diff --git a/.gitattributes b/.gitattributes index fa29e20e23bf0593adc743d2cba4d0cbfbeddec7..883b9ef8d9505eaed08c746d5172b8ed0f915640 100644 --- a/.gitattributes +++ b/.gitattributes @@ -3438,3 +3438,31 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_e752b6d369dd13e651a9+ed72d204/model.neff f neuronxcc-2.19.8089.0+8ab9f450/MODULE_5ba89bbb07ae57870f9d+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.19.8089.0+8ab9f450/MODULE_7b3c7ebc2d0673f07a89+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_0319ecab9682f42a2e0f+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_313796881a2973827e21+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_4242784510489555269+e30acd3a/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_8704cbaf0ac16e5d3ac0+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+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.dev2/llama/Maykeye/TinyLLama-v0/d8f06ba7bd2d5076813a.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/llama/Maykeye/TinyLLama-v0/d8f06ba7bd2d5076813a.json new file mode 100644 index 0000000000000000000000000000000000000000..043f1627c0ec6edb5c2eb751441e2768e16a24ec --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/llama/Maykeye/TinyLLama-v0/d8f06ba7bd2d5076813a.json @@ -0,0 +1,71 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Maykeye/TinyLLama-v0", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 256, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Maykeye/TinyLLama-v0", + "checkpoint_revision": "298338802ab94432b917bcce11382aa151aee50f", + "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": 1, + "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": 1, + "vocab_parallel": false + }, + "num_attention_heads": 16, + "num_hidden_layers": 8, + "num_key_value_heads": 16, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/llama/Maykeye/TinyLLama-v0/f1af079d52e1e2ac6a68.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/llama/Maykeye/TinyLLama-v0/f1af079d52e1e2ac6a68.json new file mode 100644 index 0000000000000000000000000000000000000000..290a3839805ab3aec9cf6f5276d517bdca83c622 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/llama/Maykeye/TinyLLama-v0/f1af079d52e1e2ac6a68.json @@ -0,0 +1,71 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Maykeye/TinyLLama-v0", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 256, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 1, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "Maykeye/TinyLLama-v0", + "checkpoint_revision": "298338802ab94432b917bcce11382aa151aee50f", + "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": 16, + "num_hidden_layers": 8, + "num_key_value_heads": 16, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/granite/ibm-granite/granite-3.1-2b-instruct/c7927a430db3da5413ec.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/granite/ibm-granite/granite-3.1-2b-instruct/c7927a430db3da5413ec.json new file mode 100644 index 0000000000000000000000000000000000000000..55b914b892523c263c53c29a0264797426655493 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/granite/ibm-granite/granite-3.1-2b-instruct/c7927a430db3da5413ec.json @@ -0,0 +1,73 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "ibm-granite/granite-3.1-2b-instruct", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.1, + "attention_multiplier": 0.015625, + "embedding_multiplier": 12.0, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "logits_scaling": 8.0, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "async_mode": false, + "attn_kernel_enabled": false, + "batch_size": 4, + "capacity_factor": null, + "cc_pipeline_tiling_factor": 2, + "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", + "checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d", + "continuous_batching": true, + "enable_bucketing": false, + "ep_degree": 1, + "flash_decoding_enabled": false, + "fused_qkv": true, + "glu_mlp": true, + "is_chunked_prefill": false, + "local_ranks_size": 2, + "logical_nc_config": 1, + "max_batch_size": 4, + "max_context_length": 4096, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 4096, + "neuronxcc_version": "2.17.194.0+d312836f", + "num_cores_per_group": 1, + "on_device_sampling": false, + "optimum_neuron_version": "0.3.0.dev4", + "output_logits": false, + "padding_side": "right", + "pp_degree": 1, + "qk_layernorm": false, + "qkv_kernel_enabled": false, + "rpl_reduce_dtype": "bfloat16", + "sequence_length": 4096, + "sequence_parallel_enabled": false, + "speculation_length": 0, + "start_rank_id": 0, + "target": null, + "torch_dtype": "bfloat16", + "tp_degree": 2, + "vocab_parallel": false + }, + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "residual_multiplier": 0.22, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 49155 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0319ecab9682f42a2e0f+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_0319ecab9682f42a2e0f+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0319ecab9682f42a2e0f+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_0319ecab9682f42a2e0f+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_0319ecab9682f42a2e0f+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0319ecab9682f42a2e0f+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_0319ecab9682f42a2e0f+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5063cf43e26d64e56dff35b5700eb167bb0f10d4 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0319ecab9682f42a2e0f+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:934c016f62b55da98d34e488bae8668f0b80b8d8cffca713f1b6fdfb9fccd7da +size 172596 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0319ecab9682f42a2e0f+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_0319ecab9682f42a2e0f+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b5b8809bdc3ddb0e3efaf321fec9285e0fafd108 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0319ecab9682f42a2e0f+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2983205a24f11d46e328ab17234974421fc4f4e5a8101d18d37978d42f27ae24 +size 246784 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_12627483106468160534+e30acd3a/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_12627483106468160534+e30acd3a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..32157f229be17480afc9e02a7ed48ca0cbc8f22a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_12627483106468160534+e30acd3a/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_12627483106468160534+e30acd3a/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_12627483106468160534+e30acd3a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_12627483106468160534+e30acd3a/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_12627483106468160534+e30acd3a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..da2098de6eaea3dfd4ad659decc833e82df603c7 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_12627483106468160534+e30acd3a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:002e7281f5713839b44010c4b90bfe6476fd6e72e142bfc561d0de77bb7c5347 +size 444 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_12627483106468160534+e30acd3a/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_12627483106468160534+e30acd3a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a2f0c5306925e900d7c9a3357146f3bb2f6ac1b9 Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_12627483106468160534+e30acd3a/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_14de102a7c791bd95a24+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_14de102a7c791bd95a24+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_14de102a7c791bd95a24+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_14de102a7c791bd95a24+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_14de102a7c791bd95a24+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..da4dd26eb7e977ad385b86cdc9f23573db3806bc --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_14de102a7c791bd95a24+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14ae716665e1a9c8c9d6031d935826ba4851b717286599b7a4c58d954408bd73 +size 18983459 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+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_24e323acf78ef5eda141+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2509107bb4fcf0773268484f1ec826c73a179769 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:128a9a7fa2e0978562d62144e988bae68a25f5540399826d15122d09e8bcefad +size 94870 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6f6630ceb919d1640434a48b4e6e52f95cc79a60 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4688b6fdcd8bb37955378d8d814f6308a576b67b1fbeb99ad9f01f03af54364b +size 697344 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2694a475d72d88e21f3be6f8f2f58699ff762e36 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_24e323acf78ef5eda141+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a004b787431d850901f0d55e2f907a20bd1ae0641492e86aaa2de713d41168c4 +size 719418 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2598f2596057e1346614+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_2598f2596057e1346614+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2598f2596057e1346614+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_2598f2596057e1346614+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_2598f2596057e1346614+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f14ff94c28eb71797a1819e525c6c696394273bf --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2598f2596057e1346614+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f0e5b28f8af837880b36cc46c7841e32fa2d3d182bd446f42aa4c64c12dc984 +size 52564523 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_29474e39f37931275586+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_29474e39f37931275586+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_29474e39f37931275586+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_29474e39f37931275586+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_29474e39f37931275586+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_29474e39f37931275586+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_29474e39f37931275586+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..aaf0a5daf821b97d61109b455e696af8fae822d1 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_29474e39f37931275586+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad46fd05ebf2e4017087e0f3d35d9fddbb73ab8d311d8b92a3aab43cfc49aaf4 +size 25857 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_29474e39f37931275586+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_29474e39f37931275586+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..667631e46629420d7b15bd2591754101a03e40c7 Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_29474e39f37931275586+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_313796881a2973827e21+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_313796881a2973827e21+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_313796881a2973827e21+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_313796881a2973827e21+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_313796881a2973827e21+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_313796881a2973827e21+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_313796881a2973827e21+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..95c6c397312c98e31d2f1bd476e30fad262e6e0a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_313796881a2973827e21+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8f1e698fa23c2e5951644290686c8f13b4beb75a9227b943568f8cdebad7796 +size 172361 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_313796881a2973827e21+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_313796881a2973827e21+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..96fc48d8fcaecf0b73d1c4d0565bd626226d55c9 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_313796881a2973827e21+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e02708ac46a0c44c69b51532b77058ff134f18ca27729d890d80af8f0212e2e +size 2243584 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4242784510489555269+e30acd3a/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_4242784510489555269+e30acd3a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..32157f229be17480afc9e02a7ed48ca0cbc8f22a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4242784510489555269+e30acd3a/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4242784510489555269+e30acd3a/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_4242784510489555269+e30acd3a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4242784510489555269+e30acd3a/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_4242784510489555269+e30acd3a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3ee48e6b0a5b6e9dd48e64049d89d2981d95e328 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4242784510489555269+e30acd3a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c96868686ca6df16e3a140bd0cf614740d8817d40ea268707bdbb4724ac5a7cf +size 75607 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4242784510489555269+e30acd3a/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_4242784510489555269+e30acd3a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0dbc380e11eebaa8c7ef08653f2c70118a63e7a6 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4242784510489555269+e30acd3a/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a07c8d2be4d29dcf50a9b108f0d3f8360ac63be1248806704fa075c1cfc551 +size 7097344 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4585214586228082616+e30acd3a/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_4585214586228082616+e30acd3a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..32157f229be17480afc9e02a7ed48ca0cbc8f22a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4585214586228082616+e30acd3a/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4585214586228082616+e30acd3a/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_4585214586228082616+e30acd3a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4585214586228082616+e30acd3a/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_4585214586228082616+e30acd3a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..aa36131c0801c8f8ddabcc524ef6114ad81c855a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4585214586228082616+e30acd3a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b432b2f785ef8e9c680909d44b1f4a240b786a1921ca0694a010f5cc8e34a33a +size 488 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4585214586228082616+e30acd3a/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_4585214586228082616+e30acd3a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..76753a7609178a775e6f2ee246c461386eef0681 Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_4585214586228082616+e30acd3a/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_49b8463ac655cfcc0b60+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_49b8463ac655cfcc0b60+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_49b8463ac655cfcc0b60+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_49b8463ac655cfcc0b60+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_49b8463ac655cfcc0b60+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f8f931b2a49733cb07750688cc4bb1556aa4ee94 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_49b8463ac655cfcc0b60+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:192c055b31e9c41e5a0532ac236e2e0b286dbd541f739d5780d5b1d863b7c23a +size 359350 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_57b107bd0499cc4986ac+63ea7cf2/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_57b107bd0499cc4986ac+63ea7cf2/model.hlo_module.pb index afffa841e449ce688f60fa67e2ddd85ec5c4f619..d14326d4a969b38336ad183ba7407b7df78c1ac3 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_57b107bd0499cc4986ac+63ea7cf2/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_57b107bd0499cc4986ac+63ea7cf2/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a914031f26bb159d35140c96a1bdb74370696834acf754811e40b142622a02a4 +oid sha256:e7cb531f40791a4bc8781299062f1dff17030241665ab6a7f42cb8e3161285ec size 68277 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_57b107bd0499cc4986ac+63ea7cf2/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_57b107bd0499cc4986ac+63ea7cf2/model.neff index f05f0440ba8fbf1e2b84f53d5d9cd934c922ada1..1cba686fca2c4cf2c89af0ec8dab8946051a11ab 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_57b107bd0499cc4986ac+63ea7cf2/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_57b107bd0499cc4986ac+63ea7cf2/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c868ec53737adc2fe50d3708f1a3cedfc2e769e9e5d707555376ee2a9a153028 +oid sha256:92cc1588cd47c084f1bb989150b17e6c000400dc5fd117a11ffcc67738121dd9 size 257024 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_57b107bd0499cc4986ac+63ea7cf2/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_57b107bd0499cc4986ac+63ea7cf2/wrapped_neff.hlo index f548660752bacf35688072c6129732ee7faa9c99..4acb6b824d1deefac76f3e4367ae7be6d658c0c6 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_57b107bd0499cc4986ac+63ea7cf2/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_57b107bd0499cc4986ac+63ea7cf2/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9eee4b03603e48bfdd262029efc30ecd40c1dbfcb10b94f627cf4e6696aa82f6 +oid sha256:64b9b899e22590f54644e24b7099b1d575db60ae12f2145dee479fe538013a36 size 268322 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.hlo_module.pb index 79821ea13dc5fa0fb23ec9ce0b3250aeeb76cd21..655824d477944d6ee3d25958ed00aead4f38d940 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d161deceb48f8f73a0aa6227a14f23c73b193b8c2f54ec986673930820610f16 +oid sha256:4c72a13fb767a6fe25407888d3085e20d62771714a0ae5df978f373d454fa1c6 size 82456 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.neff index fc0cf51ec756a04602b50666d17b7f72c0b59126..7eeaf873ac7fa4507d95e4f649aed9b800fb9efc 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:06018e131b181177574a276f6294a56b20726b844088fb5bc1b9799f8bc4eef5 +oid sha256:7668d4bd5f98b2af1e738ec0794a4c2767b5d87a34e0b4ad8f63bd27074586ea size 420864 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+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_6708f635794756c6254f+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7dc4d053443bcea09a76f85e520f27c296b6ed20 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fef8e7bcc22a6722ea6c0ab45ad76f020afc8ad127b2d6f54bbd0574cc20225 +size 359350 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6c4c27e7c6d3631da930e115e201d4663c2091ab --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aa5446a880f3b507535c535e296e9aeca2e98a7c65bf0d3c920badaefd06346 +size 779264 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..5f02ad0ffeff2b1d9fb8ab44fc71f50bbeb29e86 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6708f635794756c6254f+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:789ab784ae3447d5c7ce4adbd584ec9100168fac33c2c005070a0b28ee6e7a17 +size 799726 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6bb5680c622866b3b45b+63ea7cf2/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_6bb5680c622866b3b45b+63ea7cf2/model.hlo_module.pb index d0471536c974eb79071f7b2a0bef7036603852b9..e563114700419bed6f118aac7780809d3c5e77ce 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_6bb5680c622866b3b45b+63ea7cf2/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6bb5680c622866b3b45b+63ea7cf2/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:12aceb27cdf723d91c999dfa8673d18f8cdabe145b276c11445d19e86a5f5145 +oid sha256:731053ba55bcb60ea2044a7fa7431cc686e531e8750bd9abb746b7f014a2aee7 size 79431 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6bb5680c622866b3b45b+63ea7cf2/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_6bb5680c622866b3b45b+63ea7cf2/model.neff index 88effe4efc36aebec75802e3d1faaa6ce8865d8a..4542d7663da6900db5c61de60bf309ad598b9940 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_6bb5680c622866b3b45b+63ea7cf2/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6bb5680c622866b3b45b+63ea7cf2/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6cc031ed02ba0c6ba5aa974a455517d4c142fb3079c57115af3c0a4117b4e9f4 +oid sha256:cecd0701462f5d148e6d9fdf70356ed5c341dba17baca211688c57fde663d264 size 318464 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6bb5680c622866b3b45b+63ea7cf2/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_6bb5680c622866b3b45b+63ea7cf2/wrapped_neff.hlo index cef965a2ce7c068c231f830c322b85e1f616015b..5e8418135297d42a5b698a8005dd822287c69da6 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_6bb5680c622866b3b45b+63ea7cf2/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6bb5680c622866b3b45b+63ea7cf2/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:85e3ceea8c3aeb3881b637508b4f0bd79debc800f3a70ebf651b7c68f3ee8665 +oid sha256:1470a688269b5037612f8b99b5483a98d4e47ad810741ca70767476c76e1cbaa size 329762 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6ce6eca90c4f1a30ccbd+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_6ce6eca90c4f1a30ccbd+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6ce6eca90c4f1a30ccbd+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_6ce6eca90c4f1a30ccbd+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_6ce6eca90c4f1a30ccbd+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f1590c09824d3c18afee3f0d033c82b4c7e90278 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6ce6eca90c4f1a30ccbd+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e17f832f27bc348872b7110abaa245be25f1de9ce505fafc322b9db9fb2a21c5 +size 359350 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_715e1f3bb83370751f5c+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_715e1f3bb83370751f5c+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_715e1f3bb83370751f5c+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_715e1f3bb83370751f5c+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_715e1f3bb83370751f5c+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..204434a2b232e167b38734988f10a9026637102e --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_715e1f3bb83370751f5c+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a43a88f28fe607fdef6a5dac9f4c972e1673fa25df1273247aebc01b50723fe +size 207947 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+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_71a7e6b24554e80fa037+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4ddfa6b53017b9abfc820c8d0ee48f64b736a83a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:276a9df5d9b6d2704ff32c94846e5e08cbf3508bd8541b1848eef46b3f9a5851 +size 251904 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..55c1b02e019c97df130dfb9539f218c86cab4f99 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3ba93136bfc1503d4c8dddd052a93c8eac64da56e5ec1bf60a81c133795c86c +size 707584 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7c4ba5e01ade32d49643c89598591389dc42620e --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_71a7e6b24554e80fa037+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:934789d6fe928dc4b33545e8f09127463de544152dd8364e977ffa8ce9eb7c04 +size 729658 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_755a9113784f92f12a48+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_755a9113784f92f12a48+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_755a9113784f92f12a48+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_755a9113784f92f12a48+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_755a9113784f92f12a48+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bb73a309f4e3751ce091a51eefa0abf94afbd10d --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_755a9113784f92f12a48+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19c5d69d11fc1869c1962e5704fc49cfb6f37ea7a7f42dc8ab7effd89c5bfb07 +size 18983459 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7595713450919123700+e30acd3a/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_7595713450919123700+e30acd3a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..32157f229be17480afc9e02a7ed48ca0cbc8f22a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7595713450919123700+e30acd3a/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7595713450919123700+e30acd3a/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_7595713450919123700+e30acd3a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7595713450919123700+e30acd3a/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_7595713450919123700+e30acd3a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..85f8370196403cca6e7d8dfa07b9e1c12800033c --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7595713450919123700+e30acd3a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0d04a5a3d94248e40d4de89a22fd9424fe1f0793a9114fb140844984ee1dbfb +size 15570 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7595713450919123700+e30acd3a/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_7595713450919123700+e30acd3a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b36c7b2bdb63817113e1595663eb5abea30d7a33 Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_7595713450919123700+e30acd3a/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7633fdb9d6885e10e7d4+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_7633fdb9d6885e10e7d4+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7633fdb9d6885e10e7d4+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_7633fdb9d6885e10e7d4+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_7633fdb9d6885e10e7d4+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e0e07f140ae69b5635d0a6a5d3bea50c6ffd12a5 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7633fdb9d6885e10e7d4+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3b38b00fb041f13d8f6299b73b9514bb6ec1527b13433917e53af6b1bd3f86c +size 107652 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+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_7ff50e368ec1bcc50af3+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4a9aceaa676bd2db7387668272fc8c22ba8c7414 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80e9e00de69ebc021a24c4a84a332c6ce9fafdc97ce9f595ecce1e08daca6cb3 +size 377857 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e3f9309564ab2aa1a826624548e8abaeb6296171 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2672614b5483ff963fafb5b4a954a61ebede28e0f4567345d2b51a178896e456 +size 779264 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..5a7425effe06e02b0d561594df9f1f9ce96508d1 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7ff50e368ec1bcc50af3+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:985cba728106d4869c349399fdeaa6a4fbaab9f51f0226f05fc6cd7ef40683fc +size 799662 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8285caa442ab17fe0e5a+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_8285caa442ab17fe0e5a+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8285caa442ab17fe0e5a+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_8285caa442ab17fe0e5a+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_8285caa442ab17fe0e5a+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..58c293294d201aa9270368f02fb270e7b430ee7e --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8285caa442ab17fe0e5a+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfd079078bdc0a6fa8e0c5bc2e0be2cb7115d7e41728ff2fb96d41feac77b7c6 +size 258786 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8704cbaf0ac16e5d3ac0+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_8704cbaf0ac16e5d3ac0+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8704cbaf0ac16e5d3ac0+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_8704cbaf0ac16e5d3ac0+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_8704cbaf0ac16e5d3ac0+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8704cbaf0ac16e5d3ac0+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_8704cbaf0ac16e5d3ac0+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b6ba05dc9fb32c41dba425a30557732560d56c34 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8704cbaf0ac16e5d3ac0+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:621a68ab7f3abf4a3db064b9ab3e5a4ff4f64b93b5c748accd28d3f791df3fc8 +size 187835 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8704cbaf0ac16e5d3ac0+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_8704cbaf0ac16e5d3ac0+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2b94d3d14cd4ea20633c4fa6e65d26987447f1bb --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8704cbaf0ac16e5d3ac0+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd21b26ad0fad5a93818e871788c8fb6cca30c272241037e1d7c905744fbfd7b +size 236544 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+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_89f903d621d68d3a2cf4+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9a62472a1f3d88172768c0e39c14e19bac4d72f2 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a726bb5dbfe79cf40e462f2c54d7f20cba587aaa6b76003fdedf729e721aafbf +size 359350 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..687687befa1d550b3450139d646be2fdde956702 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67892542f08b178b92c5a77c530390f362180d67d53c6a4bf76847b8687741b8 +size 779264 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..be05cf9df0ea369992e10f76b659919e13f07c8f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_89f903d621d68d3a2cf4+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:473a5e40fae7b1bf6403bf551f6ea61cc104965c6a395801850c0fb62fe1d0e7 +size 799726 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.hlo_module.pb index 1bdc74a0eafc195859d6af6644f9101ad6aa191c..e526506873c908a96b959e4c2c79b1fbfa26ac25 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6d96dab97289c7e8f0f86606e3e28fe6ba499bac93101c635261281f994837bf +oid sha256:eb1a3918f1d35a40bdaa63ca2ab0414530c2e6f67355299fb1cf3dca6b849c47 size 81609 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.neff index 34f64f6887c50a3088115cc2cf3f5d385f17a42b..c8bdcc937d596649cee5f384dac0a8c4fa70b25c 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6283c2b8221af2ea89f2bedbae48a1b2f8d7fb42b4e630fc3ad3e16519d01b14 +oid sha256:77a270efdbffb9c3038c8583bfef6090ea5f2f00a09a5f919b96c74fcddb14d7 size 359424 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+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_975d14574546c97dc994+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3924b566ba18caf2a58e3e2626358a3ee1c4c77e --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58c54990aff64ecab92926eb63a98e8644b980abc2be717bdc40b1020dff9501 +size 184709 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..af2ee0e713cda0baa968fe3e72a93ece2e4d5a89 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:446195dcb8449fd7388d5f0eb5523209e3e81231f593cb95f2982d357280ba34 +size 257024 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..77bdaaf7bc99c5bbf3178dd583a3829ee7335930 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_975d14574546c97dc994+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a100903386d077dc5ee71e3c399ecd6c63e212c36610c40d8dfc6038dd67b6 +size 284585 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.hlo_module.pb index dfb693ace671cd73ce87864901167380f35d8714..7e219e2d6c59ede192f4f732ea4316c0d0a612d1 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:316aa6d670ec51cbf810083a84be88f91b1bb9cbc07460058f55b9f20cc9dfc2 +oid sha256:d8870e76fed555598af6cb631f0f764e8e1804fc1dab8c94bd0054ee172bdeba size 81607 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.neff index 62d26cee4accfd5ca4134e04b93782442a2dcafd..42a4df1c986c949c51b9c3b67534564145e40f22 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6613c5481ae06b85bb8abb953bc30cc50c4addff26b3478d9e71c68116482f9d +oid sha256:08db08ccd4d705d4f63a0c7fa0468ba421d78943b9197b55e3351d76fdebd7e5 size 359424 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9b0fc2c8f9c7e0f183ed+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_9b0fc2c8f9c7e0f183ed+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9b0fc2c8f9c7e0f183ed+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_9b0fc2c8f9c7e0f183ed+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_9b0fc2c8f9c7e0f183ed+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7b04c51a2ebbfecb138885e0d4000302826397c0 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9b0fc2c8f9c7e0f183ed+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90c2f5ae48278ff47a7c23bfa9674e48665687a7efa17ce9021cbff2570bc44a +size 359350 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+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_9b17218ed71a6f1040ba+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9bb5407aa3d3aec26bbec7ef1ae4044cb1f56676 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:788ad2d0c5885923c8d1c86349a4ac13b185333675d39e318cecbbc2cd4c5096 +size 258786 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c11b544fc3acbe4328a6a6117d6bea67b57796a9 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2badcb2f5371ab20ef550dac35c0305029f98c59e84c874d7bfe993482427e4 +size 707584 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..be2196cbe096949f8f1a29892fcc920e98424552 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9b17218ed71a6f1040ba+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f5dda86664af798a681b098f1d3aaca06ced99383388d9f7ed018acc2666fe +size 729658 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+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_9edc34cdab9401830e43+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..00729428d86d4b2e3baba7fed7345777a4e2aae8 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5231e758649800cee850c9857bbbd3ec83e7c1ee0288a862ee9081e1c3fc1939 +size 251816 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f3b5b3e3f862ce47b0bb4a2d7f7b06f159cf6de7 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:360379fcf5547a1224a9431c676601384c0a9fe3aa4f2280cc55c5ebf10bd8f7 +size 707584 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1b1e64a52cb0838d8b4ca161c6aebba642ef4886 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9edc34cdab9401830e43+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:742426723a5671ddd876045c04684bd45ac2e31972c9c0278727aa7498e25207 +size 729658 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a497e5bb9a8ad9c71727+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_a497e5bb9a8ad9c71727+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a497e5bb9a8ad9c71727+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_a497e5bb9a8ad9c71727+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_a497e5bb9a8ad9c71727+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9799310e9f64a47bfbd89ec50e5a6d51d09cfcdc --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a497e5bb9a8ad9c71727+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77bac5f327fdc8ccec4aa55420a20eff41d510b6e33964d0da042d53cb071ec9 +size 352379 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+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_a9fd63d01e95973c2777+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..28ab3939b5ce8c39f50ec963c610c00c90d11a8c --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9253e675517f66708f979aaa39b7885da8a8275f163e29460d2ac6eeebe2efc5 +size 359350 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..cf4f86400cd64a8fe442f70aaab5dfd324b714d6 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8bc90e38b0ef0bac4c0d627e6bb3b8325580288bcb13e721967222f0451ed63 +size 779264 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fe7e78f937be41d4ca509fa659494c4113615e87 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a9fd63d01e95973c2777+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc35adcd17c17d1fd9c3929f6cb0aec94f376398173cc59fb4513020df3a620 +size 799726 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_adf36f177d1c5c9d8f5c+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_adf36f177d1c5c9d8f5c+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_adf36f177d1c5c9d8f5c+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_adf36f177d1c5c9d8f5c+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_adf36f177d1c5c9d8f5c+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..997afb8014575dde2e2220e94a80cf7a201e7a2c --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_adf36f177d1c5c9d8f5c+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e1288a8b0feb3895d157ad19738ae7f2f9531ed38572c8425c7f6fa0bc2da05 +size 52546275 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ae5ca4b91afd03b04b25+63ea7cf2/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_ae5ca4b91afd03b04b25+63ea7cf2/model.hlo_module.pb index 63bade6fe33bdcabbe374697a199c583beaa86ac..786001f47a68e2e1eb8a6bad7b29b6b85608392f 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_ae5ca4b91afd03b04b25+63ea7cf2/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ae5ca4b91afd03b04b25+63ea7cf2/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7bf1de332dd0f1615aa9bb39e8b50034c3b02b64240d386640900156271b83e8 +oid sha256:21f7625d7b35da2731995b7f623bc680975b372daf4a86ca7b6998d64139f504 size 68279 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ae5ca4b91afd03b04b25+63ea7cf2/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_ae5ca4b91afd03b04b25+63ea7cf2/model.neff index 989c6760cfa21e0268843829089881d5a41aa68d..8fdb666d57ae2e0e0b49919f29206b3d93c58d25 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_ae5ca4b91afd03b04b25+63ea7cf2/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ae5ca4b91afd03b04b25+63ea7cf2/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c809a8eebc804bd1bd9bddf1d8d93146a057e5c1d57af08032b900a9ab6d0830 +oid sha256:94fa9c424e11aab9a10dfdd1be8ed0037885a5337c7eab9307e408d35eea779a size 257024 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ae5ca4b91afd03b04b25+63ea7cf2/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_ae5ca4b91afd03b04b25+63ea7cf2/wrapped_neff.hlo index cabd02a122eb8e39ecea3857ed75e5d0fbe86dcc..4a3cdbbe25cfb99f63c8507b135eab7024fc6c22 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_ae5ca4b91afd03b04b25+63ea7cf2/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ae5ca4b91afd03b04b25+63ea7cf2/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e3a45648500fccd8d6bada22f3ccf68bafd048f7a678b92125321c7667da7b02 +oid sha256:74ab82d014c864db4cfc5525eef1d8ce5d5cf117fad382a6799f3731a675eea1 size 268322 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+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_b267bb985f633378c63a+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e6d2e7a3a659e918ac1a23851dfe879a057f2606 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc0d3885045ba154886044797a417f7067ffcac4a81186fc4d9f17061630141 +size 199879 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0313b55299f9846815453457f8ef9a110c313edb --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fe7ceba40480693c401b16b176d75e9599cff81c632ddc024fe571dbb9060be +size 246784 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d17b4ac566dd5370bf1b12cec40dc9adc47fb405 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b267bb985f633378c63a+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77c75ebc122d4c24812b57947c3ebf74d8640b9fddc52f4f91ef87474b5332e6 +size 273916 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_bd04f00623dc9f230295+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_bd04f00623dc9f230295+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_bd04f00623dc9f230295+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_bd04f00623dc9f230295+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_bd04f00623dc9f230295+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..355290074ae0a13abebe5bb347e84b2785688191 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_bd04f00623dc9f230295+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0414870ab67f190c5ed4369bff0efbb221fd90e5df1fc89dd34acc3589e4a0c +size 207947 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c628edfe4e7d83fef90b+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_c628edfe4e7d83fef90b+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c628edfe4e7d83fef90b+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_c628edfe4e7d83fef90b+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_c628edfe4e7d83fef90b+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e4caae93c0e0c29d2dce618e5a975bf1a643e754 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c628edfe4e7d83fef90b+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e90268799a1559562c79e6ab4aa5376df8060e7124215daae9984fa8fb8a139 +size 359350 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cb41f2f1351c7549e47a+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_cb41f2f1351c7549e47a+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cb41f2f1351c7549e47a+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_cb41f2f1351c7549e47a+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_cb41f2f1351c7549e47a+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..59f2ecc5a4f334cb90881854ff54d6bcdb0839cc --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cb41f2f1351c7549e47a+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a872fed45a8d1f89df4398a89f7cbcf688343781c7975588d0b8b36fd7c80a +size 359350 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+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_cc7a21f76bfb2321fb54+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cb2431cdf2ce36e9b3e1bc40faece4f74ef62bc2 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:749fd93722531030da7eb30c60e52d83dbdeefdc1ac67459d85a058749d628dc +size 359350 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..569d8c02c6aab0e607a31b323853f58faa7aff97 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f34b2b9a6960bab0f5a63a01edd8e0ce361899d0b8bff9d1cddb43790a01b605 +size 779264 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..bd2312fbd6a86813e1c632cd4eea88aeed2a0978 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cc7a21f76bfb2321fb54+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8378fbd79d6b4ebcb96f1f301227b7006b4b4ea90ac1f3269304007633fc6fea +size 799726 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+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_cca573e7f7cd333a1619+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..32434a85f0573ed5e34e6b12bcc6c94c0ada3068 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef0dfd6d35d658a452fb63477ce8cae99aa3734efd347108ad1a1ba0392414d +size 1106388 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4e440f7bcf9306be80aeb41156e687c5aaa01e56 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebbf10eeb142e0a2b7e7c91be18e16c27d19f58f080c0068896480439db55c1f +size 4905984 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9574c421994c5f82e35423d3fdca7ffceaf759cd --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cca573e7f7cd333a1619+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b2547eb0e4e6c5ba04f41748ad5522dfe57135e46862d084da988247d36b93c +size 5079029 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_db411529aa2d6768f535+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_db411529aa2d6768f535+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_db411529aa2d6768f535+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_db411529aa2d6768f535+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_db411529aa2d6768f535+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_db411529aa2d6768f535+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_db411529aa2d6768f535+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..701dca64479752be005653c80804a703b96769bf --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_db411529aa2d6768f535+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1aa19ecb3dd17b877ca11ecd5a94c7d5316975f209073f960ee73807483dfb2 +size 26430 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_db411529aa2d6768f535+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_db411529aa2d6768f535+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8749e92a6ce0e41a380502683ecb8e5ca1fc9f0e Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_db411529aa2d6768f535+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_eaa178b2a774b7c261a2+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_eaa178b2a774b7c261a2+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_eaa178b2a774b7c261a2+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_eaa178b2a774b7c261a2+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_eaa178b2a774b7c261a2+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f70725f9e994cf6435f5f4372f9b280f86ea82d4 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_eaa178b2a774b7c261a2+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:011ab71fcbc661b742bd4655755b039ce56b22db262d4f05bdde3bd025f7396e +size 18983459 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_efd188b855128a998bff+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_efd188b855128a998bff+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_efd188b855128a998bff+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_efd188b855128a998bff+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_efd188b855128a998bff+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fefd9eb50c4a249065ea7a696022891f8728eace --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_efd188b855128a998bff+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b86ed23f28526203221bb2b0ed1217bf6a77a22abff800b3351a6177b2eaf79b +size 207859