce+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_02f045f6902463c49bce+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_02f045f6902463c49bce+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_02f045f6902463c49bce+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..74f086f9a77ea3dbff4417e7e76d349b09a45f06 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_02f045f6902463c49bce+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1379bf9d9198be3627ce2a98a8bc77592586561dba15736ada02f1a62b03546 +size 46622 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_02f045f6902463c49bce+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_02f045f6902463c49bce+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e4c6c725bf95acdede558533a717975290a90ed8 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_02f045f6902463c49bce+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bf046ebf5a86a78e87113f066962dd06a177293863e91ecea5b65641c65b57d +size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+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_0bbe60dde8eaacbc8218+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f86c6d883b197fa2f2af4bc8ea4e89e342564b74 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e1d6b91a43d0f9f90c646826c509fe753b4689880129a8155140db6a1621186 +size 46541 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..87e225531acdac05008b4336cb15e99cb3529c40 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4868ab12ff273c74e0a4eb1a1631f62a3ff9692ce6df293df4a6d0d808573392 +size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e23051223c3e3d5a42bd38fa7004dc088a2fbe8e --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0bbe60dde8eaacbc8218+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8905529633425558763cbf12d6c6817d71ab06370472e5e67169aa7a59119f8 +size 152045 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0f88705903403514996d+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_0f88705903403514996d+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/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-2.17.194.0+d312836f/MODULE_0f88705903403514996d+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_0f88705903403514996d+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0f88705903403514996d+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_0f88705903403514996d+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d082a2234e7eeaebd09433e05b15ab90d4839531 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/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-2.17.194.0+d312836f/MODULE_0f88705903403514996d+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_0f88705903403514996d+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c3b274d0ef56557a38baccd2d144b3cf5d45f6cd Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_0f88705903403514996d+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1215feca19e3858f9ef6+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_1215feca19e3858f9ef6+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1215feca19e3858f9ef6+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_1215feca19e3858f9ef6+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_1215feca19e3858f9ef6+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1215feca19e3858f9ef6+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_1215feca19e3858f9ef6+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6d19bba5f796281cf6bdab96649c48970e6bcf1b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1215feca19e3858f9ef6+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09596247b06e97404db0e3f45a6e58f5ebefe9afc54db0909b7232a603298766 +size 53803 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1215feca19e3858f9ef6+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_1215feca19e3858f9ef6+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..98a31e148d347c0e24bb57624effdc703a94976a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1215feca19e3858f9ef6+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a688781c302c2ccfe6ce93506b7149064bbc731423ba74ef2621e257d3158b7 +size 164864 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1e78bd200a100a9daaf0+26ac6be0/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_1e78bd200a100a9daaf0+26ac6be0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1f7e03e762be6e5f685a6c8f08ee8ef5c0b6f76b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1e78bd200a100a9daaf0+26ac6be0/compile_flags.json @@ -0,0 +1 @@ +"--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --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-2.17.194.0+d312836f/MODULE_1e78bd200a100a9daaf0+26ac6be0/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_1e78bd200a100a9daaf0+26ac6be0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1e78bd200a100a9daaf0+26ac6be0/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_1e78bd200a100a9daaf0+26ac6be0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..835287151af0189e456c43eabea0e9b2f8710236 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1e78bd200a100a9daaf0+26ac6be0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e79cc303169501720491636df85a8ef222e195d022e9b0af0c8c9a23aa555c2 +size 81609 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1e78bd200a100a9daaf0+26ac6be0/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_1e78bd200a100a9daaf0+26ac6be0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6263fdba458cb3ad8c2d44dd2adb197d76b3d66b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1e78bd200a100a9daaf0+26ac6be0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9f58954fc76cbb93a6552b432728a6fd38d3787465f175ec0145193a4a866dc +size 359424 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_26b84de33e6524d9507a+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_26b84de33e6524d9507a+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_26b84de33e6524d9507a+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_26b84de33e6524d9507a+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_26b84de33e6524d9507a+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_26b84de33e6524d9507a+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_26b84de33e6524d9507a+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..44d2d60463b3c3959fb60fb18e7ad54455b73253 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_26b84de33e6524d9507a+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df65817e2703ab6983c175431e26c37a0ab5ee333592a6575d221e97a643fc5 +size 81115 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_26b84de33e6524d9507a+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_26b84de33e6524d9507a+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..25db6c990a7294a1c4809845638da06b155ea7c4 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_26b84de33e6524d9507a+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:629254561002f6a231db1c9da209fc813092957c8f2d614063721685a2bb1b47 +size 226304 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_41612d58bf9ba6f268b0+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_41612d58bf9ba6f268b0+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_41612d58bf9ba6f268b0+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_41612d58bf9ba6f268b0+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_41612d58bf9ba6f268b0+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_41612d58bf9ba6f268b0+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_41612d58bf9ba6f268b0+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..eb7cac970b8a89127f14f94aa95f7772256988f2 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_41612d58bf9ba6f268b0+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea173b3def731778aae171bcbbb909ddc1467d1eb8304f5dde6f6ef914e45ec0 +size 87577 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_41612d58bf9ba6f268b0+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_41612d58bf9ba6f268b0+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b753a127faa16ee6be99736cb6c2d1f1dfe5602a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_41612d58bf9ba6f268b0+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:747f2f2298b6ad897eedb7a9ae8b4184a1dad89956bfffa354da44231c8d1cd9 +size 246784 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_61794b8717d8b5a8853d+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_61794b8717d8b5a8853d+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/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-2.17.194.0+d312836f/MODULE_61794b8717d8b5a8853d+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_61794b8717d8b5a8853d+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_61794b8717d8b5a8853d+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_61794b8717d8b5a8853d+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ec94b17abac5f40c669dd990e1d18231862b85bc --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/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-2.17.194.0+d312836f/MODULE_61794b8717d8b5a8853d+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_61794b8717d8b5a8853d+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6a5bd59dbc0f17129db225dc56419682e35d3fce Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_61794b8717d8b5a8853d+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7af318ed51d57f96cca6+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_7af318ed51d57f96cca6+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7af318ed51d57f96cca6+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_7af318ed51d57f96cca6+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_7af318ed51d57f96cca6+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7af318ed51d57f96cca6+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_7af318ed51d57f96cca6+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6cf59b185ef0600d8bead608268c2cace1a2f154 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7af318ed51d57f96cca6+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97758a2b3a85873d3978bdcc4ad957312312aadec91e4e6ed596de7aa41731fc +size 47478 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7af318ed51d57f96cca6+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_7af318ed51d57f96cca6+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a0b4cfaf9bedce6c08095241f5d5f72d2b4c6fc7 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7af318ed51d57f96cca6+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7afc2cf7419cc0ec0088f52f3ca452408f18ce12d91004649ec710e00ed064 +size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7d17be30edb500bd0e79+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_7d17be30edb500bd0e79+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7d17be30edb500bd0e79+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_7d17be30edb500bd0e79+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_7d17be30edb500bd0e79+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7d17be30edb500bd0e79+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_7d17be30edb500bd0e79+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f42e36fca152cd98db08f3a0b190d6ca2b1b636a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7d17be30edb500bd0e79+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01367b6b5a410c495ff9d3fa49e16ba09bb17b22715607ce41e30dcaf108db9b +size 87577 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7d17be30edb500bd0e79+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_7d17be30edb500bd0e79+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..255fb28b22bbf89aea66e2d6e6f0e36415d7a396 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7d17be30edb500bd0e79+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55614536bfcab0b8aa8783521e0ebffff16849c91730f0a25f0137121fa6b906 +size 246784 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_804dc8509b11b248fd01+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_804dc8509b11b248fd01+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_804dc8509b11b248fd01+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_804dc8509b11b248fd01+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_804dc8509b11b248fd01+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_804dc8509b11b248fd01+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_804dc8509b11b248fd01+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d0b8fb4b3ce39ae848a26ded374fb5f358fa2b53 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_804dc8509b11b248fd01+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69fab159e3098155acc2dd737cb7adce6353a1c7bf3bca3f51cff88057fef535 +size 80261 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_804dc8509b11b248fd01+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_804dc8509b11b248fd01+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..87d7a0a5bb0c80f200f3850ee8b3a3dcd4fe2c90 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_804dc8509b11b248fd01+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3154d6105d0857d02a151e1d1a162d16f36348e806cae1ea0e15e14a34febcda +size 205824 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9840ca94af4106910064+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_9840ca94af4106910064+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9840ca94af4106910064+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_9840ca94af4106910064+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_9840ca94af4106910064+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9840ca94af4106910064+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_9840ca94af4106910064+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bc6fdd05ac93c21973f441c388a4daf857f8e8ed --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9840ca94af4106910064+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1919885a02be2064c711ae65035e0c7f1592e09f4dc17fe27ee5081ac6ed73 +size 81115 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9840ca94af4106910064+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_9840ca94af4106910064+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..38f2981864713c370d63d29831b928f12960bb98 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9840ca94af4106910064+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90cb39827c570734c13db14880848dd9218398c05064a113856d7c86f3de5f30 +size 226304 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a24e3ed896dae389d4f2+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_a24e3ed896dae389d4f2+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a24e3ed896dae389d4f2+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_a24e3ed896dae389d4f2+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_a24e3ed896dae389d4f2+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a24e3ed896dae389d4f2+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_a24e3ed896dae389d4f2+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1e653f5abd669a492651c4f0f37d8a1f73e1b34d --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a24e3ed896dae389d4f2+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65f5fcd3424c4f630c535e174ec02e8aed0d785d1324f9cb78490d2d063b9de6 +size 50076 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a24e3ed896dae389d4f2+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_a24e3ed896dae389d4f2+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4539901218d38e30c26dd7992d202a070bd0bd32 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a24e3ed896dae389d4f2+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e3cc16666ed2e0b5ad3b24c55223a34599bfcb1693daeecffc5045480f65baf +size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b5cb392eb50260fa24a3+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_b5cb392eb50260fa24a3+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b5cb392eb50260fa24a3+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_b5cb392eb50260fa24a3+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_b5cb392eb50260fa24a3+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b5cb392eb50260fa24a3+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_b5cb392eb50260fa24a3+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4acd04ac2dcb327c4966f318ba1dadf537240257 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b5cb392eb50260fa24a3+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22818ba046b107b573affc6921007ba42a0f09d420366d35ada951a6b3f4f681 +size 83712 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b5cb392eb50260fa24a3+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_b5cb392eb50260fa24a3+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7433c69bd3745cca856c6c4158a88518a9d83df6 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b5cb392eb50260fa24a3+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecc685cb7b1d8c410900db5fea2dfb6acb717cbf289f0ddc5da0757e4d13379d +size 175104 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+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_ba9e5f7f86364cb7b38d+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3b092bed410c6797b9f270b5623407482f995b4b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cee2d35f3a2ffaa555bdb67cbc9f8914afce3ec1209c1d68a86841fbc69e38f +size 83281 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1dcc2036678bf76964bef24ef3aabc923a60c7ce --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d17949c26936f8d25749d4146190b37faeaf3fa5ff13631ebfe2a919dfc45cfa +size 185344 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b075203ee721aa0476daccd560d350feaf0afd85 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ba9e5f7f86364cb7b38d+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7869fdca9c9fbcca495ce0d3c309a6b02af9f4351fc4ca9dffd6e41bb58e0e48 +size 193114 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c36623907d50079ba312+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_c36623907d50079ba312+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c36623907d50079ba312+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_c36623907d50079ba312+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_c36623907d50079ba312+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c36623907d50079ba312+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_c36623907d50079ba312+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e1e4842fffec9bb46a6eee13ef8e68ab78983a64 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c36623907d50079ba312+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b0fae1af570970c8a697b10a4dd46f954692bbca6671f769bfd5910aedae839 +size 83712 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c36623907d50079ba312+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_c36623907d50079ba312+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4bc6de862cf75a9e3c20f5b72c3453f16263679a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c36623907d50079ba312+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44f38afceaff2b3c2d0a410b96ba1e878d6f165caab12fd62fc251330397daf3 +size 175104 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+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_cb76f3926e2853557294+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a8f2f6365b6f17ca502d74d662e9b72953b48de0 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0f01bbdf4f06860c7ed88e56cddfb3f8df3d89cfc46dc5353768d8e4abaebd9 +size 83281 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0321b60f0da0cca96385e7871140f08367ee8fbc --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:202b4e1c2d092a28057805718697d82ef1c078f523e48396a30cc03412dc77a0 +size 185344 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b084aaeb60ecfa034925cf619e75cf620ff95931 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cb76f3926e2853557294+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81ce70ca44d2d776452aa3612ba5ebe0927189cb677592ffcabc09253868b534 +size 193114 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d1e2c47cd5166e2d7503+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_d1e2c47cd5166e2d7503+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/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-2.17.194.0+d312836f/MODULE_d1e2c47cd5166e2d7503+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_d1e2c47cd5166e2d7503+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d1e2c47cd5166e2d7503+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_d1e2c47cd5166e2d7503+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..352b248b21ba0cc47d619c4b1f971076cc4ae699 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/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-2.17.194.0+d312836f/MODULE_d1e2c47cd5166e2d7503+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_d1e2c47cd5166e2d7503+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cfda60609ab1b5a7894050af528fb4a3c2135716 Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_d1e2c47cd5166e2d7503+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_dea3fa0fa1232db56e94+26ac6be0/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_dea3fa0fa1232db56e94+26ac6be0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1f7e03e762be6e5f685a6c8f08ee8ef5c0b6f76b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_dea3fa0fa1232db56e94+26ac6be0/compile_flags.json @@ -0,0 +1 @@ +"--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --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-2.17.194.0+d312836f/MODULE_dea3fa0fa1232db56e94+26ac6be0/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_dea3fa0fa1232db56e94+26ac6be0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_dea3fa0fa1232db56e94+26ac6be0/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_dea3fa0fa1232db56e94+26ac6be0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..157c6134fb9836e3dfe38913c20059ac9dbbefc8 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_dea3fa0fa1232db56e94+26ac6be0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff33db0f32b8ac97fa777866ddb0d0a3600c9ec2dae5f50134e540cfcd4d344d +size 81607 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_dea3fa0fa1232db56e94+26ac6be0/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_dea3fa0fa1232db56e94+26ac6be0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7e19311b08287ccf9404a513608375c2097f1396 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_dea3fa0fa1232db56e94+26ac6be0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b971aa7d9a9389cf21b9af3dfb1d228bdddf84978a4777ac90758cf0cf68c427 +size 359424 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_f3e8207126f92d912816+26ac6be0/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_f3e8207126f92d912816+26ac6be0/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..1f7e03e762be6e5f685a6c8f08ee8ef5c0b6f76b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_f3e8207126f92d912816+26ac6be0/compile_flags.json @@ -0,0 +1 @@ +"--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --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-2.17.194.0+d312836f/MODULE_f3e8207126f92d912816+26ac6be0/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_f3e8207126f92d912816+26ac6be0/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_f3e8207126f92d912816+26ac6be0/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_f3e8207126f92d912816+26ac6be0/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f5d031d6cc7473bf839041968a748c5e5634310c --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_f3e8207126f92d912816+26ac6be0/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60dfdc9203fbfc155e6bbad4c2c73a58a9d23c13bc691bbb339fa0909e137b98 +size 82456 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_f3e8207126f92d912816+26ac6be0/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_f3e8207126f92d912816+26ac6be0/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8348c7a017a97e3419697fea2f9d7905eed51d5d --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_f3e8207126f92d912816+26ac6be0/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:782b273e6a479f7053648d1066d3567bde3960659f87769d0970d0c14be19b60 +size 420864