├── .azure-pipelines ├── code-scan.yml ├── docker │ ├── Dockerfile.devel │ ├── DockerfileCodeScan.devel │ └── ubuntu-2404.devel ├── model-test-3x.yml ├── scripts │ ├── change_color.sh │ ├── codeScan │ │ ├── bandit │ │ │ └── bandit.sh │ │ ├── codespell │ │ │ └── inc_dict.txt │ │ └── pydocstyle │ │ │ ├── pydocstyle.sh │ │ │ └── scan_path.txt │ ├── fwk_version.sh │ ├── install_nc.sh │ ├── models │ │ ├── collect_log_all.py │ │ ├── collect_log_model.py │ │ ├── env_setup.sh │ │ ├── generate_report.sh │ │ ├── new_benchmark.py │ │ ├── run_benchmark_common.sh │ │ ├── run_model_trigger_common.sh │ │ ├── run_pytorch_models_trigger.sh │ │ ├── run_tuning_common.sh │ │ └── update_yaml_config.py │ └── ut │ │ ├── 3x │ │ ├── collect_log_3x.sh │ │ ├── coverage.3x_pt │ │ ├── coverage.3x_pt_fp8 │ │ ├── coverage.3x_tf │ │ ├── run_3x_pt.sh │ │ ├── run_3x_pt_fp8.sh │ │ └── run_3x_tf.sh │ │ ├── collect_log.sh │ │ ├── compare_coverage.sh │ │ ├── coverage.file │ │ ├── env_setup.sh │ │ ├── run_basic_adaptor.sh │ │ ├── run_basic_adaptor_tfnewapi.sh │ │ ├── run_basic_api.sh │ │ ├── run_basic_itex.sh │ │ ├── run_basic_others.sh │ │ ├── run_basic_pt_pruning.sh │ │ └── run_basic_tf_pruning.sh ├── template │ ├── code-scan-template.yml │ ├── docker-template.yml │ ├── model-template.yml │ └── ut-template.yml ├── ut-3x-pt-fp8.yml ├── ut-3x-pt.yml ├── ut-3x-tf.yml └── ut-basic.yml ├── .github ├── license_template.txt ├── pull_request_template.md └── workflows │ ├── check-stale-issue.yml │ ├── pr-agent.yml │ ├── pr-code-sync.yml │ ├── pr-io-build.yaml │ ├── pr-link-scan.yml │ ├── pr-pre-commit.yml │ └── publish.yml ├── .gitignore ├── .pre-commit-config.yaml ├── .vscode └── settings_recommended.json ├── LICENSE ├── README.md ├── SECURITY.md ├── docker ├── Dockerfile ├── Dockerfile.devel ├── README.md ├── third-party-programs-docker.txt ├── third-party-programs-pytorch.txt └── third-party-programs-tensorflow.txt ├── docs ├── build_docs │ ├── Makefile │ ├── add_readme.py │ ├── build.sh │ ├── make.bat │ ├── pip_set_env.sh │ ├── source │ │ ├── _static │ │ │ ├── custom.css │ │ │ └── index.html │ │ ├── _templates │ │ │ ├── footer.html │ │ │ └── layout.html │ │ ├── conf.py │ │ └── index.rst │ ├── sphinx-requirements.txt │ ├── update_html.py │ └── update_version.py └── source │ ├── 2x_user_guide.md │ ├── 3x │ ├── PT_DynamicQuant.md │ ├── PT_FP8Quant.md │ ├── PT_MXQuant.md │ ├── PT_MixedPrecision.md │ ├── PT_SmoothQuant.md │ ├── PT_StaticQuant.md │ ├── PT_WeightOnlyQuant.md │ ├── PyTorch.md │ ├── TF_Quant.md │ ├── TF_SQ.md │ ├── TensorFlow.md │ ├── autotune.md │ ├── client_quant.md │ ├── design.md │ ├── gaudi_version_map.md │ ├── imgs │ │ ├── architecture.png │ │ ├── data_format.png │ │ ├── fp8_dtype.png │ │ ├── lwq.png │ │ ├── mx_workflow.png │ │ ├── optimum-habana.png │ │ ├── smoothquant.png │ │ ├── sq_convert.png │ │ ├── sq_pc.png │ │ ├── vllm_gaudi.png │ │ └── workflow.png │ ├── quantization.md │ └── transformers_like_api.md │ ├── CODE_OF_CONDUCT.md │ ├── CONTRIBUTING.md │ ├── FX.md │ ├── SECURITY.md │ ├── adaptor.md │ ├── add_new_adaptor.md │ ├── add_new_data_type.md │ ├── api-doc │ ├── adaptor.rst │ ├── adaptor │ │ ├── onnxrt.rst │ │ └── torch_utils.rst │ ├── api_2.rst │ ├── api_3.rst │ ├── apis.rst │ ├── compression.rst │ ├── config.rst │ ├── mix_precision.rst │ ├── model.rst │ ├── objective.rst │ ├── quantization.rst │ ├── strategy.rst │ ├── tf_quantization_autotune.rst │ ├── tf_quantization_common.rst │ ├── tf_quantization_config.rst │ ├── torch_quantization_autotune.rst │ ├── torch_quantization_common.rst │ ├── torch_quantization_config.rst │ └── training.rst │ ├── calibration.md │ ├── coding_style.md │ ├── dataloader.md │ ├── design.md │ ├── distillation.md │ ├── examples_readme.md │ ├── faq.md │ ├── framework_yaml.md │ ├── get_started.md │ ├── imgs │ ├── Conv2D_PyTorch_Cap.png │ ├── Distillation_workflow.png │ ├── accuracy_aware_tuning_flow.png │ ├── architecture.png │ ├── bf16_convert_pt.png │ ├── bf16_convert_tf.png │ ├── common │ │ ├── code.svg │ │ ├── intel.svg │ │ └── right.svg │ ├── data_format.png │ ├── distributed_tuning_intro.png │ ├── export.png │ ├── fake_quant.png │ ├── lwq.png │ ├── lwq_ort.png │ ├── metric.jpg │ ├── model.png │ ├── model_scale_accuracy.png │ ├── mx_workflow.png │ ├── pruning │ │ ├── 2in4_sparsity_demo.png │ │ ├── Pruning_schedule.jpg │ │ ├── Regularization.jpg │ │ ├── progressive_pruning.png │ │ ├── pruning.png │ │ ├── pruning_criteria.png │ │ ├── pruning_intro.png │ │ ├── pruning_patterns.jpg │ │ ├── pruning_scatter.png │ │ ├── sparse_dim.png │ │ ├── sparsity_decay_type.png │ │ └── train_for_sparsity.png │ ├── self-distillation.png │ ├── smoothquant.png │ ├── sq_convert.png │ ├── sq_pc.png │ ├── strategy.png │ ├── wechat_group.jpg │ └── workflow.png │ ├── infrastructure.md │ ├── installation_guide.md │ ├── legal_information.md │ ├── llm_recipes.md │ ├── metric.md │ ├── mixed_precision.md │ ├── model.md │ ├── mx_quantization.md │ ├── objective.md │ ├── orchestration.md │ ├── pruning.md │ ├── publication_list.md │ ├── quantization.md │ ├── quantization_layer_wise.md │ ├── quantization_mixed_precision.md │ ├── quantization_weight_only.md │ ├── smooth_quant.md │ ├── tuning_strategies.md │ └── validated_model_list.md ├── examples ├── .config │ ├── model_params_keras.json │ ├── model_params_keras_3x.json │ ├── model_params_onnxrt.json │ ├── model_params_onnxrt_win.json │ ├── model_params_pt2onnx.json │ ├── model_params_pytorch.json │ ├── model_params_pytorch_3x.json │ ├── model_params_pytorch_win.json │ ├── model_params_tensorflow.json │ ├── model_params_tensorflow_3x.json │ ├── model_params_tensorflow_win.json │ └── model_params_tf2onnx.json ├── README.md ├── deprecated │ ├── README.md │ ├── helloworld │ │ ├── README.md │ │ ├── fp8_example │ │ │ ├── README.md │ │ │ ├── maxabs_measure.json │ │ │ ├── maxabs_quant.json │ │ │ ├── quant_config.json │ │ │ ├── sample_one_step.py │ │ │ └── sample_two_steps.py │ │ ├── tf_example1 │ │ │ ├── README.md │ │ │ ├── requirements.txt │ │ │ └── test.py │ │ ├── tf_example2 │ │ │ ├── README.md │ │ │ ├── requirements.txt │ │ │ └── test.py │ │ ├── tf_example3 │ │ │ ├── README.md │ │ │ ├── requirements.txt │ │ │ └── test.py │ │ ├── tf_example4 │ │ │ ├── README.md │ │ │ ├── requirements.txt │ │ │ └── test.py │ │ ├── tf_example5 │ │ │ ├── README.md │ │ │ ├── requirements.txt │ │ │ └── test.py │ │ ├── tf_example6 │ │ │ ├── README.md │ │ │ ├── requirements.txt │ │ │ └── test.py │ │ ├── tf_example7 │ │ │ ├── README.md │ │ │ ├── requirements.txt │ │ │ └── test.py │ │ ├── torch_static_quant │ │ │ ├── README.md │ │ │ ├── quant_resnet18.py │ │ │ └── requirements.txt │ │ ├── torch_woq │ │ │ ├── README.md │ │ │ ├── quant_mistral.py │ │ │ └── requirements.txt │ │ ├── torch_woq_autoround │ │ │ ├── README.md │ │ │ ├── requirements.txt │ │ │ └── test.py │ │ └── train.py │ ├── keras │ │ └── image_recognition │ │ │ ├── imagenet_prepare │ │ │ ├── build_imagenet_data.py │ │ │ ├── download_and_convert_imagenet.sh │ │ │ ├── download_imagenet.sh │ │ │ ├── imagenet_lsvrc_2015_synsets.txt │ │ │ └── imagenet_metadata.txt │ │ │ ├── inception_resnet_v2 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── inception_v3 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── mobilenet_v2 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── prepare_dataset.sh │ │ │ ├── resnet101 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── resnet50 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── resnet50_fashion │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── resnet50_fashion_mnist_train.py │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── resnetv2_101 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── resnetv2_50 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── vgg16 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── vgg19 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ └── xception │ │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── main.py │ │ │ ├── prepare_model.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ ├── notebook │ │ ├── onnxruntime │ │ │ ├── Quick_Started_Notebook_of_INC_for_ONNXRuntime.ipynb │ │ │ ├── benchmark.py │ │ │ └── requirements.txt │ │ ├── perf_fp32_int8_tf │ │ │ ├── README.md │ │ │ ├── compare_result.py │ │ │ ├── run.sh │ │ │ ├── set_env.sh │ │ │ └── test_performance.py │ │ ├── pytorch │ │ │ ├── Quick_Started_Notebook_of_INC_for_Pytorch.ipynb │ │ │ └── requirements.txt │ │ └── tensorflow │ │ │ ├── alexnet_mnist │ │ │ ├── License.txt │ │ │ ├── README.md │ │ │ ├── alexnet.py │ │ │ ├── compare_perf.py │ │ │ ├── conda_set_env.sh │ │ │ ├── devcloud_setup_env.sh │ │ │ ├── inc_quantize_model.py │ │ │ ├── inc_sample_for_tensorflow.ipynb │ │ │ ├── keras_tf_train_mnist.py │ │ │ ├── mnist_dataset.py │ │ │ ├── pip_set_env.sh │ │ │ ├── profiling_inc.py │ │ │ ├── requirements.txt │ │ │ ├── run_in_intel_devcloud.sh │ │ │ ├── run_jupyter.sh │ │ │ └── run_sample.sh │ │ │ ├── resnet │ │ │ ├── README.md │ │ │ ├── requirements.txt │ │ │ ├── resnet_benchmark.py │ │ │ └── resnet_quantization.ipynb │ │ │ └── vgg19_ibean │ │ │ ├── README.md │ │ │ ├── compare_perf.py │ │ │ ├── conda_set_env.sh │ │ │ ├── devcloud_setup_env.sh │ │ │ ├── inc_quantize_model.py │ │ │ ├── inc_quantize_vgg19.ipynb │ │ │ ├── pip_set_env.sh │ │ │ ├── profiling_inc.py │ │ │ ├── requirements.txt │ │ │ ├── run_in_intel_devcloud.sh │ │ │ ├── run_jupyter.sh │ │ │ ├── run_sample.sh │ │ │ └── train_model.py │ ├── onnxrt │ │ ├── body_analysis │ │ │ └── onnx_model_zoo │ │ │ │ ├── arcface │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── emotion_ferplus │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ │ └── ultraface │ │ │ │ └── quantization │ │ │ │ └── ptq_static │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ ├── run_quant.sh │ │ │ │ ├── wider_easy_val.mat │ │ │ │ └── wider_face_val.mat │ │ ├── image_recognition │ │ │ ├── beit │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── beit_modeling_finetune.py │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── mobilenet_v2 │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── mobilenet_v3 │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── onnx_model_zoo │ │ │ │ ├── alexnet │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── caffenet │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── densenet │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── efficientnet │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── fcn │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── googlenet │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── inception │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── mnist │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── mobilenet │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── resnet50 │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── shufflenet │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── squeezenet │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── vgg16 │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ └── zfnet │ │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── resnet50_mlperf │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── resnet50_torchvision │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ └── vgg16 │ │ │ │ └── quantization │ │ │ │ └── ptq_static │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ ├── nlp │ │ │ ├── bert │ │ │ │ └── quantization │ │ │ │ │ ├── ptq_dynamic │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_data.sh │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_data.sh │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── distilbert │ │ │ │ └── quantization │ │ │ │ │ ├── ptq_dynamic │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_data.sh │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_data.sh │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── huggingface_model │ │ │ │ ├── language_modeling │ │ │ │ │ └── quantization │ │ │ │ │ │ ├── ptq_dynamic │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── question_answering │ │ │ │ │ └── quantization │ │ │ │ │ │ ├── ptq_dynamic │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ │ ├── trainer_qa.py │ │ │ │ │ │ ├── utils_model.py │ │ │ │ │ │ └── utils_qa.py │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ │ ├── trainer_qa.py │ │ │ │ │ │ ├── utils_model.py │ │ │ │ │ │ └── utils_qa.py │ │ │ │ ├── text_classification │ │ │ │ │ └── mix_precision │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── eval.sh │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_data.sh │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ └── run.sh │ │ │ │ ├── text_generation │ │ │ │ │ ├── gptj │ │ │ │ │ │ └── quantization │ │ │ │ │ │ │ ├── ptq_dynamic │ │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ │ └── run_quant.sh │ │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ │ └── run_quant.sh │ │ │ │ │ └── llama │ │ │ │ │ │ └── quantization │ │ │ │ │ │ ├── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── prompt.json │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ │ │ └── weight_only │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ └── token_classification │ │ │ │ │ ├── layoutlm │ │ │ │ │ └── quantization │ │ │ │ │ │ ├── ptq_dynamic │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── funsd.py │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── model.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ │ ├── trainer.py │ │ │ │ │ │ └── utils.py │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── funsd.py │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── model.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ │ ├── trainer.py │ │ │ │ │ │ └── utils.py │ │ │ │ │ ├── layoutlmv2 │ │ │ │ │ └── quantization │ │ │ │ │ │ ├── ptq_dynamic │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── funsd.py │ │ │ │ │ │ ├── image_utils.py │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── model.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ │ │ └── ptq_static │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── funsd.py │ │ │ │ │ │ ├── image_utils.py │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── model.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ │ └── layoutlmv3 │ │ │ │ │ └── quantization │ │ │ │ │ ├── ptq_dynamic │ │ │ │ │ ├── README.md │ │ │ │ │ ├── funsd.py │ │ │ │ │ ├── main.py │ │ │ │ │ ├── model.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ └── utils.py │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── funsd.py │ │ │ │ │ ├── main.py │ │ │ │ │ ├── model.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ └── utils.py │ │ │ ├── mobilebert │ │ │ │ └── quantization │ │ │ │ │ ├── ptq_dynamic │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_data.sh │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_data.sh │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── onnx_model_zoo │ │ │ │ ├── BiDAF │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_dynamic │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── bert-squad │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_dynamic │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ ├── run_onnx_squad.py │ │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ │ ├── squad_evaluate.py │ │ │ │ │ │ └── tokenization.py │ │ │ │ ├── gpt2 │ │ │ │ │ └── quantization │ │ │ │ │ │ └── ptq_dynamic │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── gpt2.py │ │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ └── mobilebert │ │ │ │ │ └── quantization │ │ │ │ │ ├── ptq_dynamic │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_onnx_squad.py │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ ├── squad_evaluate.py │ │ │ │ │ └── tokenization.py │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_onnx_squad.py │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ ├── squad_evaluate.py │ │ │ │ │ └── tokenization.py │ │ │ └── roberta │ │ │ │ └── quantization │ │ │ │ ├── ptq_dynamic │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_data.sh │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ │ └── ptq_static │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_data.sh │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ └── object_detection │ │ │ ├── onnx_model_zoo │ │ │ ├── DUC │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── cityscapes_labels.py │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── faster_rcnn │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── coco_label_map.py │ │ │ │ │ ├── coco_tools.py │ │ │ │ │ ├── label_map.yaml │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── mask_rcnn │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── coco_label_map.py │ │ │ │ │ ├── coco_tools.py │ │ │ │ │ ├── label_map.yaml │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── ssd │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── coco_label_map.py │ │ │ │ │ ├── coco_tools.py │ │ │ │ │ ├── data_utils.py │ │ │ │ │ ├── label_map.yaml │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── ssd_mobilenet_v1 │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── coco_label_map.py │ │ │ │ │ ├── coco_tools.py │ │ │ │ │ ├── data_utils.py │ │ │ │ │ ├── label_map.yaml │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── tiny_yolov3 │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── coco_label_map.py │ │ │ │ │ ├── coco_tools.py │ │ │ │ │ ├── label_map.yaml │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── yolov3 │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── README.md │ │ │ │ │ ├── coco_label_map.py │ │ │ │ │ ├── coco_tools.py │ │ │ │ │ ├── label_map.yaml │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ └── yolov4 │ │ │ │ └── quantization │ │ │ │ └── ptq_static │ │ │ │ ├── README.md │ │ │ │ ├── coco_label_map.py │ │ │ │ ├── coco_tools.py │ │ │ │ ├── label_map.yaml │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ ├── run_quant.sh │ │ │ │ └── yolov4_anchors.txt │ │ │ ├── ssd_mobilenet_v1 │ │ │ └── quantization │ │ │ │ └── ptq_static │ │ │ │ ├── README.md │ │ │ │ ├── coco_label_map.py │ │ │ │ ├── coco_tools.py │ │ │ │ ├── data_utils.py │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── ssd_mobilenet_v2 │ │ │ └── quantization │ │ │ │ └── ptq_static │ │ │ │ ├── README.md │ │ │ │ ├── coco_label_map.py │ │ │ │ ├── coco_tools.py │ │ │ │ ├── data_utils.py │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ └── table_transformer │ │ │ └── quantization │ │ │ └── ptq_static │ │ │ ├── README.md │ │ │ ├── patch │ │ │ ├── prepare.sh │ │ │ ├── prepare_model.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ ├── pytorch │ │ ├── diffusion_model │ │ │ └── diffusers │ │ │ │ ├── dreambooth │ │ │ │ ├── README.md │ │ │ │ ├── generated_images │ │ │ │ │ ├── dog-bucket-ipex.png │ │ │ │ │ └── dog-bucket.png │ │ │ │ ├── requirements.txt │ │ │ │ ├── train_dreambooth.py │ │ │ │ └── train_dreambooth_ipex.py │ │ │ │ └── textual_inversion │ │ │ │ ├── README.md │ │ │ │ ├── dicoo │ │ │ │ └── 1.jpeg │ │ │ │ ├── distillation_for_quantization │ │ │ │ ├── README.md │ │ │ │ ├── images │ │ │ │ │ ├── FP32.png │ │ │ │ │ └── INT8.png │ │ │ │ ├── requirements.txt │ │ │ │ ├── text2images.py │ │ │ │ └── textual_inversion.py │ │ │ │ ├── generated_images │ │ │ │ └── dicoo_christmas.png │ │ │ │ ├── requirements.txt │ │ │ │ ├── textual_inversion.py │ │ │ │ └── textual_inversion_ipex.py │ │ ├── image_recognition │ │ │ ├── 3d-unet │ │ │ │ ├── __init__.py │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ └── fx │ │ │ │ │ ├── .dockerignore │ │ │ │ │ ├── .gitignore │ │ │ │ │ ├── Makefile │ │ │ │ │ ├── README.md │ │ │ │ │ ├── Task043_BraTS_2019.py │ │ │ │ │ ├── accuracy-brats.py │ │ │ │ │ ├── brats_QSL.py │ │ │ │ │ ├── brats_cal_images_list.txt │ │ │ │ │ ├── folds │ │ │ │ │ ├── fold0_validation.txt │ │ │ │ │ ├── fold1_validation.txt │ │ │ │ │ ├── fold2_validation.txt │ │ │ │ │ ├── fold3_validation.txt │ │ │ │ │ └── fold4_validation.txt │ │ │ │ │ ├── mlperf.conf │ │ │ │ │ ├── onnxruntime_SUT.py │ │ │ │ │ ├── ov_SUT.py │ │ │ │ │ ├── preprocess.py │ │ │ │ │ ├── pytorch_SUT.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run.py │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ ├── tf_SUT.py │ │ │ │ │ ├── unet_onnx_to_tf.py │ │ │ │ │ ├── unet_pytorch_to_onnx.py │ │ │ │ │ └── user.conf │ │ │ ├── CNN-2 │ │ │ │ └── distillation │ │ │ │ │ └── eager │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── plain_cnn_cifar.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ └── train_without_distillation.py │ │ │ ├── MobileNetV2-0.35 │ │ │ │ └── distillation │ │ │ │ │ └── eager │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── train_without_distillation.py │ │ │ │ │ └── wideresnet.py │ │ │ ├── ResNet50 │ │ │ │ └── pruning │ │ │ │ │ └── eager │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_resnet50_prune.sh │ │ │ │ │ └── train.py │ │ │ ├── VGG-8 │ │ │ │ └── distillation │ │ │ │ │ └── eager │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── plain_cnn_cifar.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ └── train_without_distillation.py │ │ │ ├── peleenet │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ └── fx │ │ │ │ │ ├── LICENSE │ │ │ │ │ ├── PeleeNet_README.md │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── peleenet.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── resnest │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ └── fx │ │ │ │ │ ├── LICENSE │ │ │ │ │ ├── README.md │ │ │ │ │ ├── ResNest_README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ └── verify.py │ │ │ ├── se_resnext │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ └── fx │ │ │ │ │ ├── LICENSE.txt │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_eval.py │ │ │ │ │ └── run_quant.sh │ │ │ ├── segment_anything │ │ │ │ ├── README.md │ │ │ │ ├── download_dataset.py │ │ │ │ ├── inc_dataset_loader.py │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ └── torchvision_models │ │ │ │ ├── distillation │ │ │ │ └── eager │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ └── run_distillation.sh │ │ │ │ ├── export │ │ │ │ └── fx │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── onnx_evaluation.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_export.sh │ │ │ │ ├── mixed_precision │ │ │ │ └── resnet18 │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ └── run_benchmark.sh │ │ │ │ ├── optimization_pipeline │ │ │ │ ├── prune_and_ptq │ │ │ │ │ └── fx │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ └── requirements.txt │ │ │ │ └── qat_during_prune │ │ │ │ │ └── fx │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ └── requirements.txt │ │ │ │ ├── quantization │ │ │ │ ├── ptq │ │ │ │ │ └── cpu │ │ │ │ │ │ ├── fx │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ │ │ └── ipex │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ ├── patch.patch │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ └── qat │ │ │ │ │ └── fx │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ │ └── self_distillation │ │ │ │ └── eager │ │ │ │ ├── README.md │ │ │ │ ├── autoaugment.py │ │ │ │ ├── cutout.py │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── resnet.py │ │ │ │ ├── run_distillation.sh │ │ │ │ └── run_selfteacher.sh │ │ ├── nlp │ │ │ ├── blendcnn │ │ │ │ ├── distillation │ │ │ │ │ └── eager │ │ │ │ │ │ ├── .gitignore │ │ │ │ │ │ ├── LICENSE │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── checkpoint.py │ │ │ │ │ │ ├── classify.py │ │ │ │ │ │ ├── config │ │ │ │ │ │ ├── agnews_data.json │ │ │ │ │ │ ├── bert_base.json │ │ │ │ │ │ ├── blendcnn │ │ │ │ │ │ │ ├── agnews │ │ │ │ │ │ │ │ ├── eval.json │ │ │ │ │ │ │ │ ├── optim.json │ │ │ │ │ │ │ │ └── train.json │ │ │ │ │ │ │ └── mrpc │ │ │ │ │ │ │ │ ├── eval.json │ │ │ │ │ │ │ │ ├── optim.json │ │ │ │ │ │ │ │ └── train.json │ │ │ │ │ │ ├── distill │ │ │ │ │ │ │ ├── agnews │ │ │ │ │ │ │ │ ├── eval.json │ │ │ │ │ │ │ │ ├── optim.json │ │ │ │ │ │ │ │ └── train.json │ │ │ │ │ │ │ └── mrpc │ │ │ │ │ │ │ │ ├── eval.json │ │ │ │ │ │ │ │ ├── optim.json │ │ │ │ │ │ │ │ └── train.json │ │ │ │ │ │ ├── finetune │ │ │ │ │ │ │ ├── agnews │ │ │ │ │ │ │ │ ├── eval.json │ │ │ │ │ │ │ │ ├── optim.json │ │ │ │ │ │ │ │ └── train.json │ │ │ │ │ │ │ └── mrpc │ │ │ │ │ │ │ │ ├── eval.json │ │ │ │ │ │ │ │ ├── optim.json │ │ │ │ │ │ │ │ └── train.json │ │ │ │ │ │ ├── mrpc_data.json │ │ │ │ │ │ └── pretrain.json │ │ │ │ │ │ ├── data.py │ │ │ │ │ │ ├── distill.py │ │ │ │ │ │ ├── finetune.py │ │ │ │ │ │ ├── models.py │ │ │ │ │ │ ├── optim.py │ │ │ │ │ │ ├── pretrain.py │ │ │ │ │ │ ├── tokenization.py │ │ │ │ │ │ ├── trainer.py │ │ │ │ │ │ └── utils.py │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ └── ipex │ │ │ │ │ ├── LICENSE │ │ │ │ │ ├── README.md │ │ │ │ │ ├── checkpoint.py │ │ │ │ │ ├── classify.py │ │ │ │ │ ├── config │ │ │ │ │ ├── agnews_data.json │ │ │ │ │ ├── bert_base.json │ │ │ │ │ ├── blendcnn │ │ │ │ │ │ ├── agnews │ │ │ │ │ │ │ ├── eval.json │ │ │ │ │ │ │ ├── optim.json │ │ │ │ │ │ │ └── train.json │ │ │ │ │ │ └── mrpc │ │ │ │ │ │ │ ├── eval.json │ │ │ │ │ │ │ ├── optim.json │ │ │ │ │ │ │ └── train.json │ │ │ │ │ ├── finetune │ │ │ │ │ │ ├── agnews │ │ │ │ │ │ │ ├── eval.json │ │ │ │ │ │ │ ├── optim.json │ │ │ │ │ │ │ └── train.json │ │ │ │ │ │ └── mrpc │ │ │ │ │ │ │ ├── eval.json │ │ │ │ │ │ │ ├── optim.json │ │ │ │ │ │ │ └── train.json │ │ │ │ │ └── mrpc_data.json │ │ │ │ │ ├── data.py │ │ │ │ │ ├── models.py │ │ │ │ │ ├── optim.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ ├── tokenization.py │ │ │ │ │ ├── trainer.py │ │ │ │ │ └── utils.py │ │ │ └── huggingface_models │ │ │ │ ├── language-modeling │ │ │ │ ├── pruning │ │ │ │ │ ├── eager │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_clm_no_trainer.py │ │ │ │ │ │ ├── run_clm_sparsegpt.py │ │ │ │ │ │ ├── scripts │ │ │ │ │ │ │ ├── run_bloom_pruning.sh │ │ │ │ │ │ │ ├── run_gptj_pruning.sh │ │ │ │ │ │ │ ├── run_llama_pruning.sh │ │ │ │ │ │ │ ├── run_llm_sparsegpt.sh │ │ │ │ │ │ │ └── run_opt_pruning.sh │ │ │ │ │ │ └── timers.py │ │ │ │ │ └── multi_cards │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── config │ │ │ │ │ │ ├── zero_stage2_config.json │ │ │ │ │ │ └── zero_stage3_config.json │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run.sh │ │ │ │ │ │ ├── run_clm_no_trainer.py │ │ │ │ │ │ ├── run_clm_no_trainer_deepspeed.py │ │ │ │ │ │ ├── run_ds.sh │ │ │ │ │ │ └── run_ds_z3.sh │ │ │ │ └── quantization │ │ │ │ │ ├── llm │ │ │ │ │ ├── README.md │ │ │ │ │ ├── cnn_dm_dataset.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_clm_no_trainer.py │ │ │ │ │ ├── run_gptj_mlperf_int4.py │ │ │ │ │ ├── run_gptj_mlperf_int4.sh │ │ │ │ │ └── run_quant.sh │ │ │ │ │ └── ptq_static │ │ │ │ │ └── fx │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_clm.py │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── load_model_hub.py │ │ │ │ ├── question-answering │ │ │ │ ├── distillation │ │ │ │ │ └── eager │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_qa_no_trainer_distillation.py │ │ │ │ │ │ └── utils_qa.py │ │ │ │ ├── mixed_precision │ │ │ │ │ └── ipex │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ ├── run_qa.py │ │ │ │ │ │ ├── trainer_qa.py │ │ │ │ │ │ └── utils_qa.py │ │ │ │ ├── model_slim │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_qa_auto_slim_bert-base.sh │ │ │ │ │ ├── run_qa_auto_slim_bert-large.sh │ │ │ │ │ ├── run_qa_no_trainer_auto_slim.py │ │ │ │ │ ├── timers.py │ │ │ │ │ └── utils_qa.py │ │ │ │ ├── optimization_pipeline │ │ │ │ │ └── prune_once_for_all │ │ │ │ │ │ └── fx │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_qa_no_trainer_pruneOFA.py │ │ │ │ │ │ └── utils_qa.py │ │ │ │ ├── pruning │ │ │ │ │ └── eager │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_qa_no_trainer.py │ │ │ │ │ │ ├── run_qa_no_trainer_block.py │ │ │ │ │ │ ├── scripts │ │ │ │ │ │ ├── bertbase_squad_4x1.sh │ │ │ │ │ │ ├── bertlarge_squad_4x1.sh │ │ │ │ │ │ ├── bertmini_dense_fintune.sh │ │ │ │ │ │ ├── bertmini_squad_2in4.sh │ │ │ │ │ │ ├── bertmini_squad_4x1.sh │ │ │ │ │ │ └── distilbert_squad_4x1.sh │ │ │ │ │ │ └── utils_qa.py │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ ├── fx │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_qa.py │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ ├── trainer_qa.py │ │ │ │ │ └── utils_qa.py │ │ │ │ │ └── ipex │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_qa.py │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ ├── trainer_qa.py │ │ │ │ │ └── utils_qa.py │ │ │ │ ├── summarization │ │ │ │ └── quantization │ │ │ │ │ └── ptq_dynamic │ │ │ │ │ └── fx │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ └── run_summarization.py │ │ │ │ ├── text-classification │ │ │ │ ├── distillation │ │ │ │ │ └── eager │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ └── run_glue_no_trainer_distillation.py │ │ │ │ ├── export │ │ │ │ │ └── fx │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── onnx_evaluation.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ ├── run_export.sh │ │ │ │ │ │ └── run_glue.py │ │ │ │ ├── optimization_pipeline │ │ │ │ │ ├── distillation_for_quantization │ │ │ │ │ │ └── fx │ │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ │ └── run_glue_no_trainer.py │ │ │ │ │ └── prune_once_for_all │ │ │ │ │ │ └── fx │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ └── run_glue_no_trainer_pruneOFA.py │ │ │ │ ├── pruning │ │ │ │ │ ├── eager │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_glue_no_trainer.py │ │ │ │ │ │ ├── run_glue_no_trainer_mixed.py │ │ │ │ │ │ └── scripts │ │ │ │ │ │ │ ├── bertmini_mrpc_2in4.sh │ │ │ │ │ │ │ ├── bertmini_mrpc_4x1.sh │ │ │ │ │ │ │ ├── bertmini_mrpc_dense_finetune.sh │ │ │ │ │ │ │ ├── bertmini_mrpc_mixed.sh │ │ │ │ │ │ │ ├── bertmini_mrpc_perchannel.sh │ │ │ │ │ │ │ ├── bertmini_sst2_2in4.sh │ │ │ │ │ │ │ ├── bertmini_sst2_4x1.sh │ │ │ │ │ │ │ ├── bertmini_sst2_dense_fintune.sh │ │ │ │ │ │ │ ├── bertmini_sst2_perchannel.sh │ │ │ │ │ │ │ ├── distilbert_mrpc_2in4.sh │ │ │ │ │ │ │ └── distilbert_mrpc_4x1.sh │ │ │ │ │ └── hpo │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ └── run_glue_no_trainer.py │ │ │ │ └── quantization │ │ │ │ │ ├── ptq_dynamic │ │ │ │ │ └── fx │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ ├── run_glue.py │ │ │ │ │ │ └── run_quant.sh │ │ │ │ │ ├── ptq_static │ │ │ │ │ └── fx │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ ├── run_distributed_tuning.sh │ │ │ │ │ │ ├── run_glue.py │ │ │ │ │ │ └── run_quant.sh │ │ │ │ │ └── qat │ │ │ │ │ └── fx │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_glue.py │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── text-to-image │ │ │ │ ├── inference │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ └── run_sd.py │ │ │ │ └── quantization │ │ │ │ │ ├── README.md │ │ │ │ │ ├── base_images │ │ │ │ │ └── image.jpg │ │ │ │ │ ├── images │ │ │ │ │ ├── fp32.png │ │ │ │ │ ├── ground_truth.jpg │ │ │ │ │ └── int8.png │ │ │ │ │ ├── ptq_static │ │ │ │ │ └── fx │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ └── run_quant.sh │ │ │ │ │ ├── requirements.txt │ │ │ │ │ └── run_diffusion.py │ │ │ │ └── translation │ │ │ │ ├── pruning │ │ │ │ └── eager │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_translation_no_trainer.py │ │ │ │ │ └── scripts │ │ │ │ │ ├── run_translation_finetune.sh │ │ │ │ │ └── run_translation_prune.sh │ │ │ │ └── quantization │ │ │ │ └── ptq_dynamic │ │ │ │ └── fx │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ ├── run_quant.sh │ │ │ │ └── run_translation.py │ │ ├── object_detection │ │ │ ├── maskrcnn │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ └── fx │ │ │ │ │ ├── README.md │ │ │ │ │ ├── download_dataset.sh │ │ │ │ │ ├── download_weights.sh │ │ │ │ │ ├── pytorch │ │ │ │ │ ├── LICENSE │ │ │ │ │ ├── TROUBLESHOOTING.md │ │ │ │ │ ├── configs │ │ │ │ │ │ └── e2e_mask_rcnn_R_50_FPN_1x.yaml │ │ │ │ │ ├── maskrnn.patch │ │ │ │ │ ├── setup.py │ │ │ │ │ └── tools │ │ │ │ │ │ ├── cityscapes │ │ │ │ │ │ ├── convert_cityscapes_to_coco.py │ │ │ │ │ │ └── instances2dict_with_polygons.py │ │ │ │ │ │ ├── test_net.py │ │ │ │ │ │ ├── train_mlperf.py │ │ │ │ │ │ └── train_net.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_and_time.sh │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── ssd_resnet34 │ │ │ │ └── quantization │ │ │ │ │ ├── ptq │ │ │ │ │ ├── fx │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── mlperf.conf │ │ │ │ │ │ ├── prepare_dataset.sh │ │ │ │ │ │ ├── prepare_loadgen.sh │ │ │ │ │ │ ├── python │ │ │ │ │ │ │ ├── backend.py │ │ │ │ │ │ │ ├── backend_null.py │ │ │ │ │ │ │ ├── backend_onnxruntime.py │ │ │ │ │ │ │ ├── backend_pytorch.py │ │ │ │ │ │ │ ├── backend_pytorch_native.py │ │ │ │ │ │ │ ├── backend_tf.py │ │ │ │ │ │ │ ├── backend_tflite.py │ │ │ │ │ │ │ ├── coco.py │ │ │ │ │ │ │ ├── dataset.py │ │ │ │ │ │ │ ├── imagenet.py │ │ │ │ │ │ │ ├── main.py │ │ │ │ │ │ │ ├── models │ │ │ │ │ │ │ │ ├── anchor_generator.py │ │ │ │ │ │ │ │ ├── base_model_r34.py │ │ │ │ │ │ │ │ ├── convert_tf_weights.py │ │ │ │ │ │ │ │ ├── ssd_mobilenet_v1.py │ │ │ │ │ │ │ │ ├── ssd_r34.py │ │ │ │ │ │ │ │ └── utils.py │ │ │ │ │ │ │ ├── pycoco.py │ │ │ │ │ │ │ └── version.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ │ ├── setup.py │ │ │ │ │ │ ├── tools │ │ │ │ │ │ │ ├── accuracy-coco.py │ │ │ │ │ │ │ ├── accuracy-imagenet.py │ │ │ │ │ │ │ ├── calibrate_torchvision_model.py │ │ │ │ │ │ │ ├── ci-run.sh │ │ │ │ │ │ │ ├── coco-analyze.py │ │ │ │ │ │ │ ├── convert-to-onnx.sh │ │ │ │ │ │ │ ├── lglog2csv.py │ │ │ │ │ │ │ ├── make_fake_imagenet.sh │ │ │ │ │ │ │ ├── mobilenet-to-onnx.sh │ │ │ │ │ │ │ ├── pylintrc │ │ │ │ │ │ │ ├── resnet50-to-tflite.sh │ │ │ │ │ │ │ ├── resnet_save.py │ │ │ │ │ │ │ └── ssd-nhwc.py │ │ │ │ │ │ ├── upscale_coco │ │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ │ ├── coco.py │ │ │ │ │ │ │ ├── upscale.sh │ │ │ │ │ │ │ └── upscale_coco.py │ │ │ │ │ │ └── user.conf │ │ │ │ │ └── ipex │ │ │ │ │ │ ├── README.md │ │ │ │ │ │ ├── base_model.py │ │ │ │ │ │ ├── coco.py │ │ │ │ │ │ ├── download_dataset.sh │ │ │ │ │ │ ├── download_model.sh │ │ │ │ │ │ ├── infer.py │ │ │ │ │ │ ├── infer_weight_sharing.py │ │ │ │ │ │ ├── oob_utils.py │ │ │ │ │ │ ├── requirements.txt │ │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ │ ├── ssd300.py │ │ │ │ │ │ ├── ssd_r34.py │ │ │ │ │ │ └── utils.py │ │ │ │ │ └── qat │ │ │ │ │ └── fx │ │ │ │ │ ├── README.md │ │ │ │ │ ├── download_dataset.sh │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ └── ssd │ │ │ │ │ ├── base_model.py │ │ │ │ │ ├── coco.py │ │ │ │ │ ├── main.py │ │ │ │ │ ├── mlperf_logger.py │ │ │ │ │ ├── ssd300.py │ │ │ │ │ └── utils.py │ │ │ ├── yolo_v3 │ │ │ │ └── quantization │ │ │ │ │ └── ptq_static │ │ │ │ │ └── fx │ │ │ │ │ ├── LICENSE │ │ │ │ │ ├── README.md │ │ │ │ │ ├── YOLOV3_README.md │ │ │ │ │ ├── config │ │ │ │ │ ├── coco.data │ │ │ │ │ ├── create_custom_model.sh │ │ │ │ │ ├── custom.data │ │ │ │ │ ├── yolov3-tiny.cfg │ │ │ │ │ └── yolov3.cfg │ │ │ │ │ ├── data │ │ │ │ │ ├── coco.names │ │ │ │ │ ├── custom │ │ │ │ │ │ ├── classes.names │ │ │ │ │ │ ├── images │ │ │ │ │ │ │ └── train.jpg │ │ │ │ │ │ ├── labels │ │ │ │ │ │ │ └── train.txt │ │ │ │ │ │ ├── train.txt │ │ │ │ │ │ └── valid.txt │ │ │ │ │ ├── get_coco_dataset.sh │ │ │ │ │ └── samples │ │ │ │ │ │ ├── dog.jpg │ │ │ │ │ │ ├── eagle.jpg │ │ │ │ │ │ ├── field.jpg │ │ │ │ │ │ ├── giraffe.jpg │ │ │ │ │ │ ├── herd_of_horses.jpg │ │ │ │ │ │ ├── messi.jpg │ │ │ │ │ │ ├── person.jpg │ │ │ │ │ │ ├── room.jpg │ │ │ │ │ │ └── street.jpg │ │ │ │ │ ├── detect.py │ │ │ │ │ ├── models.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ ├── test.py │ │ │ │ │ ├── train.py │ │ │ │ │ ├── utils │ │ │ │ │ ├── augmentations.py │ │ │ │ │ ├── datasets.py │ │ │ │ │ ├── logger.py │ │ │ │ │ ├── parse_config.py │ │ │ │ │ └── utils.py │ │ │ │ │ └── weights │ │ │ │ │ └── download_weights.sh │ │ │ └── yolo_v5 │ │ │ │ └── pruning │ │ │ │ └── eager │ │ │ │ ├── README.md │ │ │ │ ├── coco.yaml │ │ │ │ ├── hyp.scratch-low.yaml │ │ │ │ ├── requirements.txt │ │ │ │ ├── scripts │ │ │ │ ├── yolov5s6_dense_finetune.sh │ │ │ │ ├── yolov5s_coco_1x1.sh │ │ │ │ └── yolov5s_coco_4x1.sh │ │ │ │ └── train.py │ │ ├── recommendation │ │ │ └── dlrm │ │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── fx │ │ │ │ ├── README.md │ │ │ │ ├── conf.yaml │ │ │ │ ├── data_loader_terabyte.py │ │ │ │ ├── data_utils.py │ │ │ │ ├── dlrm_data_pytorch.py │ │ │ │ ├── dlrm_s_pytorch.py │ │ │ │ ├── dlrm_s_pytorch_tune.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_and_time.sh │ │ │ │ ├── run_benchmark.sh │ │ │ │ ├── run_quant.sh │ │ │ │ └── tricks │ │ │ │ │ ├── md_embedding_bag.py │ │ │ │ │ └── qr_embedding_bag.py │ │ │ │ └── ipex │ │ │ │ ├── CODE_OF_CONDUCT.md │ │ │ │ ├── CONTRIBUTING.md │ │ │ │ ├── LICENSE │ │ │ │ ├── README.md │ │ │ │ ├── conf_ipex.yaml │ │ │ │ ├── data_loader_terabyte.py │ │ │ │ ├── data_utils.py │ │ │ │ ├── dlrm_data_pytorch.py │ │ │ │ ├── dlrm_s_pytorch.py │ │ │ │ ├── extend_distributed.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ └── speech_recognition │ │ │ ├── torchaudio_models │ │ │ └── quantization │ │ │ │ ├── ptq_dynamic │ │ │ │ └── fx │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_asr.py │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ │ └── ptq_static │ │ │ │ └── fx │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_asr.py │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ └── whisper_large │ │ │ └── quantization │ │ │ └── ptq_dynamic │ │ │ └── fx │ │ │ ├── README.md │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ ├── run_quant.sh │ │ │ └── run_whisper_large.py │ └── tensorflow │ │ ├── graph_networks │ │ └── graphsage │ │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── dataloader.py │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ ├── run_quant.sh │ │ │ └── utils.py │ │ ├── image_recognition │ │ ├── SavedModel │ │ │ ├── efficientnet_v2_b0 │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── mobilenet_v1 │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ └── mobilenet_v2 │ │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ ├── ViT │ │ │ └── pruning │ │ │ │ └── magnitude │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ └── requirements.txt │ │ ├── resnet_v2 │ │ │ ├── pruning │ │ │ │ └── magnitude │ │ │ │ │ ├── README.md │ │ │ │ │ └── main.py │ │ │ └── quantization │ │ │ │ └── qat │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ └── tensorflow_models │ │ │ ├── densenet121 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── densenet161 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── densenet169 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── distillation │ │ │ ├── README.md │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ └── run_distillation.sh │ │ │ ├── efficientnet-b0 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── imagenet_prepare │ │ │ ├── build_imagenet_data.py │ │ │ ├── download_and_convert_imagenet.sh │ │ │ ├── download_imagenet.sh │ │ │ ├── imagenet_lsvrc_2015_synsets.txt │ │ │ └── imagenet_metadata.txt │ │ │ ├── inception_resnet_v2 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── inception_v1 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── inception_v2 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── inception_v3 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── inception_v4 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── mobilenet_v1 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── mobilenet_v2 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── mobilenet_v3 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── prepare_dataset.sh │ │ │ ├── prepare_model.py │ │ │ ├── resnet101 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── resnet50_v1 │ │ │ ├── mixed_precision │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_mixed.sh │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── resnet50_v1_5 │ │ │ ├── export │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_export.sh │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── resnet_v2_101 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── resnet_v2_152 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── resnet_v2_50 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── vgg16 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ ├── vgg19 │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ └── vision_transformer │ │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ │ ├── nlp │ │ ├── bert_base_mrpc │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── __init__.py │ │ │ │ ├── modeling.py │ │ │ │ ├── optimization.py │ │ │ │ ├── prepare_dataset.py │ │ │ │ ├── prepare_model.sh │ │ │ │ ├── run_benchmark.sh │ │ │ │ ├── run_classifier.py │ │ │ │ ├── run_quant.sh │ │ │ │ └── tokenization.py │ │ ├── bert_large_squad │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── create_pretraining_data.py │ │ │ │ ├── create_tf_record.py │ │ │ │ ├── evaluate_squad.py │ │ │ │ ├── export_classifier.py │ │ │ │ ├── freeze_estimator_to_pb.py │ │ │ │ ├── generic_ops.py │ │ │ │ ├── modeling.py │ │ │ │ ├── optimization.py │ │ │ │ ├── prepare_dataset.sh │ │ │ │ ├── prepare_model.sh │ │ │ │ ├── run_benchmark.sh │ │ │ │ ├── run_quant.sh │ │ │ │ ├── tokenization.py │ │ │ │ └── tune_squad.py │ │ ├── bert_large_squad_model_zoo │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── create_pretraining_data.py │ │ │ │ ├── create_tf_record.py │ │ │ │ ├── evaluate_squad.py │ │ │ │ ├── export_classifier.py │ │ │ │ ├── freeze_estimator_to_pb.py │ │ │ │ ├── generic_ops.py │ │ │ │ ├── modeling.py │ │ │ │ ├── optimization.py │ │ │ │ ├── prepare_dataset.sh │ │ │ │ ├── prepare_model.sh │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ ├── run_quant.sh │ │ │ │ ├── tokenization.py │ │ │ │ └── tune_squad.py │ │ ├── distilbert_base │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── download_dataset.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ ├── run_inference.py │ │ │ │ └── run_quant.sh │ │ ├── large_language_models │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── gpt-j │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── prepare_model.sh │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ │ └── smoothquant │ │ │ │ ├── README.md │ │ │ │ ├── benchmark.py │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ ├── transformer_lt │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_dataset_model.sh │ │ │ │ ├── run_benchmark.sh │ │ │ │ ├── run_quant.sh │ │ │ │ └── utils │ │ │ │ ├── __init__.py │ │ │ │ ├── metrics.py │ │ │ │ ├── tokenizer.py │ │ │ │ └── tokenizer_test.py │ │ └── transformer_lt_mlperf │ │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── mlperf_compliance │ │ │ ├── __init__.py │ │ │ ├── _gnmt_tags.py │ │ │ ├── _maskrcnn_tags.py │ │ │ ├── _ncf_tags.py │ │ │ ├── _resnet_tags.py │ │ │ ├── _ssd_tags.py │ │ │ ├── _transformer_tags.py │ │ │ ├── mlperf_log.py │ │ │ ├── resnet_log_helper.py │ │ │ ├── tags.py │ │ │ ├── test_tag_set.py │ │ │ └── tf_mlperf_log.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ ├── run_inference.py │ │ │ ├── run_quant.sh │ │ │ └── utils │ │ │ ├── __init__.py │ │ │ ├── dataset.py │ │ │ ├── metrics.py │ │ │ ├── tokenizer.py │ │ │ └── tokenizer_test.py │ │ ├── object_detection │ │ ├── tensorflow_models │ │ │ ├── faster_rcnn_inception_v2 │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── faster_rcnn_resnet101 │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── faster_rcnn_resnet50 │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── mask_rcnn_inception_v2 │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── prepare_dataset.sh │ │ │ ├── requirements.txt │ │ │ ├── ssd_mobilenet_v1 │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ ├── README.md │ │ │ │ │ ├── main.py │ │ │ │ │ ├── prepare_model.py │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ ├── ssd_resnet34 │ │ │ │ └── quantization │ │ │ │ │ └── ptq │ │ │ │ │ ├── README.md │ │ │ │ │ ├── label_map.yaml │ │ │ │ │ ├── main.py │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ └── run_quant.sh │ │ │ └── ssd_resnet50_v1 │ │ │ │ └── quantization │ │ │ │ └── ptq │ │ │ │ ├── README.md │ │ │ │ ├── main.py │ │ │ │ ├── prepare_model.py │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ └── yolo_v3 │ │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── coco_constants.py │ │ │ ├── infer_detections.py │ │ │ ├── prepare_dataset.sh │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ ├── run_quant.sh │ │ │ └── utils.py │ │ ├── oob_models │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── dataloaders.py │ │ │ ├── find_outputs.py │ │ │ ├── model_detail.py │ │ │ ├── run_benchmark.sh │ │ │ ├── run_quant.sh │ │ │ ├── tf_benchmark.py │ │ │ ├── tf_savemodel_benchmark.py │ │ │ └── utils.py │ │ ├── recommendation │ │ └── wide_deep_large_ds │ │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── inference.py │ │ │ ├── preprocess_csv_tfrecords.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ │ ├── semantic_image_segmentation │ │ └── 3dunet-mlperf │ │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── brats_cal_images_list.txt │ │ │ ├── nnUNet │ │ │ ├── Task043_BraTS_2019.py │ │ │ ├── __init__.py │ │ │ ├── folds │ │ │ │ ├── fold0_validation.txt │ │ │ │ ├── fold1_validation.txt │ │ │ │ ├── fold2_validation.txt │ │ │ │ ├── fold3_validation.txt │ │ │ │ └── fold4_validation.txt │ │ │ ├── postprocess.py │ │ │ ├── preprocess.py │ │ │ └── setup.py │ │ │ ├── requirements.txt │ │ │ ├── run_accuracy.py │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ │ └── style_transfer │ │ └── arbitrary_style_transfer │ │ └── quantization │ │ └── ptq │ │ ├── README.md │ │ ├── content_images │ │ ├── colva_beach_sq.jpg │ │ └── golden_gate_sq.jpg │ │ ├── prepare_model.py │ │ ├── requirements.txt │ │ ├── run_benchmark.sh │ │ ├── run_quant.sh │ │ ├── style_images │ │ ├── kanagawa_great_wave.jpg │ │ └── zigzag_colorful.jpg │ │ └── style_tune.py ├── pytorch │ ├── cv │ │ ├── fp8_quant │ │ │ ├── README.md │ │ │ ├── extract_ILSVRC.sh │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ └── run_quant.sh │ │ ├── mixed_precision │ │ │ ├── README.md │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_autotune.sh │ │ │ └── run_benchmark.sh │ │ └── static_quant │ │ │ ├── README.md │ │ │ ├── extract_ILSVRC.sh │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ ├── diffusion_model │ │ └── diffusers │ │ │ ├── flux │ │ │ ├── README.md │ │ │ ├── dataset_split.py │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ │ │ └── stable_diffusion │ │ │ ├── fp8_quant │ │ │ ├── README.md │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ └── setup.sh │ │ │ ├── smooth_quant │ │ │ ├── README.md │ │ │ ├── images │ │ │ │ ├── fp32.jpg │ │ │ │ └── int8.jpg │ │ │ ├── latents.pt │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ ├── run_quant.sh │ │ │ └── sdxl_smooth_quant.py │ │ │ └── static_quant │ │ │ ├── README.md │ │ │ ├── download_dataset.sh │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ ├── image_recognition │ │ └── torchvision_models │ │ │ └── quantization │ │ │ └── static_quant │ │ │ └── ipex │ │ │ ├── README.md │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ ├── run_quant.sh │ │ │ └── utils.py │ ├── multimodal-modeling │ │ └── quantization │ │ │ └── auto_round │ │ │ ├── __init__.py │ │ │ ├── llama4 │ │ │ ├── README.md │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ ├── run_quant.sh │ │ │ └── setup.sh │ │ │ ├── mllm.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ ├── nlp │ │ └── huggingface_models │ │ │ ├── language-modeling │ │ │ └── quantization │ │ │ │ ├── fp8_quant │ │ │ │ ├── README.md │ │ │ │ ├── quantize.py │ │ │ │ ├── requirement.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ └── run_quant.sh │ │ │ │ ├── llm_qat │ │ │ │ ├── README.md │ │ │ │ ├── accelerate_config │ │ │ │ │ ├── ddp.yaml │ │ │ │ │ └── fsdp1.yaml │ │ │ │ ├── main.py │ │ │ │ ├── requirements.txt │ │ │ │ └── utils.py │ │ │ │ ├── mix-precision │ │ │ │ ├── README.md │ │ │ │ ├── quantize.py │ │ │ │ ├── recipes │ │ │ │ │ ├── Meta-Llama-3.1-8B-Instruct_7bits.json │ │ │ │ │ └── Meta-Llama-3.3-70B-Instruct_5bits.json │ │ │ │ ├── requirements.txt │ │ │ │ └── run_hf_inf.py │ │ │ │ ├── mx_quant │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ └── run_clm_no_trainer.py │ │ │ │ ├── smooth_quant │ │ │ │ ├── README.md │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ ├── run_clm_no_trainer.py │ │ │ │ ├── run_quant.sh │ │ │ │ └── utils.py │ │ │ │ ├── static_quant │ │ │ │ ├── ipex │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_clm_no_trainer.py │ │ │ │ │ ├── run_quant.sh │ │ │ │ │ └── utils.py │ │ │ │ └── pt2e │ │ │ │ │ ├── README.md │ │ │ │ │ ├── requirements.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_clm_no_trainer.py │ │ │ │ │ └── run_quant.sh │ │ │ │ ├── transformers │ │ │ │ └── weight_only │ │ │ │ │ └── text-generation │ │ │ │ │ ├── README.md │ │ │ │ │ ├── llm_quantization_recipes.md │ │ │ │ │ ├── requirements_GPU.txt │ │ │ │ │ ├── requirements_cpu_woq.txt │ │ │ │ │ ├── run_benchmark.sh │ │ │ │ │ ├── run_generation_cpu_woq.py │ │ │ │ │ ├── run_generation_gpu_woq.py │ │ │ │ │ └── run_tuning.sh │ │ │ │ └── weight_only │ │ │ │ ├── README.md │ │ │ │ ├── requirements-autoround-hpu.txt │ │ │ │ ├── requirements.txt │ │ │ │ ├── run_benchmark.sh │ │ │ │ ├── run_clm_no_trainer.py │ │ │ │ ├── run_quant.sh │ │ │ │ └── utils.py │ │ │ └── question-answering │ │ │ └── quantization │ │ │ └── static_quant │ │ │ └── ipex │ │ │ ├── README.md │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ ├── run_qa.py │ │ │ ├── run_quant.sh │ │ │ ├── trainer_qa.py │ │ │ └── utils_qa.py │ └── recommendation │ │ ├── dlrm │ │ └── static_quant │ │ │ └── ipex │ │ │ ├── CODE_OF_CONDUCT.md │ │ │ ├── CONTRIBUTING.md │ │ │ ├── LICENSE │ │ │ ├── README.md │ │ │ ├── data_loader_terabyte.py │ │ │ ├── data_utils.py │ │ │ ├── dlrm_data_pytorch.py │ │ │ ├── dlrm_s_pytorch.py │ │ │ ├── extend_distributed.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ │ └── dlrm_v2 │ │ └── fp8_quant │ │ └── cpu │ │ ├── README.md │ │ ├── data_process │ │ ├── __init__.py │ │ ├── dlrm_dataloader.py │ │ └── multi_hot_criteo.py │ │ ├── dlrm_model.py │ │ ├── main.py │ │ ├── requirements.txt │ │ └── setup.sh └── tensorflow │ ├── graph_networks │ └── graphsage │ │ └── quantization │ │ └── ptq │ │ ├── README.md │ │ ├── dataloader.py │ │ ├── main.py │ │ ├── requirements.txt │ │ ├── run_benchmark.sh │ │ ├── run_quant.sh │ │ └── utils.py │ ├── image_recognition │ ├── inception_v3 │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── data_process.py │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ ├── mobilenet_v2 │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── data_process.py │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ ├── prepare_dataset.sh │ ├── resnet_v2_50 │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── data_process.py │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ ├── vgg16 │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── data_process.py │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ └── vision_transformer │ │ └── quantization │ │ └── ptq │ │ ├── README.md │ │ ├── __init__.py │ │ ├── data_process.py │ │ ├── main.py │ │ ├── requirements.txt │ │ ├── run_benchmark.sh │ │ └── run_quant.sh │ ├── keras │ └── image_recognition │ │ ├── imagenet_prepare │ │ ├── build_imagenet_data.py │ │ ├── download_and_convert_imagenet.sh │ │ ├── download_imagenet.sh │ │ ├── imagenet_lsvrc_2015_synsets.txt │ │ └── imagenet_metadata.txt │ │ ├── inception_v3 │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── data_process.py │ │ │ ├── main.py │ │ │ ├── prepare_model.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ │ ├── prepare_dataset.sh │ │ └── resnet_v2_50 │ │ └── quantization │ │ └── ptq │ │ ├── README.md │ │ ├── data_process.py │ │ ├── main.py │ │ ├── prepare_model.py │ │ ├── requirements.txt │ │ ├── run_benchmark.sh │ │ └── run_quant.sh │ ├── nlp │ ├── bert_large_squad_model_zoo │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── create_pretraining_data.py │ │ │ ├── create_tf_record.py │ │ │ ├── data_process.py │ │ │ ├── main.py │ │ │ ├── prepare_dataset.sh │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ ├── run_quant.sh │ │ │ └── tokenization.py │ ├── large_language_models │ │ └── quantization │ │ │ └── ptq │ │ │ ├── gpt-j │ │ │ ├── README.md │ │ │ ├── main.py │ │ │ ├── prepare_model.py │ │ │ ├── prepare_model.sh │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ │ │ └── smoothquant │ │ │ ├── README.md │ │ │ ├── benchmark.py │ │ │ ├── main.py │ │ │ ├── requirements.txt │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ └── transformer_lt │ │ └── quantization │ │ └── ptq │ │ ├── README.md │ │ ├── main.py │ │ ├── prepare_dataset_model.sh │ │ ├── run_benchmark.sh │ │ ├── run_quant.sh │ │ └── utils │ │ ├── __init__.py │ │ ├── metrics.py │ │ ├── tokenizer.py │ │ └── tokenizer_test.py │ ├── object_detection │ ├── faster_rcnn_resnet50 │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── coco_tools.py │ │ │ ├── data_process.py │ │ │ ├── main.py │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ ├── mask_rcnn_inception_v2 │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── coco_tools.py │ │ │ ├── data_process.py │ │ │ ├── main.py │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ ├── prepare_dataset.sh │ ├── requirements.txt │ ├── ssd_mobilenet_v1 │ │ └── quantization │ │ │ └── ptq │ │ │ ├── README.md │ │ │ ├── coco_tools.py │ │ │ ├── data_process.py │ │ │ ├── main.py │ │ │ ├── prepare_model.py │ │ │ ├── run_benchmark.sh │ │ │ └── run_quant.sh │ └── yolo_v5 │ │ └── quantization │ │ └── ptq │ │ ├── README.md │ │ ├── main.py │ │ ├── prepare_dataset.sh │ │ ├── prepare_model.sh │ │ ├── requirements.txt │ │ ├── run_benchmark.sh │ │ └── run_quant.sh │ ├── recommendation │ └── wide_deep_large_ds │ │ └── quantization │ │ └── ptq │ │ ├── README.md │ │ ├── main.py │ │ ├── preprocess_csv_tfrecords.py │ │ ├── requirements.txt │ │ ├── run_benchmark.sh │ │ └── run_quant.sh │ ├── semantic_image_segmentation │ └── 3dunet-mlperf │ │ └── quantization │ │ └── ptq │ │ ├── README.md │ │ ├── __init__.py │ │ ├── brats_cal_images_list.txt │ │ ├── main.py │ │ ├── nnUNet │ │ ├── Task043_BraTS_2019.py │ │ ├── __init__.py │ │ ├── folds │ │ │ ├── fold0_validation.txt │ │ │ ├── fold1_validation.txt │ │ │ ├── fold2_validation.txt │ │ │ ├── fold3_validation.txt │ │ │ └── fold4_validation.txt │ │ ├── postprocess.py │ │ ├── preprocess.py │ │ └── setup.py │ │ ├── requirements.txt │ │ ├── run_benchmark.sh │ │ └── run_quant.sh │ └── style_transfer │ └── arbitrary_style_transfer │ └── quantization │ └── ptq │ ├── README.md │ ├── content_images │ ├── colva_beach_sq.jpg │ └── golden_gate_sq.jpg │ ├── data_process.py │ ├── main.py │ ├── prepare_model.py │ ├── requirements.txt │ ├── run_benchmark.sh │ ├── run_quant.sh │ └── style_images │ ├── kanagawa_great_wave.jpg │ └── zigzag_colorful.jpg ├── neural_compressor ├── __init__.py ├── adaptor │ ├── __init__.py │ ├── adaptor.py │ ├── keras.py │ ├── keras.yaml │ ├── keras_utils │ │ ├── __init__.py │ │ ├── conv2d.py │ │ ├── dense.py │ │ ├── depthwise_conv2d.py │ │ ├── pool2d.py │ │ ├── quantizer.py │ │ └── separable_conv2d.py │ ├── onnxrt.py │ ├── onnxrt.yaml │ ├── onnxrt_cuda.yaml │ ├── onnxrt_dml.yaml │ ├── onnxrt_dnnl.yaml │ ├── onnxrt_trt.yaml │ ├── ox_utils │ │ ├── __init__.py │ │ ├── calibration.py │ │ ├── calibrator.py │ │ ├── operators │ │ │ ├── __init__.py │ │ │ ├── activation.py │ │ │ ├── argmax.py │ │ │ ├── attention.py │ │ │ ├── binary_op.py │ │ │ ├── concat.py │ │ │ ├── conv.py │ │ │ ├── direct_q8.py │ │ │ ├── embed_layernorm.py │ │ │ ├── gather.py │ │ │ ├── gavgpool.py │ │ │ ├── gemm.py │ │ │ ├── lstm.py │ │ │ ├── matmul.py │ │ │ ├── maxpool.py │ │ │ ├── norm.py │ │ │ ├── ops.py │ │ │ ├── pad.py │ │ │ ├── pooling.py │ │ │ ├── reduce.py │ │ │ ├── resize.py │ │ │ ├── split.py │ │ │ └── unary_op.py │ │ ├── quantizer.py │ │ ├── smooth_quant.py │ │ ├── util.py │ │ └── weight_only.py │ ├── pytorch.py │ ├── pytorch_cpu.yaml │ ├── pytorch_gpu.yaml │ ├── pytorch_ipex.yaml │ ├── query.py │ ├── tensorflow.py │ ├── tensorflow.yaml │ ├── tensorflow_itex.yaml │ ├── tf_utils │ │ ├── __init__.py │ │ ├── graph_converter.py │ │ ├── graph_converter_without_calib.py │ │ ├── graph_rewriter │ │ │ ├── __init__.py │ │ │ ├── bf16 │ │ │ │ ├── __init__.py │ │ │ │ ├── bf16_convert.py │ │ │ │ └── dequantize_cast_optimizer.py │ │ │ ├── generic │ │ │ │ ├── __init__.py │ │ │ │ ├── convert_add_to_biasadd.py │ │ │ │ ├── convert_layout.py │ │ │ │ ├── convert_leakyrelu.py │ │ │ │ ├── convert_nan_to_random.py │ │ │ │ ├── convert_placeholder_to_const.py │ │ │ │ ├── dilated_contraction.py │ │ │ │ ├── dummy_biasadd.py │ │ │ │ ├── expanddims_optimizer.py │ │ │ │ ├── fetch_weight_from_reshape.py │ │ │ │ ├── fold_batch_norm.py │ │ │ │ ├── fold_constant.py │ │ │ │ ├── fuse_biasadd_add.py │ │ │ │ ├── fuse_column_wise_mul.py │ │ │ │ ├── fuse_conv_with_math.py │ │ │ │ ├── fuse_decomposed_bn.py │ │ │ │ ├── fuse_decomposed_in.py │ │ │ │ ├── fuse_gelu.py │ │ │ │ ├── fuse_layer_norm.py │ │ │ │ ├── fuse_pad_with_conv.py │ │ │ │ ├── fuse_pad_with_fp32_conv.py │ │ │ │ ├── fuse_reshape_transpose.py │ │ │ │ ├── graph_cse_optimizer.py │ │ │ │ ├── grappler_pass.py │ │ │ │ ├── insert_print_node.py │ │ │ │ ├── move_squeeze_after_relu.py │ │ │ │ ├── pre_optimize.py │ │ │ │ ├── remove_training_nodes.py │ │ │ │ ├── rename_batch_norm.py │ │ │ │ ├── split_shared_input.py │ │ │ │ ├── strip_equivalent_nodes.py │ │ │ │ ├── strip_unused_nodes.py │ │ │ │ └── switch_optimizer.py │ │ │ ├── graph_base.py │ │ │ ├── int8 │ │ │ │ ├── __init__.py │ │ │ │ ├── freeze_fake_quant.py │ │ │ │ ├── freeze_value.py │ │ │ │ ├── freeze_value_without_calib.py │ │ │ │ ├── fuse_conv_redundant_dequantize.py │ │ │ │ ├── fuse_conv_requantize.py │ │ │ │ ├── fuse_matmul_redundant_dequantize.py │ │ │ │ ├── fuse_matmul_requantize.py │ │ │ │ ├── meta_op_optimizer.py │ │ │ │ ├── post_hostconst_converter.py │ │ │ │ ├── post_quantized_op_cse.py │ │ │ │ ├── rnn_convert.py │ │ │ │ └── scale_propagation.py │ │ │ ├── onnx │ │ │ │ ├── __init__.py │ │ │ │ ├── onnx_graph.py │ │ │ │ ├── onnx_node.py │ │ │ │ ├── onnx_schema.py │ │ │ │ └── tf2onnx_utils.py │ │ │ └── qdq │ │ │ │ ├── __init__.py │ │ │ │ ├── insert_qdq_pattern.py │ │ │ │ ├── merge_duplicated_qdq.py │ │ │ │ └── share_qdq_y_pattern.py │ │ ├── graph_util.py │ │ ├── quantize_graph │ │ │ ├── __init__.py │ │ │ ├── qat │ │ │ │ ├── __init__.py │ │ │ │ ├── fake_quantize.py │ │ │ │ ├── quantize_config.py │ │ │ │ ├── quantize_helper.py │ │ │ │ ├── quantize_layers │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── optimize_layer.py │ │ │ │ │ ├── quantize_layer_add.py │ │ │ │ │ ├── quantize_layer_base.py │ │ │ │ │ └── quantize_layer_bn.py │ │ │ │ └── quantize_wrapper.py │ │ │ ├── qdq │ │ │ │ ├── __init__.py │ │ │ │ ├── fuse_qdq_bn.py │ │ │ │ ├── fuse_qdq_concatv2.py │ │ │ │ ├── fuse_qdq_conv.py │ │ │ │ ├── fuse_qdq_deconv.py │ │ │ │ ├── fuse_qdq_in.py │ │ │ │ ├── fuse_qdq_matmul.py │ │ │ │ ├── fuse_qdq_pooling.py │ │ │ │ └── optimize_qdq.py │ │ │ ├── quantize_graph_base.py │ │ │ ├── quantize_graph_bn.py │ │ │ ├── quantize_graph_concatv2.py │ │ │ ├── quantize_graph_conv.py │ │ │ ├── quantize_graph_for_intel_cpu.py │ │ │ ├── quantize_graph_matmul.py │ │ │ └── quantize_graph_pooling.py │ │ ├── quantize_graph_common.py │ │ ├── smooth_quant_calibration.py │ │ ├── smooth_quant_scaler.py │ │ ├── tf2onnx_converter.py │ │ ├── transform_graph │ │ │ ├── __init__.py │ │ │ ├── bias_correction.py │ │ │ ├── graph_transform_base.py │ │ │ ├── insert_logging.py │ │ │ └── rerange_quantized_concat.py │ │ └── util.py │ └── torch_utils │ │ ├── __init__.py │ │ ├── auto_round.py │ │ ├── awq.py │ │ ├── bf16_convert.py │ │ ├── gptq.py │ │ ├── hawq_metric.py │ │ ├── layer_wise_quant │ │ ├── __init__.py │ │ ├── modified_pickle.py │ │ ├── quantize.py │ │ ├── torch_load.py │ │ └── utils.py │ │ ├── mixed_precision.py │ │ ├── model_wrapper.py │ │ ├── pattern_detector.py │ │ ├── symbolic_trace.py │ │ ├── teq.py │ │ ├── util.py │ │ ├── waq │ │ ├── README.md │ │ ├── __init__.py │ │ ├── auto_alpha.py │ │ ├── calibration.py │ │ ├── graph_trace.py │ │ ├── smooth_quant.py │ │ └── utils.py │ │ └── weight_only.py ├── algorithm │ ├── __init__.py │ ├── algorithm.py │ ├── fast_bias_correction.py │ ├── smooth_quant.py │ └── weight_correction.py ├── common │ ├── __init__.py │ ├── base_config.py │ ├── base_tuning.py │ ├── tuning_param.py │ ├── utils │ │ ├── __init__.py │ │ ├── constants.py │ │ ├── logger.py │ │ ├── save_load.py │ │ └── utility.py │ └── version.py ├── compression │ ├── __init__.py │ ├── callbacks.py │ ├── distillation │ │ ├── __init__.py │ │ ├── criterions.py │ │ ├── optimizers.py │ │ └── utility.py │ ├── hpo │ │ ├── __init__.py │ │ ├── sa_optimizer.py │ │ ├── search_algorithms.py │ │ └── search_space.py │ └── pruner │ │ ├── README.md │ │ ├── __init__.py │ │ ├── criteria.py │ │ ├── dsnot.py │ │ ├── model_slim │ │ ├── README.md │ │ ├── __init__.py │ │ ├── auto_slim.py │ │ ├── imgs │ │ │ └── auto_slim_feed_forward_network.png │ │ ├── pattern_analyzer.py │ │ └── weight_slim.py │ │ ├── patterns │ │ ├── __init__.py │ │ ├── base.py │ │ ├── mha.py │ │ ├── ninm.py │ │ └── nxm.py │ │ ├── pruners │ │ ├── __init__.py │ │ ├── base.py │ │ ├── basic.py │ │ ├── block_mask.py │ │ ├── mha.py │ │ ├── pattern_lock.py │ │ ├── progressive.py │ │ ├── retrain_free.py │ │ └── sparse_gpt.py │ │ ├── pruning.py │ │ ├── regs.py │ │ ├── schedulers.py │ │ ├── tf_criteria.py │ │ ├── utils.py │ │ └── wanda │ │ ├── __init__.py │ │ ├── prune.py │ │ ├── utils.py │ │ └── wrapper.py ├── config.py ├── contrib │ ├── __init__.py │ └── strategy │ │ ├── __init__.py │ │ └── tpe.py ├── data │ ├── __init__.py │ ├── dataloaders │ │ ├── __init__.py │ │ ├── base_dataloader.py │ │ ├── dataloader.py │ │ ├── default_dataloader.py │ │ ├── fetcher.py │ │ ├── onnxrt_dataloader.py │ │ ├── pytorch_dataloader.py │ │ ├── sampler.py │ │ └── tensorflow_dataloader.py │ ├── datasets │ │ ├── __init__.py │ │ ├── bert_dataset.py │ │ ├── coco_dataset.py │ │ ├── dataset.py │ │ ├── dummy_dataset.py │ │ ├── dummy_dataset_v2.py │ │ ├── imagenet_dataset.py │ │ └── style_transfer_dataset.py │ ├── filters │ │ ├── __init__.py │ │ ├── coco_filter.py │ │ └── filter.py │ └── transforms │ │ ├── __init__.py │ │ ├── coco_transform.py │ │ ├── imagenet_transform.py │ │ ├── postprocess.py │ │ ├── tokenization.py │ │ └── transform.py ├── evaluation │ ├── __init__.py │ ├── bigcode_eval │ │ ├── __init__.py │ │ └── evaluator.py │ ├── hf_eval │ │ ├── __init__.py │ │ ├── datasets │ │ │ ├── cnn_dailymail.py │ │ │ └── cnn_validation.json │ │ ├── evaluator.py │ │ └── hf_datasets │ │ │ ├── __init__.py │ │ │ └── cnn_dailymail.py │ └── lm_eval │ │ ├── __init__.py │ │ ├── accuracy.py │ │ ├── models │ │ ├── __init__.py │ │ └── huggingface.py │ │ └── utils.py ├── metric │ ├── __init__.py │ ├── bleu.py │ ├── bleu_util.py │ ├── coco_label_map.py │ ├── coco_tools.py │ ├── evaluate_squad.py │ ├── f1.py │ └── metric.py ├── mix_precision.py ├── model │ ├── __init__.py │ ├── base_model.py │ ├── keras_model.py │ ├── model.py │ ├── nets_factory.py │ ├── onnx_model.py │ ├── tensorflow_model.py │ └── torch_model.py ├── objective.py ├── profiling │ ├── __init__.py │ ├── parser │ │ ├── __init__.py │ │ ├── factory.py │ │ ├── onnx_parser │ │ │ ├── __init__.py │ │ │ ├── factory.py │ │ │ └── parser.py │ │ ├── parser.py │ │ ├── result.py │ │ └── tensorflow_parser │ │ │ ├── __init__.py │ │ │ ├── factory.py │ │ │ └── parser.py │ └── profiler │ │ ├── __init__.py │ │ ├── factory.py │ │ ├── onnxrt_profiler │ │ ├── __init__.py │ │ ├── factory.py │ │ ├── profiler.py │ │ └── utils.py │ │ ├── profiler.py │ │ └── tensorflow_profiler │ │ ├── __init__.py │ │ ├── factory.py │ │ ├── profiler.py │ │ └── utils.py ├── quantization.py ├── strategy │ ├── __init__.py │ ├── auto.py │ ├── auto_mixed_precision.py │ ├── basic.py │ ├── bayesian.py │ ├── conservative.py │ ├── exhaustive.py │ ├── hawq_v2.py │ ├── mse.py │ ├── mse_v2.py │ ├── random.py │ ├── strategy.py │ └── utils │ │ ├── __init__.py │ │ ├── constant.py │ │ ├── tuning_sampler.py │ │ ├── tuning_space.py │ │ ├── tuning_structs.py │ │ └── utility.py ├── tensorflow │ ├── __init__.py │ ├── algorithms │ │ ├── __init__.py │ │ ├── smoother │ │ │ ├── __init__.py │ │ │ ├── calibration.py │ │ │ ├── core.py │ │ │ └── scaler.py │ │ └── static_quant │ │ │ ├── __init__.py │ │ │ ├── keras.py │ │ │ ├── keras.yaml │ │ │ ├── tensorflow.py │ │ │ ├── tensorflow.yaml │ │ │ └── tensorflow_itex.yaml │ ├── keras │ │ ├── __init__.py │ │ ├── layers │ │ │ ├── __init__.py │ │ │ ├── conv2d.py │ │ │ ├── dense.py │ │ │ ├── depthwise_conv2d.py │ │ │ ├── layer_initializer.py │ │ │ ├── pool2d.py │ │ │ └── separable_conv2d.py │ │ └── quantization │ │ │ ├── __init__.py │ │ │ └── config.py │ ├── quantization │ │ ├── __init__.py │ │ ├── algorithm_entry.py │ │ ├── autotune.py │ │ ├── config.py │ │ ├── quantize.py │ │ └── utils │ │ │ ├── __init__.py │ │ │ ├── graph_converter.py │ │ │ ├── graph_rewriter │ │ │ ├── __init__.py │ │ │ ├── bf16 │ │ │ │ ├── __init__.py │ │ │ │ ├── bf16_convert.py │ │ │ │ └── dequantize_cast_optimizer.py │ │ │ ├── generic │ │ │ │ ├── __init__.py │ │ │ │ ├── convert_add_to_biasadd.py │ │ │ │ ├── convert_layout.py │ │ │ │ ├── convert_leakyrelu.py │ │ │ │ ├── convert_nan_to_random.py │ │ │ │ ├── convert_placeholder_to_const.py │ │ │ │ ├── dilated_contraction.py │ │ │ │ ├── dummy_biasadd.py │ │ │ │ ├── expanddims_optimizer.py │ │ │ │ ├── fetch_weight_from_reshape.py │ │ │ │ ├── fold_batch_norm.py │ │ │ │ ├── fold_constant.py │ │ │ │ ├── fuse_biasadd_add.py │ │ │ │ ├── fuse_column_wise_mul.py │ │ │ │ ├── fuse_conv_with_math.py │ │ │ │ ├── fuse_decomposed_bn.py │ │ │ │ ├── fuse_decomposed_in.py │ │ │ │ ├── fuse_gelu.py │ │ │ │ ├── fuse_layer_norm.py │ │ │ │ ├── fuse_pad_with_conv.py │ │ │ │ ├── fuse_pad_with_fp32_conv.py │ │ │ │ ├── fuse_reshape_transpose.py │ │ │ │ ├── graph_cse_optimizer.py │ │ │ │ ├── grappler_pass.py │ │ │ │ ├── insert_print_node.py │ │ │ │ ├── move_squeeze_after_relu.py │ │ │ │ ├── pre_optimize.py │ │ │ │ ├── remove_training_nodes.py │ │ │ │ ├── rename_batch_norm.py │ │ │ │ ├── split_shared_input.py │ │ │ │ ├── strip_equivalent_nodes.py │ │ │ │ ├── strip_unused_nodes.py │ │ │ │ └── switch_optimizer.py │ │ │ ├── graph_base.py │ │ │ ├── int8 │ │ │ │ ├── __init__.py │ │ │ │ ├── freeze_fake_quant.py │ │ │ │ ├── freeze_value.py │ │ │ │ ├── fuse_conv_redundant_dequantize.py │ │ │ │ ├── fuse_conv_requantize.py │ │ │ │ ├── fuse_matmul_redundant_dequantize.py │ │ │ │ ├── fuse_matmul_requantize.py │ │ │ │ ├── meta_op_optimizer.py │ │ │ │ ├── post_hostconst_converter.py │ │ │ │ ├── post_quantized_op_cse.py │ │ │ │ └── scale_propagation.py │ │ │ └── qdq │ │ │ │ ├── __init__.py │ │ │ │ ├── insert_qdq_pattern.py │ │ │ │ ├── merge_duplicated_qdq.py │ │ │ │ └── share_qdq_y_pattern.py │ │ │ ├── graph_util.py │ │ │ ├── quantize_graph │ │ │ ├── __init__.py │ │ │ ├── qdq │ │ │ │ ├── __init__.py │ │ │ │ ├── fuse_qdq_bn.py │ │ │ │ ├── fuse_qdq_concatv2.py │ │ │ │ ├── fuse_qdq_conv.py │ │ │ │ ├── fuse_qdq_deconv.py │ │ │ │ ├── fuse_qdq_in.py │ │ │ │ ├── fuse_qdq_matmul.py │ │ │ │ ├── fuse_qdq_pooling.py │ │ │ │ └── optimize_qdq.py │ │ │ ├── quantize_graph_base.py │ │ │ ├── quantize_graph_bn.py │ │ │ ├── quantize_graph_concatv2.py │ │ │ ├── quantize_graph_conv.py │ │ │ ├── quantize_graph_for_intel_cpu.py │ │ │ ├── quantize_graph_matmul.py │ │ │ └── quantize_graph_pooling.py │ │ │ ├── quantize_graph_common.py │ │ │ ├── transform_graph │ │ │ ├── __init__.py │ │ │ ├── bias_correction.py │ │ │ ├── graph_transform_base.py │ │ │ ├── insert_logging.py │ │ │ └── rerange_quantized_concat.py │ │ │ └── utility.py │ └── utils │ │ ├── __init__.py │ │ ├── constants.py │ │ ├── data.py │ │ ├── model.py │ │ ├── model_wrappers.py │ │ └── utility.py ├── torch │ ├── __init__.py │ ├── algorithms │ │ ├── __init__.py │ │ ├── base_algorithm.py │ │ ├── fp8_quant │ │ │ ├── __init__.py │ │ │ ├── _core │ │ │ │ ├── __init__.py │ │ │ │ ├── common.py │ │ │ │ ├── fp_utils.py │ │ │ │ ├── measure.py │ │ │ │ ├── patching_common.py │ │ │ │ ├── quant_dequant.py │ │ │ │ ├── quantize.py │ │ │ │ ├── quantized_func_wrappers │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── cpu │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ └── cpu_quantized_func_wrapper.py │ │ │ │ │ ├── hpu │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ └── hpu_quantized_func_wrapper.py │ │ │ │ │ ├── quantized_func_wrapper.py │ │ │ │ │ ├── quantized_func_wrapper_api.py │ │ │ │ │ └── xpu │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ └── xpu_quantized_func_wrapper.py │ │ │ │ ├── save_measure │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── hook_logic.py │ │ │ │ │ ├── save_file_proccess.py │ │ │ │ │ └── save_files.py │ │ │ │ ├── scale.py │ │ │ │ ├── scale_handler.py │ │ │ │ ├── scale_methods │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── ops_quantizer.py │ │ │ │ │ ├── round_scales_function.py │ │ │ │ │ ├── scale_method_config.py │ │ │ │ │ ├── scale_method_factory.py │ │ │ │ │ ├── scale_method_parser.py │ │ │ │ │ └── scales_method.py │ │ │ │ ├── utils.py │ │ │ │ └── vllm_functions.py │ │ │ ├── _quant_common │ │ │ │ ├── __init__.py │ │ │ │ ├── helper_modules.py │ │ │ │ └── quant_config.py │ │ │ ├── common.py │ │ │ ├── custom_config │ │ │ │ ├── __init__.py │ │ │ │ ├── custom_example.json │ │ │ │ ├── llama_measure.json │ │ │ │ ├── llama_quant.json │ │ │ │ ├── measure_config.json │ │ │ │ └── quant_config.json │ │ │ ├── model_configs.py │ │ │ ├── observer.py │ │ │ ├── patched_module_base.py │ │ │ ├── prepare_quant │ │ │ │ ├── __init__.py │ │ │ │ └── prepare_model.py │ │ │ ├── quantizer.py │ │ │ ├── save_load.py │ │ │ ├── scaling_method_base.py │ │ │ ├── scripts │ │ │ │ ├── __init__.py │ │ │ │ └── postprocessing_vllm_measurements.py │ │ │ └── utils │ │ │ │ ├── __init__.py │ │ │ │ └── logger.py │ │ ├── layer_wise │ │ │ ├── __init__.py │ │ │ ├── load.py │ │ │ ├── modified_pickle.py │ │ │ └── utils.py │ │ ├── mixed_low_precision │ │ │ ├── __init__.py │ │ │ ├── custom_methods │ │ │ │ ├── __init__.py │ │ │ │ ├── gptq.py │ │ │ │ ├── quarot.py │ │ │ │ └── quarot_utils.py │ │ │ ├── internal │ │ │ │ ├── methods_scripts │ │ │ │ │ └── gptq_quant_and_eval.sh │ │ │ │ └── quantization_methods │ │ │ │ │ └── quantize_gptq.py │ │ │ ├── maxabs_quant.json │ │ │ ├── modules.py │ │ │ └── quantizer.py │ │ ├── mixed_precision │ │ │ ├── __init__.py │ │ │ ├── half_precision_convert.py │ │ │ └── module_wrappers.py │ │ ├── mx_quant │ │ │ ├── __init__.py │ │ │ ├── mx.py │ │ │ └── utils.py │ │ ├── pt2e_quant │ │ │ ├── __init__.py │ │ │ ├── core.py │ │ │ ├── half_precision_rewriter.py │ │ │ ├── save_load.py │ │ │ └── utility.py │ │ ├── qat │ │ │ ├── __init__.py │ │ │ ├── quant_linear.py │ │ │ ├── quant_utils.py │ │ │ └── tensor_quantizer.py │ │ ├── smooth_quant │ │ │ ├── __init__.py │ │ │ ├── save_load.py │ │ │ ├── smooth_quant.py │ │ │ └── utility.py │ │ ├── static_quant │ │ │ ├── __init__.py │ │ │ ├── save_load.py │ │ │ ├── static_quant.py │ │ │ └── utility.py │ │ └── weight_only │ │ │ ├── __init__.py │ │ │ ├── autoround.py │ │ │ ├── awq.py │ │ │ ├── gptq.py │ │ │ ├── hqq │ │ │ ├── __init__.py │ │ │ ├── bitpack.py │ │ │ ├── config.py │ │ │ ├── core.py │ │ │ ├── optimizer.py │ │ │ ├── qtensor.py │ │ │ └── quantizer.py │ │ │ ├── modules.py │ │ │ ├── rtn.py │ │ │ ├── save_load.py │ │ │ ├── teq.py │ │ │ └── utility.py │ ├── export │ │ ├── __init__.py │ │ ├── export_hf.py │ │ └── pt2e_export.py │ ├── quantization │ │ ├── __init__.py │ │ ├── algorithm_entry.py │ │ ├── autotune.py │ │ ├── config.py │ │ ├── quantize.py │ │ └── save_load_entry.py │ └── utils │ │ ├── __init__.py │ │ ├── auto_accelerator.py │ │ ├── bit_packer.py │ │ ├── block_wise.py │ │ ├── constants.py │ │ ├── environ.py │ │ ├── llm_utility.py │ │ └── utility.py ├── training.py ├── transformers │ ├── __init__.py │ ├── generation │ │ ├── __init__.py │ │ ├── beam_search.py │ │ └── greedy_search.py │ ├── models │ │ ├── __init__.py │ │ └── modeling_auto.py │ ├── quantization │ │ ├── __init__.py │ │ └── utils.py │ └── utils │ │ ├── __init__.py │ │ └── quantization_config.py ├── utils │ ├── __init__.py │ ├── collect_layer_histogram.py │ ├── constant.py │ ├── create_obj_from_config.py │ ├── export │ │ ├── __init__.py │ │ ├── qlinear2qdq.py │ │ ├── tf2onnx.py │ │ └── torch2onnx.py │ ├── kl_divergence.py │ ├── load_huggingface.py │ ├── logger.py │ ├── options.py │ ├── pytorch.py │ ├── utility.py │ └── weights_details.py └── version.py ├── pyproject.toml ├── requirements.txt ├── requirements_pt.txt ├── requirements_tf.txt ├── setup.cfg ├── setup.py ├── test ├── 3x │ ├── common │ │ ├── test_common.py │ │ ├── test_logger.py │ │ ├── test_param.py │ │ └── test_utility.py │ ├── tensorflow │ │ ├── keras │ │ │ ├── requirements.txt │ │ │ ├── test_config.py │ │ │ ├── test_layers.py │ │ │ └── test_model_wrappers.py │ │ ├── quantization │ │ │ ├── ptq │ │ │ │ ├── newapi │ │ │ │ │ ├── test_bias_correction_newapi.py │ │ │ │ │ ├── test_big_saved_model.py │ │ │ │ │ ├── test_graph_biasadd_add_fusion.py │ │ │ │ │ ├── test_graph_conv_fusion_newapi.py │ │ │ │ │ ├── test_graph_conv_requantize_fusion.py │ │ │ │ │ ├── test_graph_depthwiseconv_fusion.py │ │ │ │ │ ├── test_graph_dequantize_cast_optimizer_newapi.py │ │ │ │ │ ├── test_graph_dq_cast_fusion.py │ │ │ │ │ ├── test_graph_fuse_pad_conv_fp32.py │ │ │ │ │ ├── test_graph_qdq_bn_fusion.py │ │ │ │ │ ├── test_graph_qdq_concat_fusion.py │ │ │ │ │ ├── test_graph_qdq_conv3d_fusion.py │ │ │ │ │ ├── test_graph_qdq_conv_fusion.py │ │ │ │ │ ├── test_graph_qdq_depthwiseconv_fusion.py │ │ │ │ │ ├── test_graph_qdq_matmul_fusion.py │ │ │ │ │ ├── test_graph_qdq_new_conv_fusion.py │ │ │ │ │ ├── test_graph_qdq_pooling_fusion.py │ │ │ │ │ └── test_use_reshape_transpose.py │ │ │ │ ├── test_auto_input_output.py │ │ │ │ ├── test_bf16_convert.py │ │ │ │ ├── test_bias_correction.py │ │ │ │ ├── test_data_pipline.py │ │ │ │ ├── test_fold_batch_norm.py │ │ │ │ ├── test_fold_const.py │ │ │ │ ├── test_gpu.py │ │ │ │ ├── test_graph_cac.py │ │ │ │ ├── test_graph_column_wise_mul.py │ │ │ │ ├── test_graph_concat.py │ │ │ │ ├── test_graph_conv_add_relu_fusion.py │ │ │ │ ├── test_graph_conv_as_output.py │ │ │ │ ├── test_graph_conv_fusion.py │ │ │ │ ├── test_graph_conv_math.py │ │ │ │ ├── test_graph_convert_layout.py │ │ │ │ ├── test_graph_convert_leakyrelu.py │ │ │ │ ├── test_graph_convert_nan.py │ │ │ │ ├── test_graph_cse_optimization.py │ │ │ │ ├── test_graph_debug_mode.py │ │ │ │ ├── test_graph_dequantize_cast_optimizer.py │ │ │ │ ├── test_graph_expanddims_optimizer.py │ │ │ │ ├── test_graph_fetch_weight_from_reshape.py │ │ │ │ ├── test_graph_fold_bn.py │ │ │ │ ├── test_graph_fuse_decomposed_bn.py │ │ │ │ ├── test_graph_fuse_gelu.py │ │ │ │ ├── test_graph_input_output.py │ │ │ │ ├── test_graph_insert_logging.py │ │ │ │ ├── test_graph_library_detection.py │ │ │ │ ├── test_graph_matmul_fusion.py │ │ │ │ ├── test_graph_meta_pass.py │ │ │ │ ├── test_graph_pad_conv.py │ │ │ │ ├── test_graph_post_cse_optimize.py │ │ │ │ ├── test_graph_search_patterns.py │ │ │ │ ├── test_graph_switch_optimizer.py │ │ │ │ ├── test_graph_util.py │ │ │ │ ├── test_grappler_pass.py │ │ │ │ ├── test_move_squeeze_after_relu.py │ │ │ │ ├── test_quantize_input.py │ │ │ │ ├── test_query_yaml.py │ │ │ │ ├── test_remove_training_nodes.py │ │ │ │ ├── test_rnn.py │ │ │ │ ├── test_share_nodes_graph.py │ │ │ │ ├── test_strip_equivalent_nodes.py │ │ │ │ └── test_utils.py │ │ │ └── test_smooth_quant.py │ │ ├── requirements.txt │ │ ├── test_autotune.py │ │ ├── test_config.py │ │ ├── test_model_wrappers.py │ │ └── test_quantize_model.py │ └── torch │ │ ├── algorithms │ │ ├── fp8_quant │ │ │ ├── __init__.py │ │ │ ├── conftest.py │ │ │ ├── fp8_tests.py │ │ │ ├── pytest.ini │ │ │ ├── test_basic.py │ │ │ ├── test_hpu_utils.py │ │ │ ├── test_jsons │ │ │ │ ├── test_fake_measure.json │ │ │ │ ├── test_hw_aligned_quant.json │ │ │ │ ├── test_hw_quant.json │ │ │ │ ├── test_hw_quant_ignored_unmeasured_models.json │ │ │ │ ├── test_measure.json │ │ │ │ ├── test_pow2_quant.json │ │ │ │ └── test_unit_quant.json │ │ │ ├── test_register_apis.py │ │ │ ├── test_utils.py │ │ │ ├── tester.py │ │ │ └── unit_tests │ │ │ │ ├── __init__.py │ │ │ │ ├── test_block_wise.py │ │ │ │ ├── test_calibration_counter.py │ │ │ │ ├── test_deepspeed.py │ │ │ │ ├── test_fakequant.py │ │ │ │ ├── test_fp8_config.py │ │ │ │ ├── test_functions │ │ │ │ ├── __init__.py │ │ │ │ ├── test_config_json.py │ │ │ │ └── test_matmul_fp8.py │ │ │ │ ├── test_layers │ │ │ │ ├── __init__.py │ │ │ │ ├── test_conv2d.py │ │ │ │ ├── test_linear.py │ │ │ │ └── test_matmul.py │ │ │ │ ├── test_qdq.py │ │ │ │ ├── test_quarot.py │ │ │ │ ├── test_runtime_scale_patching.py │ │ │ │ ├── test_save_load.py │ │ │ │ ├── test_scalar.py │ │ │ │ └── test_scale_method_config.py │ │ ├── fp8_quant_cpu │ │ │ └── unit_tests │ │ │ │ ├── test_cpu_basic.py │ │ │ │ └── test_cpu_save_load.py │ │ ├── fp8_quant_xpu │ │ │ └── unit_tests │ │ │ │ ├── aux_files │ │ │ │ └── empty_measure_hooks_maxabs.npz │ │ │ │ └── test_xpu_basic.py │ │ ├── mx_quant │ │ │ └── test_mx_utility.py │ │ ├── pt2e_quant │ │ │ ├── test_half_precision_rewriter.py │ │ │ └── test_pt2e_w8a8.py │ │ ├── qat │ │ │ ├── test_qat.py │ │ │ ├── test_quant_utils.py │ │ │ └── test_quantizer_and_linear.py │ │ ├── smooth_quant │ │ │ └── test_sq_utility.py │ │ └── weight_only │ │ │ ├── test_hqq_quantizer.py │ │ │ ├── test_teq_quantizer.py │ │ │ ├── test_woq_module.py │ │ │ └── test_woq_utility.py │ │ ├── quantization │ │ ├── fp8_quant │ │ │ ├── conftest.py │ │ │ ├── model_configs │ │ │ │ └── tiny_gptj.json │ │ │ ├── test_fp8_jsons │ │ │ │ ├── test_hw_quant.json │ │ │ │ ├── test_measure.json │ │ │ │ └── test_pow2_w4a8_quant.json │ │ │ ├── test_fp8_static_quant.py │ │ │ ├── test_gptq_mixed_precision.py │ │ │ ├── test_layer_wise.py │ │ │ └── test_save_load.py │ │ ├── jsons │ │ │ └── test_hw_quant.json │ │ ├── test_mx_quant.py │ │ ├── test_pt2e_quant.py │ │ ├── test_smooth_quant.py │ │ ├── test_static_quant.py │ │ └── weight_only │ │ │ ├── test_autoround.py │ │ │ ├── test_awq.py │ │ │ ├── test_gptq.py │ │ │ ├── test_hqq.py │ │ │ ├── test_load.py │ │ │ ├── test_mixed_algos.py │ │ │ ├── test_rtn.py │ │ │ ├── test_teq.py │ │ │ ├── test_transformers.py │ │ │ └── test_woq_utils.py │ │ ├── requirements.txt │ │ ├── test_autotune.py │ │ ├── test_config.py │ │ └── utils │ │ ├── test_auto_accelerator.py │ │ └── test_torch_utility.py ├── adaptor │ ├── onnxrt_adaptor │ │ ├── test_adaptor_onnxrt.py │ │ ├── test_layer_wise.py │ │ ├── test_onnxrt_augment.py │ │ ├── test_onnxrt_operators.py │ │ └── test_weight_only_adaptor_onnxrt.py │ ├── pytorch_adaptor │ │ ├── test_adaptor_pytorch_2x.py │ │ ├── test_adaptor_security.py │ │ └── test_weight_only_adaptor_pytorch.py │ ├── tensorflow_adaptor │ │ ├── test_bf16_convert.py │ │ ├── test_smooth_quant_tf.py │ │ ├── test_tensorflow_bias_correction.py │ │ ├── test_tensorflow_convert_layout.py │ │ ├── test_tensorflow_data_pipline.py │ │ ├── test_tensorflow_fold_batch_norm.py │ │ ├── test_tensorflow_fold_const.py │ │ ├── test_tensorflow_get_estimator_graph.py │ │ ├── test_tensorflow_gpu.py │ │ ├── test_tensorflow_graph_cac.py │ │ ├── test_tensorflow_graph_column_wise_mul.py │ │ ├── test_tensorflow_graph_conv_add_relu_fusion.py │ │ ├── test_tensorflow_graph_conv_math.py │ │ ├── test_tensorflow_graph_convert_layout.py │ │ ├── test_tensorflow_graph_convert_leakyrelu.py │ │ ├── test_tensorflow_graph_convert_nan.py │ │ ├── test_tensorflow_graph_cse_optimization.py │ │ ├── test_tensorflow_graph_dequantize_cast_optimizer.py │ │ ├── test_tensorflow_graph_expanddims_optimizer.py │ │ ├── test_tensorflow_graph_fetch_weight_from_reshape.py │ │ ├── test_tensorflow_graph_fold_bn.py │ │ ├── test_tensorflow_graph_fuse_decomposed_bn.py │ │ ├── test_tensorflow_graph_fuse_gelu.py │ │ ├── test_tensorflow_graph_input_output.py │ │ ├── test_tensorflow_graph_insert_logging.py │ │ ├── test_tensorflow_graph_library_detection.py │ │ ├── test_tensorflow_graph_search_patterns.py │ │ ├── test_tensorflow_graph_switch_optimizer.py │ │ ├── test_tensorflow_graph_util.py │ │ ├── test_tensorflow_grappler_pass.py │ │ ├── test_tensorflow_move_squeeze_after_relu.py │ │ ├── test_tensorflow_query_yaml.py │ │ ├── test_tensorflow_remove_training_nodes.py │ │ ├── test_tensorflow_rnn.py │ │ ├── test_tensorflow_share_nodes_graph.py │ │ └── test_tf_util.py │ └── test_pytorch_layer_scale.py ├── algorithm │ ├── ipex_config_tmp.json │ ├── modeling_gptj.py │ ├── test_layer_wise_quant.py │ ├── test_lwq_weight_only.py │ ├── test_smooth_quant.py │ └── test_smooth_quant_onnx.py ├── config │ └── test_config_2x.py ├── data │ ├── test_dataloader.py │ ├── test_filter.py │ └── test_transform.py ├── distillation │ ├── test_distillation_2.x.py │ └── test_self_distillation_2.x.py ├── distributed │ └── test_distributed_tf_dataloader.py ├── export │ ├── test_onnx_qlieanr_to_qdq.py │ └── test_torch2onnx.py ├── hpo │ └── test_hpo.py ├── images │ └── cat.jpg ├── ipex │ └── test_adaptor_ipex.py ├── itex │ ├── test_keras_in_keras_out.py │ ├── test_smooth_quant_itex.py │ ├── test_tensorflow_itex_2.x.py │ └── test_tensorflow_qdq_convert_to_onnx_qdq.py ├── metric │ ├── test_coco_tools.py │ ├── test_metrics.py │ ├── test_metrics_2x.py │ └── test_mse_2x.py ├── mixed_precision │ ├── test_mixed_precision.py │ └── test_mixed_precision_keras_model.py ├── model │ ├── test_model.py │ ├── test_model_pytorch.py │ ├── test_onnx_model.py │ └── test_tensorflow_auto_input_output.py ├── objective │ └── test_objective.py ├── pruning_with_pt │ ├── pruning_2.x │ │ ├── test_auto_excluding_classifier.py │ │ ├── test_auto_slim.py │ │ ├── test_conv_pruning.py │ │ ├── test_pruning.py │ │ ├── test_pruning_block.py │ │ ├── test_pruning_config.py │ │ ├── test_pruning_criteria.py │ │ ├── test_pruning_patterns.py │ │ ├── test_pruning_progressive.py │ │ ├── test_pruning_regs.py │ │ ├── test_pruning_schedulers.py │ │ └── test_pruning_types.py │ └── pruning_2_plus.x │ │ ├── test_pruning.py │ │ ├── test_pruning_block.py │ │ ├── test_pruning_retrain_free.py │ │ ├── test_pruning_sparsegpt.py │ │ └── test_wanda.py ├── pruning_with_tf │ └── pruning_2.x │ │ └── test_pruning_keras.py ├── quantization │ ├── test_tensorflow_qat.py │ └── test_weight_only_quantization.py ├── requirements.txt ├── strategy │ ├── test_basic.py │ ├── test_bayesian.py │ ├── test_distributed_tuning.py │ ├── test_exhaustive.py │ ├── test_hawq_v2_2x.py │ ├── test_lower_bit_sampler.py │ ├── test_mse.py │ ├── test_mse_v2_2x.py │ ├── test_new_datatype.py │ ├── test_quant_level.py │ ├── test_random.py │ ├── test_tpe.py │ ├── test_tuning_sampler.py │ ├── test_tuning_space.py │ ├── test_tuning_space_v2.py │ └── test_utility.py ├── tfnewapi │ ├── test_big_saved_model.py │ └── test_smooth_quant_newapi.py └── utils │ ├── test_cpu_info.py │ ├── test_huggingface.py │ ├── test_layer_histogram.py │ └── test_logger.py └── third-party-programs.txt /.azure-pipelines/code-scan.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/code-scan.yml -------------------------------------------------------------------------------- /.azure-pipelines/docker/Dockerfile.devel: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/docker/Dockerfile.devel -------------------------------------------------------------------------------- /.azure-pipelines/docker/DockerfileCodeScan.devel: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/docker/DockerfileCodeScan.devel -------------------------------------------------------------------------------- /.azure-pipelines/docker/ubuntu-2404.devel: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/docker/ubuntu-2404.devel -------------------------------------------------------------------------------- /.azure-pipelines/model-test-3x.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/model-test-3x.yml -------------------------------------------------------------------------------- /.azure-pipelines/scripts/change_color.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/change_color.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/codeScan/bandit/bandit.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/codeScan/bandit/bandit.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/codeScan/codespell/inc_dict.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/codeScan/codespell/inc_dict.txt -------------------------------------------------------------------------------- /.azure-pipelines/scripts/codeScan/pydocstyle/pydocstyle.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/codeScan/pydocstyle/pydocstyle.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/codeScan/pydocstyle/scan_path.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/codeScan/pydocstyle/scan_path.txt -------------------------------------------------------------------------------- /.azure-pipelines/scripts/fwk_version.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/fwk_version.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/install_nc.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/install_nc.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/models/collect_log_all.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/models/collect_log_all.py -------------------------------------------------------------------------------- /.azure-pipelines/scripts/models/collect_log_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/models/collect_log_model.py -------------------------------------------------------------------------------- /.azure-pipelines/scripts/models/env_setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/models/env_setup.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/models/generate_report.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/models/generate_report.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/models/new_benchmark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/models/new_benchmark.py -------------------------------------------------------------------------------- /.azure-pipelines/scripts/models/run_benchmark_common.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/models/run_benchmark_common.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/models/run_model_trigger_common.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/models/run_model_trigger_common.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/models/run_tuning_common.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/models/run_tuning_common.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/models/update_yaml_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/models/update_yaml_config.py -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/3x/collect_log_3x.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/3x/collect_log_3x.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/3x/coverage.3x_pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/3x/coverage.3x_pt -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/3x/coverage.3x_pt_fp8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/3x/coverage.3x_pt_fp8 -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/3x/coverage.3x_tf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/3x/coverage.3x_tf -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/3x/run_3x_pt.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/3x/run_3x_pt.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/3x/run_3x_pt_fp8.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/3x/run_3x_pt_fp8.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/3x/run_3x_tf.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/3x/run_3x_tf.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/collect_log.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/collect_log.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/compare_coverage.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/compare_coverage.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/coverage.file: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/coverage.file -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/env_setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/env_setup.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/run_basic_adaptor.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/run_basic_adaptor.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/run_basic_adaptor_tfnewapi.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/run_basic_adaptor_tfnewapi.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/run_basic_api.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/run_basic_api.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/run_basic_itex.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/run_basic_itex.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/run_basic_others.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/run_basic_others.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/run_basic_pt_pruning.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/run_basic_pt_pruning.sh -------------------------------------------------------------------------------- /.azure-pipelines/scripts/ut/run_basic_tf_pruning.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/scripts/ut/run_basic_tf_pruning.sh -------------------------------------------------------------------------------- /.azure-pipelines/template/code-scan-template.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/template/code-scan-template.yml -------------------------------------------------------------------------------- /.azure-pipelines/template/docker-template.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/template/docker-template.yml -------------------------------------------------------------------------------- /.azure-pipelines/template/model-template.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/template/model-template.yml -------------------------------------------------------------------------------- /.azure-pipelines/template/ut-template.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/template/ut-template.yml -------------------------------------------------------------------------------- /.azure-pipelines/ut-3x-pt-fp8.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/ut-3x-pt-fp8.yml -------------------------------------------------------------------------------- /.azure-pipelines/ut-3x-pt.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/ut-3x-pt.yml -------------------------------------------------------------------------------- /.azure-pipelines/ut-3x-tf.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/ut-3x-tf.yml -------------------------------------------------------------------------------- /.azure-pipelines/ut-basic.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.azure-pipelines/ut-basic.yml -------------------------------------------------------------------------------- /.github/license_template.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.github/license_template.txt -------------------------------------------------------------------------------- /.github/pull_request_template.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.github/pull_request_template.md -------------------------------------------------------------------------------- /.github/workflows/check-stale-issue.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.github/workflows/check-stale-issue.yml -------------------------------------------------------------------------------- /.github/workflows/pr-agent.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.github/workflows/pr-agent.yml -------------------------------------------------------------------------------- /.github/workflows/pr-code-sync.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.github/workflows/pr-code-sync.yml -------------------------------------------------------------------------------- /.github/workflows/pr-io-build.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.github/workflows/pr-io-build.yaml -------------------------------------------------------------------------------- /.github/workflows/pr-link-scan.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.github/workflows/pr-link-scan.yml -------------------------------------------------------------------------------- /.github/workflows/pr-pre-commit.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.github/workflows/pr-pre-commit.yml -------------------------------------------------------------------------------- /.github/workflows/publish.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.github/workflows/publish.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.gitignore -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /.vscode/settings_recommended.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/.vscode/settings_recommended.json -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/README.md -------------------------------------------------------------------------------- /SECURITY.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/SECURITY.md -------------------------------------------------------------------------------- /docker/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docker/Dockerfile -------------------------------------------------------------------------------- /docker/Dockerfile.devel: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docker/Dockerfile.devel -------------------------------------------------------------------------------- /docker/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docker/README.md -------------------------------------------------------------------------------- /docker/third-party-programs-docker.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docker/third-party-programs-docker.txt -------------------------------------------------------------------------------- /docker/third-party-programs-pytorch.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docker/third-party-programs-pytorch.txt -------------------------------------------------------------------------------- /docker/third-party-programs-tensorflow.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docker/third-party-programs-tensorflow.txt -------------------------------------------------------------------------------- /docs/build_docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/Makefile -------------------------------------------------------------------------------- /docs/build_docs/add_readme.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/add_readme.py -------------------------------------------------------------------------------- /docs/build_docs/build.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/build.sh -------------------------------------------------------------------------------- /docs/build_docs/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/make.bat -------------------------------------------------------------------------------- /docs/build_docs/pip_set_env.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/pip_set_env.sh -------------------------------------------------------------------------------- /docs/build_docs/source/_static/custom.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/source/_static/custom.css -------------------------------------------------------------------------------- /docs/build_docs/source/_static/index.html: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /docs/build_docs/source/_templates/footer.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/source/_templates/footer.html -------------------------------------------------------------------------------- /docs/build_docs/source/_templates/layout.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/source/_templates/layout.html -------------------------------------------------------------------------------- /docs/build_docs/source/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/source/conf.py -------------------------------------------------------------------------------- /docs/build_docs/source/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/source/index.rst -------------------------------------------------------------------------------- /docs/build_docs/sphinx-requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/sphinx-requirements.txt -------------------------------------------------------------------------------- /docs/build_docs/update_html.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/update_html.py -------------------------------------------------------------------------------- /docs/build_docs/update_version.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/build_docs/update_version.py -------------------------------------------------------------------------------- /docs/source/2x_user_guide.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/2x_user_guide.md -------------------------------------------------------------------------------- /docs/source/3x/PT_DynamicQuant.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/PT_DynamicQuant.md -------------------------------------------------------------------------------- /docs/source/3x/PT_FP8Quant.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/PT_FP8Quant.md -------------------------------------------------------------------------------- /docs/source/3x/PT_MXQuant.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/PT_MXQuant.md -------------------------------------------------------------------------------- /docs/source/3x/PT_MixedPrecision.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/PT_MixedPrecision.md -------------------------------------------------------------------------------- /docs/source/3x/PT_SmoothQuant.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/PT_SmoothQuant.md -------------------------------------------------------------------------------- /docs/source/3x/PT_StaticQuant.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/PT_StaticQuant.md -------------------------------------------------------------------------------- /docs/source/3x/PT_WeightOnlyQuant.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/PT_WeightOnlyQuant.md -------------------------------------------------------------------------------- /docs/source/3x/PyTorch.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/PyTorch.md -------------------------------------------------------------------------------- /docs/source/3x/TF_Quant.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/TF_Quant.md -------------------------------------------------------------------------------- /docs/source/3x/TF_SQ.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/TF_SQ.md -------------------------------------------------------------------------------- /docs/source/3x/TensorFlow.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/TensorFlow.md -------------------------------------------------------------------------------- /docs/source/3x/autotune.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/autotune.md -------------------------------------------------------------------------------- /docs/source/3x/client_quant.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/client_quant.md -------------------------------------------------------------------------------- /docs/source/3x/design.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/design.md -------------------------------------------------------------------------------- /docs/source/3x/gaudi_version_map.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/gaudi_version_map.md -------------------------------------------------------------------------------- /docs/source/3x/imgs/architecture.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/imgs/architecture.png -------------------------------------------------------------------------------- /docs/source/3x/imgs/data_format.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/imgs/data_format.png -------------------------------------------------------------------------------- /docs/source/3x/imgs/fp8_dtype.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/imgs/fp8_dtype.png -------------------------------------------------------------------------------- /docs/source/3x/imgs/lwq.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/imgs/lwq.png -------------------------------------------------------------------------------- /docs/source/3x/imgs/mx_workflow.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/imgs/mx_workflow.png -------------------------------------------------------------------------------- /docs/source/3x/imgs/optimum-habana.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/imgs/optimum-habana.png -------------------------------------------------------------------------------- /docs/source/3x/imgs/smoothquant.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/imgs/smoothquant.png -------------------------------------------------------------------------------- /docs/source/3x/imgs/sq_convert.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/imgs/sq_convert.png -------------------------------------------------------------------------------- /docs/source/3x/imgs/sq_pc.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/imgs/sq_pc.png -------------------------------------------------------------------------------- /docs/source/3x/imgs/vllm_gaudi.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/imgs/vllm_gaudi.png -------------------------------------------------------------------------------- /docs/source/3x/imgs/workflow.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/imgs/workflow.png -------------------------------------------------------------------------------- /docs/source/3x/quantization.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/quantization.md -------------------------------------------------------------------------------- /docs/source/3x/transformers_like_api.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/3x/transformers_like_api.md -------------------------------------------------------------------------------- /docs/source/CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /docs/source/CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/CONTRIBUTING.md -------------------------------------------------------------------------------- /docs/source/FX.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/FX.md -------------------------------------------------------------------------------- /docs/source/SECURITY.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/SECURITY.md -------------------------------------------------------------------------------- /docs/source/adaptor.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/adaptor.md -------------------------------------------------------------------------------- /docs/source/add_new_adaptor.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/add_new_adaptor.md -------------------------------------------------------------------------------- /docs/source/add_new_data_type.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/add_new_data_type.md -------------------------------------------------------------------------------- /docs/source/api-doc/adaptor.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/adaptor.rst -------------------------------------------------------------------------------- /docs/source/api-doc/adaptor/onnxrt.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/adaptor/onnxrt.rst -------------------------------------------------------------------------------- /docs/source/api-doc/adaptor/torch_utils.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/adaptor/torch_utils.rst -------------------------------------------------------------------------------- /docs/source/api-doc/api_2.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/api_2.rst -------------------------------------------------------------------------------- /docs/source/api-doc/api_3.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/api_3.rst -------------------------------------------------------------------------------- /docs/source/api-doc/apis.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/apis.rst -------------------------------------------------------------------------------- /docs/source/api-doc/compression.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/compression.rst -------------------------------------------------------------------------------- /docs/source/api-doc/config.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/config.rst -------------------------------------------------------------------------------- /docs/source/api-doc/mix_precision.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/mix_precision.rst -------------------------------------------------------------------------------- /docs/source/api-doc/model.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/model.rst -------------------------------------------------------------------------------- /docs/source/api-doc/objective.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/objective.rst -------------------------------------------------------------------------------- /docs/source/api-doc/quantization.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/quantization.rst -------------------------------------------------------------------------------- /docs/source/api-doc/strategy.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/strategy.rst -------------------------------------------------------------------------------- /docs/source/api-doc/tf_quantization_autotune.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/tf_quantization_autotune.rst -------------------------------------------------------------------------------- /docs/source/api-doc/tf_quantization_common.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/tf_quantization_common.rst -------------------------------------------------------------------------------- /docs/source/api-doc/tf_quantization_config.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/tf_quantization_config.rst -------------------------------------------------------------------------------- /docs/source/api-doc/torch_quantization_autotune.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/torch_quantization_autotune.rst -------------------------------------------------------------------------------- /docs/source/api-doc/torch_quantization_common.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/torch_quantization_common.rst -------------------------------------------------------------------------------- /docs/source/api-doc/torch_quantization_config.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/torch_quantization_config.rst -------------------------------------------------------------------------------- /docs/source/api-doc/training.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/api-doc/training.rst -------------------------------------------------------------------------------- /docs/source/calibration.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/calibration.md -------------------------------------------------------------------------------- /docs/source/coding_style.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/coding_style.md -------------------------------------------------------------------------------- /docs/source/dataloader.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/dataloader.md -------------------------------------------------------------------------------- /docs/source/design.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/design.md -------------------------------------------------------------------------------- /docs/source/distillation.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/distillation.md -------------------------------------------------------------------------------- /docs/source/examples_readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/examples_readme.md -------------------------------------------------------------------------------- /docs/source/faq.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/faq.md -------------------------------------------------------------------------------- /docs/source/framework_yaml.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/framework_yaml.md -------------------------------------------------------------------------------- /docs/source/get_started.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/get_started.md -------------------------------------------------------------------------------- /docs/source/imgs/Conv2D_PyTorch_Cap.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/Conv2D_PyTorch_Cap.png -------------------------------------------------------------------------------- /docs/source/imgs/Distillation_workflow.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/Distillation_workflow.png -------------------------------------------------------------------------------- /docs/source/imgs/accuracy_aware_tuning_flow.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/accuracy_aware_tuning_flow.png -------------------------------------------------------------------------------- /docs/source/imgs/architecture.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/architecture.png -------------------------------------------------------------------------------- /docs/source/imgs/bf16_convert_pt.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/bf16_convert_pt.png -------------------------------------------------------------------------------- /docs/source/imgs/bf16_convert_tf.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/bf16_convert_tf.png -------------------------------------------------------------------------------- /docs/source/imgs/common/code.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/common/code.svg -------------------------------------------------------------------------------- /docs/source/imgs/common/intel.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/common/intel.svg -------------------------------------------------------------------------------- /docs/source/imgs/common/right.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/common/right.svg -------------------------------------------------------------------------------- /docs/source/imgs/data_format.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/data_format.png -------------------------------------------------------------------------------- /docs/source/imgs/distributed_tuning_intro.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/distributed_tuning_intro.png -------------------------------------------------------------------------------- /docs/source/imgs/export.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/export.png -------------------------------------------------------------------------------- /docs/source/imgs/fake_quant.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/fake_quant.png -------------------------------------------------------------------------------- /docs/source/imgs/lwq.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/lwq.png -------------------------------------------------------------------------------- /docs/source/imgs/lwq_ort.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/lwq_ort.png -------------------------------------------------------------------------------- /docs/source/imgs/metric.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/metric.jpg -------------------------------------------------------------------------------- /docs/source/imgs/model.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/model.png -------------------------------------------------------------------------------- /docs/source/imgs/model_scale_accuracy.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/model_scale_accuracy.png -------------------------------------------------------------------------------- /docs/source/imgs/mx_workflow.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/mx_workflow.png -------------------------------------------------------------------------------- /docs/source/imgs/pruning/2in4_sparsity_demo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/pruning/2in4_sparsity_demo.png -------------------------------------------------------------------------------- /docs/source/imgs/pruning/Pruning_schedule.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/pruning/Pruning_schedule.jpg -------------------------------------------------------------------------------- /docs/source/imgs/pruning/Regularization.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/pruning/Regularization.jpg -------------------------------------------------------------------------------- /docs/source/imgs/pruning/progressive_pruning.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/pruning/progressive_pruning.png -------------------------------------------------------------------------------- /docs/source/imgs/pruning/pruning.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/pruning/pruning.png -------------------------------------------------------------------------------- /docs/source/imgs/pruning/pruning_criteria.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/pruning/pruning_criteria.png -------------------------------------------------------------------------------- /docs/source/imgs/pruning/pruning_intro.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/pruning/pruning_intro.png -------------------------------------------------------------------------------- /docs/source/imgs/pruning/pruning_patterns.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/pruning/pruning_patterns.jpg -------------------------------------------------------------------------------- /docs/source/imgs/pruning/pruning_scatter.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/pruning/pruning_scatter.png -------------------------------------------------------------------------------- /docs/source/imgs/pruning/sparse_dim.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/pruning/sparse_dim.png -------------------------------------------------------------------------------- /docs/source/imgs/pruning/sparsity_decay_type.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/pruning/sparsity_decay_type.png -------------------------------------------------------------------------------- /docs/source/imgs/pruning/train_for_sparsity.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/pruning/train_for_sparsity.png -------------------------------------------------------------------------------- /docs/source/imgs/self-distillation.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/self-distillation.png -------------------------------------------------------------------------------- /docs/source/imgs/smoothquant.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/smoothquant.png -------------------------------------------------------------------------------- /docs/source/imgs/sq_convert.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/sq_convert.png -------------------------------------------------------------------------------- /docs/source/imgs/sq_pc.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/sq_pc.png -------------------------------------------------------------------------------- /docs/source/imgs/strategy.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/strategy.png -------------------------------------------------------------------------------- /docs/source/imgs/wechat_group.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/wechat_group.jpg -------------------------------------------------------------------------------- /docs/source/imgs/workflow.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/imgs/workflow.png -------------------------------------------------------------------------------- /docs/source/infrastructure.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/infrastructure.md -------------------------------------------------------------------------------- /docs/source/installation_guide.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/installation_guide.md -------------------------------------------------------------------------------- /docs/source/legal_information.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/legal_information.md -------------------------------------------------------------------------------- /docs/source/llm_recipes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/llm_recipes.md -------------------------------------------------------------------------------- /docs/source/metric.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/metric.md -------------------------------------------------------------------------------- /docs/source/mixed_precision.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/mixed_precision.md -------------------------------------------------------------------------------- /docs/source/model.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/model.md -------------------------------------------------------------------------------- /docs/source/mx_quantization.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/mx_quantization.md -------------------------------------------------------------------------------- /docs/source/objective.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/objective.md -------------------------------------------------------------------------------- /docs/source/orchestration.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/orchestration.md -------------------------------------------------------------------------------- /docs/source/pruning.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/pruning.md -------------------------------------------------------------------------------- /docs/source/publication_list.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/publication_list.md -------------------------------------------------------------------------------- /docs/source/quantization.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/quantization.md -------------------------------------------------------------------------------- /docs/source/quantization_layer_wise.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/quantization_layer_wise.md -------------------------------------------------------------------------------- /docs/source/quantization_mixed_precision.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/quantization_mixed_precision.md -------------------------------------------------------------------------------- /docs/source/quantization_weight_only.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/quantization_weight_only.md -------------------------------------------------------------------------------- /docs/source/smooth_quant.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/smooth_quant.md -------------------------------------------------------------------------------- /docs/source/tuning_strategies.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/tuning_strategies.md -------------------------------------------------------------------------------- /docs/source/validated_model_list.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/docs/source/validated_model_list.md -------------------------------------------------------------------------------- /examples/.config/model_params_keras.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/.config/model_params_keras.json -------------------------------------------------------------------------------- /examples/.config/model_params_keras_3x.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/.config/model_params_keras_3x.json -------------------------------------------------------------------------------- /examples/.config/model_params_onnxrt.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/.config/model_params_onnxrt.json -------------------------------------------------------------------------------- /examples/.config/model_params_onnxrt_win.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/.config/model_params_onnxrt_win.json -------------------------------------------------------------------------------- /examples/.config/model_params_pt2onnx.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/.config/model_params_pt2onnx.json -------------------------------------------------------------------------------- /examples/.config/model_params_pytorch.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/.config/model_params_pytorch.json -------------------------------------------------------------------------------- /examples/.config/model_params_pytorch_3x.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/.config/model_params_pytorch_3x.json -------------------------------------------------------------------------------- /examples/.config/model_params_pytorch_win.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/.config/model_params_pytorch_win.json -------------------------------------------------------------------------------- /examples/.config/model_params_tensorflow.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/.config/model_params_tensorflow.json -------------------------------------------------------------------------------- /examples/.config/model_params_tensorflow_3x.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/.config/model_params_tensorflow_3x.json -------------------------------------------------------------------------------- /examples/.config/model_params_tensorflow_win.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/.config/model_params_tensorflow_win.json -------------------------------------------------------------------------------- /examples/.config/model_params_tf2onnx.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/.config/model_params_tf2onnx.json -------------------------------------------------------------------------------- /examples/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/README.md -------------------------------------------------------------------------------- /examples/deprecated/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/README.md -------------------------------------------------------------------------------- /examples/deprecated/helloworld/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/README.md -------------------------------------------------------------------------------- /examples/deprecated/helloworld/fp8_example/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/fp8_example/README.md -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example1/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example1/README.md -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example1/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | protobuf!=4.24.0 -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example1/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example1/test.py -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example2/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example2/README.md -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example2/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example2/requirements.txt -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example2/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example2/test.py -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example3/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example3/README.md -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example3/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | protobuf!=4.24.0 -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example3/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example3/test.py -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example4/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example4/README.md -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example4/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example4/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example4/test.py -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example5/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example5/README.md -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example5/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | protobuf!=4.24.0 -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example5/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example5/test.py -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example6/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example6/README.md -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example6/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | protobuf!=4.24.0 -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example6/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example6/test.py -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example7/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example7/README.md -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example7/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | protobuf!=4.24.0 -------------------------------------------------------------------------------- /examples/deprecated/helloworld/tf_example7/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/tf_example7/test.py -------------------------------------------------------------------------------- /examples/deprecated/helloworld/torch_static_quant/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/torch_static_quant/README.md -------------------------------------------------------------------------------- /examples/deprecated/helloworld/torch_woq/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/torch_woq/README.md -------------------------------------------------------------------------------- /examples/deprecated/helloworld/torch_woq/quant_mistral.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/torch_woq/quant_mistral.py -------------------------------------------------------------------------------- /examples/deprecated/helloworld/torch_woq/requirements.txt: -------------------------------------------------------------------------------- 1 | neural-compressor>=2.3 2 | torch 3 | transformers>=4.34.0 -------------------------------------------------------------------------------- /examples/deprecated/helloworld/torch_woq_autoround/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/torch_woq_autoround/test.py -------------------------------------------------------------------------------- /examples/deprecated/helloworld/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/helloworld/train.py -------------------------------------------------------------------------------- /examples/deprecated/notebook/onnxruntime/benchmark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/notebook/onnxruntime/benchmark.py -------------------------------------------------------------------------------- /examples/deprecated/notebook/onnxruntime/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/notebook/onnxruntime/requirements.txt -------------------------------------------------------------------------------- /examples/deprecated/notebook/perf_fp32_int8_tf/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/notebook/perf_fp32_int8_tf/README.md -------------------------------------------------------------------------------- /examples/deprecated/notebook/perf_fp32_int8_tf/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/notebook/perf_fp32_int8_tf/run.sh -------------------------------------------------------------------------------- /examples/deprecated/notebook/perf_fp32_int8_tf/set_env.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/notebook/perf_fp32_int8_tf/set_env.sh -------------------------------------------------------------------------------- /examples/deprecated/notebook/pytorch/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/notebook/pytorch/requirements.txt -------------------------------------------------------------------------------- /examples/deprecated/notebook/tensorflow/resnet/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/deprecated/notebook/tensorflow/resnet/README.md -------------------------------------------------------------------------------- /examples/deprecated/pytorch/image_recognition/3d-unet/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /examples/deprecated/pytorch/image_recognition/3d-unet/quantization/ptq/fx/.dockerignore: -------------------------------------------------------------------------------- 1 | build/ 2 | -------------------------------------------------------------------------------- /examples/deprecated/pytorch/image_recognition/3d-unet/quantization/ptq/fx/.gitignore: -------------------------------------------------------------------------------- 1 | build/ 2 | -------------------------------------------------------------------------------- /examples/deprecated/pytorch/image_recognition/segment_anything/requirements.txt: -------------------------------------------------------------------------------- 1 | torchvision 2 | tdqm 3 | torchmetrics 4 | neural-compressor -------------------------------------------------------------------------------- /examples/deprecated/pytorch/object_detection/yolo_v3/quantization/ptq_static/fx/data/custom/classes.names: -------------------------------------------------------------------------------- 1 | train 2 | -------------------------------------------------------------------------------- /examples/deprecated/pytorch/object_detection/yolo_v3/quantization/ptq_static/fx/data/custom/train.txt: -------------------------------------------------------------------------------- 1 | data/custom/images/train.jpg 2 | -------------------------------------------------------------------------------- /examples/deprecated/pytorch/object_detection/yolo_v3/quantization/ptq_static/fx/data/custom/valid.txt: -------------------------------------------------------------------------------- 1 | data/custom/images/train.jpg 2 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/graph_networks/graphsage/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | networkx 2 | scikit-learn -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/densenet121/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/densenet161/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/densenet169/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/distillation/requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow<=2.15.0 -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/efficientnet-b0/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/inception_resnet_v2/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/inception_v1/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/inception_v2/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/inception_v3/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/inception_v4/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/mobilenet_v1/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/mobilenet_v2/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/mobilenet_v3/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/resnet101/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/resnet50_v1/mixed_precision/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/resnet50_v1/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/resnet50_v1_5/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/resnet_v2_101/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/resnet_v2_152/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/resnet_v2_50/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/vgg16/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/vgg19/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/image_recognition/tensorflow_models/vision_transformer/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow==2.11.0 2 | neural-compressor -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/nlp/bert_base_mrpc/quantization/ptq/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/nlp/bert_large_squad_model_zoo/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/nlp/large_language_models/quantization/ptq/gpt-j/requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow==2.12.1 2 | transformers 3 | datasets 4 | numpy -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/nlp/large_language_models/quantization/ptq/smoothquant/requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow 2 | datasets 3 | transformers -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/nlp/transformer_lt/quantization/ptq/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/nlp/transformer_lt_mlperf/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/nlp/transformer_lt_mlperf/quantization/ptq/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/object_detection/tensorflow_models/ssd_resnet34/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/semantic_image_segmentation/3dunet-mlperf/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | nnunet 2 | -------------------------------------------------------------------------------- /examples/deprecated/tensorflow/style_transfer/arbitrary_style_transfer/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | scikit-image 2 | Pillow>=8.2.0 3 | -------------------------------------------------------------------------------- /examples/pytorch/cv/fp8_quant/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/fp8_quant/README.md -------------------------------------------------------------------------------- /examples/pytorch/cv/fp8_quant/extract_ILSVRC.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/fp8_quant/extract_ILSVRC.sh -------------------------------------------------------------------------------- /examples/pytorch/cv/fp8_quant/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/fp8_quant/main.py -------------------------------------------------------------------------------- /examples/pytorch/cv/fp8_quant/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/fp8_quant/requirements.txt -------------------------------------------------------------------------------- /examples/pytorch/cv/fp8_quant/run_quant.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/fp8_quant/run_quant.sh -------------------------------------------------------------------------------- /examples/pytorch/cv/mixed_precision/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/mixed_precision/README.md -------------------------------------------------------------------------------- /examples/pytorch/cv/mixed_precision/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/mixed_precision/main.py -------------------------------------------------------------------------------- /examples/pytorch/cv/mixed_precision/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/mixed_precision/requirements.txt -------------------------------------------------------------------------------- /examples/pytorch/cv/mixed_precision/run_autotune.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/mixed_precision/run_autotune.sh -------------------------------------------------------------------------------- /examples/pytorch/cv/mixed_precision/run_benchmark.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/mixed_precision/run_benchmark.sh -------------------------------------------------------------------------------- /examples/pytorch/cv/static_quant/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/static_quant/README.md -------------------------------------------------------------------------------- /examples/pytorch/cv/static_quant/extract_ILSVRC.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/static_quant/extract_ILSVRC.sh -------------------------------------------------------------------------------- /examples/pytorch/cv/static_quant/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/static_quant/main.py -------------------------------------------------------------------------------- /examples/pytorch/cv/static_quant/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/static_quant/requirements.txt -------------------------------------------------------------------------------- /examples/pytorch/cv/static_quant/run_benchmark.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/static_quant/run_benchmark.sh -------------------------------------------------------------------------------- /examples/pytorch/cv/static_quant/run_quant.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/cv/static_quant/run_quant.sh -------------------------------------------------------------------------------- /examples/pytorch/diffusion_model/diffusers/flux/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/diffusion_model/diffusers/flux/README.md -------------------------------------------------------------------------------- /examples/pytorch/diffusion_model/diffusers/flux/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/pytorch/diffusion_model/diffusers/flux/main.py -------------------------------------------------------------------------------- /examples/pytorch/multimodal-modeling/quantization/auto_round/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /examples/pytorch/recommendation/dlrm_v2/fp8_quant/cpu/data_process/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /examples/tensorflow/graph_networks/graphsage/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | networkx 2 | scikit-learn -------------------------------------------------------------------------------- /examples/tensorflow/image_recognition/inception_v3/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/tensorflow/image_recognition/mobilenet_v2/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/tensorflow/image_recognition/prepare_dataset.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/tensorflow/image_recognition/prepare_dataset.sh -------------------------------------------------------------------------------- /examples/tensorflow/image_recognition/resnet_v2_50/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/tensorflow/image_recognition/vgg16/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow 2 | neural-compressor 3 | -------------------------------------------------------------------------------- /examples/tensorflow/image_recognition/vision_transformer/quantization/ptq/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /examples/tensorflow/image_recognition/vision_transformer/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow 2 | neural-compressor -------------------------------------------------------------------------------- /examples/tensorflow/nlp/bert_large_squad_model_zoo/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | intel-tensorflow>=2.12.0 -------------------------------------------------------------------------------- /examples/tensorflow/nlp/large_language_models/quantization/ptq/smoothquant/requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow==2.15 2 | datasets 3 | transformers==4.53.0 -------------------------------------------------------------------------------- /examples/tensorflow/nlp/transformer_lt/quantization/ptq/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /examples/tensorflow/object_detection/prepare_dataset.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/tensorflow/object_detection/prepare_dataset.sh -------------------------------------------------------------------------------- /examples/tensorflow/object_detection/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/examples/tensorflow/object_detection/requirements.txt -------------------------------------------------------------------------------- /examples/tensorflow/object_detection/yolo_v5/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | yolov5 2 | -------------------------------------------------------------------------------- /examples/tensorflow/semantic_image_segmentation/3dunet-mlperf/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | nnunet 2 | tensorflow -------------------------------------------------------------------------------- /examples/tensorflow/style_transfer/arbitrary_style_transfer/quantization/ptq/requirements.txt: -------------------------------------------------------------------------------- 1 | scikit-image 2 | Pillow>=8.2.0 3 | -------------------------------------------------------------------------------- /neural_compressor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/__init__.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/__init__.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/adaptor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/adaptor.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/keras.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/keras.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/keras.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/keras.yaml -------------------------------------------------------------------------------- /neural_compressor/adaptor/keras_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/keras_utils/__init__.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/keras_utils/conv2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/keras_utils/conv2d.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/keras_utils/dense.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/keras_utils/dense.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/keras_utils/depthwise_conv2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/keras_utils/depthwise_conv2d.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/keras_utils/pool2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/keras_utils/pool2d.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/keras_utils/quantizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/keras_utils/quantizer.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/keras_utils/separable_conv2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/keras_utils/separable_conv2d.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/onnxrt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/onnxrt.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/onnxrt.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/onnxrt.yaml -------------------------------------------------------------------------------- /neural_compressor/adaptor/onnxrt_cuda.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/onnxrt_cuda.yaml -------------------------------------------------------------------------------- /neural_compressor/adaptor/onnxrt_dml.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/onnxrt_dml.yaml -------------------------------------------------------------------------------- /neural_compressor/adaptor/onnxrt_dnnl.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/onnxrt_dnnl.yaml -------------------------------------------------------------------------------- /neural_compressor/adaptor/onnxrt_trt.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/onnxrt_trt.yaml -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/__init__.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/calibration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/calibration.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/calibrator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/calibrator.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/__init__.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/argmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/argmax.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/attention.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/binary_op.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/binary_op.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/concat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/concat.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/conv.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/direct_q8.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/direct_q8.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/gather.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/gather.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/gavgpool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/gavgpool.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/gemm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/gemm.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/lstm.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/matmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/matmul.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/maxpool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/maxpool.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/norm.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/ops.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/pad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/pad.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/pooling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/pooling.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/reduce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/reduce.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/resize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/resize.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/split.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/split.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/operators/unary_op.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/operators/unary_op.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/quantizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/quantizer.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/smooth_quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/smooth_quant.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/util.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/ox_utils/weight_only.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/ox_utils/weight_only.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/pytorch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/pytorch.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/pytorch_cpu.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/pytorch_cpu.yaml -------------------------------------------------------------------------------- /neural_compressor/adaptor/pytorch_gpu.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/pytorch_gpu.yaml -------------------------------------------------------------------------------- /neural_compressor/adaptor/pytorch_ipex.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/pytorch_ipex.yaml -------------------------------------------------------------------------------- /neural_compressor/adaptor/query.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/query.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/tensorflow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/tensorflow.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/tensorflow.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/tensorflow.yaml -------------------------------------------------------------------------------- /neural_compressor/adaptor/tensorflow_itex.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/tensorflow_itex.yaml -------------------------------------------------------------------------------- /neural_compressor/adaptor/tf_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/tf_utils/__init__.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/tf_utils/graph_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/tf_utils/graph_converter.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/tf_utils/graph_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/tf_utils/graph_util.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/tf_utils/smooth_quant_scaler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/tf_utils/smooth_quant_scaler.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/tf_utils/tf2onnx_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/tf_utils/tf2onnx_converter.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/tf_utils/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/tf_utils/util.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/__init__.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/auto_round.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/auto_round.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/awq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/awq.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/bf16_convert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/bf16_convert.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/gptq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/gptq.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/hawq_metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/hawq_metric.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/mixed_precision.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/mixed_precision.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/model_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/model_wrapper.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/pattern_detector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/pattern_detector.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/symbolic_trace.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/symbolic_trace.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/teq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/teq.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/util.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/waq/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/waq/README.md -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/waq/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/waq/__init__.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/waq/auto_alpha.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/waq/auto_alpha.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/waq/calibration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/waq/calibration.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/waq/graph_trace.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/waq/graph_trace.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/waq/smooth_quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/waq/smooth_quant.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/waq/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/waq/utils.py -------------------------------------------------------------------------------- /neural_compressor/adaptor/torch_utils/weight_only.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/adaptor/torch_utils/weight_only.py -------------------------------------------------------------------------------- /neural_compressor/algorithm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/algorithm/__init__.py -------------------------------------------------------------------------------- /neural_compressor/algorithm/algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/algorithm/algorithm.py -------------------------------------------------------------------------------- /neural_compressor/algorithm/fast_bias_correction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/algorithm/fast_bias_correction.py -------------------------------------------------------------------------------- /neural_compressor/algorithm/smooth_quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/algorithm/smooth_quant.py -------------------------------------------------------------------------------- /neural_compressor/algorithm/weight_correction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/algorithm/weight_correction.py -------------------------------------------------------------------------------- /neural_compressor/common/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/common/__init__.py -------------------------------------------------------------------------------- /neural_compressor/common/base_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/common/base_config.py -------------------------------------------------------------------------------- /neural_compressor/common/base_tuning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/common/base_tuning.py -------------------------------------------------------------------------------- /neural_compressor/common/tuning_param.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/common/tuning_param.py -------------------------------------------------------------------------------- /neural_compressor/common/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/common/utils/__init__.py -------------------------------------------------------------------------------- /neural_compressor/common/utils/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/common/utils/constants.py -------------------------------------------------------------------------------- /neural_compressor/common/utils/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/common/utils/logger.py -------------------------------------------------------------------------------- /neural_compressor/common/utils/save_load.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/common/utils/save_load.py -------------------------------------------------------------------------------- /neural_compressor/common/utils/utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/common/utils/utility.py -------------------------------------------------------------------------------- /neural_compressor/common/version.py: -------------------------------------------------------------------------------- 1 | ../version.py -------------------------------------------------------------------------------- /neural_compressor/compression/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/__init__.py -------------------------------------------------------------------------------- /neural_compressor/compression/callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/callbacks.py -------------------------------------------------------------------------------- /neural_compressor/compression/distillation/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/distillation/__init__.py -------------------------------------------------------------------------------- /neural_compressor/compression/distillation/criterions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/distillation/criterions.py -------------------------------------------------------------------------------- /neural_compressor/compression/distillation/optimizers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/distillation/optimizers.py -------------------------------------------------------------------------------- /neural_compressor/compression/distillation/utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/distillation/utility.py -------------------------------------------------------------------------------- /neural_compressor/compression/hpo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/hpo/__init__.py -------------------------------------------------------------------------------- /neural_compressor/compression/hpo/sa_optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/hpo/sa_optimizer.py -------------------------------------------------------------------------------- /neural_compressor/compression/hpo/search_algorithms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/hpo/search_algorithms.py -------------------------------------------------------------------------------- /neural_compressor/compression/hpo/search_space.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/hpo/search_space.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/README.md -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/__init__.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/criteria.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/criteria.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/dsnot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/dsnot.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/model_slim/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/model_slim/README.md -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/patterns/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/patterns/__init__.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/patterns/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/patterns/base.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/patterns/mha.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/patterns/mha.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/patterns/ninm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/patterns/ninm.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/patterns/nxm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/patterns/nxm.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/pruners/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/pruners/__init__.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/pruners/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/pruners/base.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/pruners/basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/pruners/basic.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/pruners/mha.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/pruners/mha.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/pruning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/pruning.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/regs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/regs.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/schedulers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/schedulers.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/tf_criteria.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/tf_criteria.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/utils.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/wanda/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/wanda/__init__.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/wanda/prune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/wanda/prune.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/wanda/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/wanda/utils.py -------------------------------------------------------------------------------- /neural_compressor/compression/pruner/wanda/wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/compression/pruner/wanda/wrapper.py -------------------------------------------------------------------------------- /neural_compressor/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/config.py -------------------------------------------------------------------------------- /neural_compressor/contrib/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/contrib/__init__.py -------------------------------------------------------------------------------- /neural_compressor/contrib/strategy/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/contrib/strategy/__init__.py -------------------------------------------------------------------------------- /neural_compressor/contrib/strategy/tpe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/contrib/strategy/tpe.py -------------------------------------------------------------------------------- /neural_compressor/data/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/__init__.py -------------------------------------------------------------------------------- /neural_compressor/data/dataloaders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/dataloaders/__init__.py -------------------------------------------------------------------------------- /neural_compressor/data/dataloaders/base_dataloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/dataloaders/base_dataloader.py -------------------------------------------------------------------------------- /neural_compressor/data/dataloaders/dataloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/dataloaders/dataloader.py -------------------------------------------------------------------------------- /neural_compressor/data/dataloaders/default_dataloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/dataloaders/default_dataloader.py -------------------------------------------------------------------------------- /neural_compressor/data/dataloaders/fetcher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/dataloaders/fetcher.py -------------------------------------------------------------------------------- /neural_compressor/data/dataloaders/onnxrt_dataloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/dataloaders/onnxrt_dataloader.py -------------------------------------------------------------------------------- /neural_compressor/data/dataloaders/pytorch_dataloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/dataloaders/pytorch_dataloader.py -------------------------------------------------------------------------------- /neural_compressor/data/dataloaders/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/dataloaders/sampler.py -------------------------------------------------------------------------------- /neural_compressor/data/datasets/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/datasets/__init__.py -------------------------------------------------------------------------------- /neural_compressor/data/datasets/bert_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/datasets/bert_dataset.py -------------------------------------------------------------------------------- /neural_compressor/data/datasets/coco_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/datasets/coco_dataset.py -------------------------------------------------------------------------------- /neural_compressor/data/datasets/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/datasets/dataset.py -------------------------------------------------------------------------------- /neural_compressor/data/datasets/dummy_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/datasets/dummy_dataset.py -------------------------------------------------------------------------------- /neural_compressor/data/datasets/dummy_dataset_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/datasets/dummy_dataset_v2.py -------------------------------------------------------------------------------- /neural_compressor/data/datasets/imagenet_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/datasets/imagenet_dataset.py -------------------------------------------------------------------------------- /neural_compressor/data/datasets/style_transfer_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/datasets/style_transfer_dataset.py -------------------------------------------------------------------------------- /neural_compressor/data/filters/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/filters/__init__.py -------------------------------------------------------------------------------- /neural_compressor/data/filters/coco_filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/filters/coco_filter.py -------------------------------------------------------------------------------- /neural_compressor/data/filters/filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/filters/filter.py -------------------------------------------------------------------------------- /neural_compressor/data/transforms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/transforms/__init__.py -------------------------------------------------------------------------------- /neural_compressor/data/transforms/coco_transform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/transforms/coco_transform.py -------------------------------------------------------------------------------- /neural_compressor/data/transforms/imagenet_transform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/transforms/imagenet_transform.py -------------------------------------------------------------------------------- /neural_compressor/data/transforms/postprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/transforms/postprocess.py -------------------------------------------------------------------------------- /neural_compressor/data/transforms/tokenization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/transforms/tokenization.py -------------------------------------------------------------------------------- /neural_compressor/data/transforms/transform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/data/transforms/transform.py -------------------------------------------------------------------------------- /neural_compressor/evaluation/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/evaluation/__init__.py -------------------------------------------------------------------------------- /neural_compressor/evaluation/bigcode_eval/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/evaluation/bigcode_eval/__init__.py -------------------------------------------------------------------------------- /neural_compressor/evaluation/bigcode_eval/evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/evaluation/bigcode_eval/evaluator.py -------------------------------------------------------------------------------- /neural_compressor/evaluation/hf_eval/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/evaluation/hf_eval/__init__.py -------------------------------------------------------------------------------- /neural_compressor/evaluation/hf_eval/evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/evaluation/hf_eval/evaluator.py -------------------------------------------------------------------------------- /neural_compressor/evaluation/lm_eval/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/evaluation/lm_eval/__init__.py -------------------------------------------------------------------------------- /neural_compressor/evaluation/lm_eval/accuracy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/evaluation/lm_eval/accuracy.py -------------------------------------------------------------------------------- /neural_compressor/evaluation/lm_eval/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/evaluation/lm_eval/models/__init__.py -------------------------------------------------------------------------------- /neural_compressor/evaluation/lm_eval/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/evaluation/lm_eval/utils.py -------------------------------------------------------------------------------- /neural_compressor/metric/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/metric/__init__.py -------------------------------------------------------------------------------- /neural_compressor/metric/bleu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/metric/bleu.py -------------------------------------------------------------------------------- /neural_compressor/metric/bleu_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/metric/bleu_util.py -------------------------------------------------------------------------------- /neural_compressor/metric/coco_label_map.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/metric/coco_label_map.py -------------------------------------------------------------------------------- /neural_compressor/metric/coco_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/metric/coco_tools.py -------------------------------------------------------------------------------- /neural_compressor/metric/evaluate_squad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/metric/evaluate_squad.py -------------------------------------------------------------------------------- /neural_compressor/metric/f1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/metric/f1.py -------------------------------------------------------------------------------- /neural_compressor/metric/metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/metric/metric.py -------------------------------------------------------------------------------- /neural_compressor/mix_precision.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/mix_precision.py -------------------------------------------------------------------------------- /neural_compressor/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/model/__init__.py -------------------------------------------------------------------------------- /neural_compressor/model/base_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/model/base_model.py -------------------------------------------------------------------------------- /neural_compressor/model/keras_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/model/keras_model.py -------------------------------------------------------------------------------- /neural_compressor/model/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/model/model.py -------------------------------------------------------------------------------- /neural_compressor/model/nets_factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/model/nets_factory.py -------------------------------------------------------------------------------- /neural_compressor/model/onnx_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/model/onnx_model.py -------------------------------------------------------------------------------- /neural_compressor/model/tensorflow_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/model/tensorflow_model.py -------------------------------------------------------------------------------- /neural_compressor/model/torch_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/model/torch_model.py -------------------------------------------------------------------------------- /neural_compressor/objective.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/objective.py -------------------------------------------------------------------------------- /neural_compressor/profiling/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/profiling/__init__.py -------------------------------------------------------------------------------- /neural_compressor/profiling/parser/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/profiling/parser/__init__.py -------------------------------------------------------------------------------- /neural_compressor/profiling/parser/factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/profiling/parser/factory.py -------------------------------------------------------------------------------- /neural_compressor/profiling/parser/onnx_parser/factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/profiling/parser/onnx_parser/factory.py -------------------------------------------------------------------------------- /neural_compressor/profiling/parser/onnx_parser/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/profiling/parser/onnx_parser/parser.py -------------------------------------------------------------------------------- /neural_compressor/profiling/parser/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/profiling/parser/parser.py -------------------------------------------------------------------------------- /neural_compressor/profiling/parser/result.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/profiling/parser/result.py -------------------------------------------------------------------------------- /neural_compressor/profiling/profiler/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/profiling/profiler/__init__.py -------------------------------------------------------------------------------- /neural_compressor/profiling/profiler/factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/profiling/profiler/factory.py -------------------------------------------------------------------------------- /neural_compressor/profiling/profiler/profiler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/profiling/profiler/profiler.py -------------------------------------------------------------------------------- /neural_compressor/quantization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/quantization.py -------------------------------------------------------------------------------- /neural_compressor/strategy/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/__init__.py -------------------------------------------------------------------------------- /neural_compressor/strategy/auto.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/auto.py -------------------------------------------------------------------------------- /neural_compressor/strategy/auto_mixed_precision.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/auto_mixed_precision.py -------------------------------------------------------------------------------- /neural_compressor/strategy/basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/basic.py -------------------------------------------------------------------------------- /neural_compressor/strategy/bayesian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/bayesian.py -------------------------------------------------------------------------------- /neural_compressor/strategy/conservative.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/conservative.py -------------------------------------------------------------------------------- /neural_compressor/strategy/exhaustive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/exhaustive.py -------------------------------------------------------------------------------- /neural_compressor/strategy/hawq_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/hawq_v2.py -------------------------------------------------------------------------------- /neural_compressor/strategy/mse.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/mse.py -------------------------------------------------------------------------------- /neural_compressor/strategy/mse_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/mse_v2.py -------------------------------------------------------------------------------- /neural_compressor/strategy/random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/random.py -------------------------------------------------------------------------------- /neural_compressor/strategy/strategy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/strategy.py -------------------------------------------------------------------------------- /neural_compressor/strategy/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/utils/__init__.py -------------------------------------------------------------------------------- /neural_compressor/strategy/utils/constant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/utils/constant.py -------------------------------------------------------------------------------- /neural_compressor/strategy/utils/tuning_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/utils/tuning_sampler.py -------------------------------------------------------------------------------- /neural_compressor/strategy/utils/tuning_space.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/utils/tuning_space.py -------------------------------------------------------------------------------- /neural_compressor/strategy/utils/tuning_structs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/utils/tuning_structs.py -------------------------------------------------------------------------------- /neural_compressor/strategy/utils/utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/strategy/utils/utility.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/__init__.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/algorithms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/algorithms/__init__.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/algorithms/smoother/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/algorithms/smoother/core.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/keras/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/keras/__init__.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/keras/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/keras/layers/__init__.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/keras/layers/conv2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/keras/layers/conv2d.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/keras/layers/dense.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/keras/layers/dense.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/keras/layers/pool2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/keras/layers/pool2d.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/keras/quantization/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/keras/quantization/config.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/quantization/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/quantization/__init__.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/quantization/autotune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/quantization/autotune.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/quantization/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/quantization/config.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/quantization/quantize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/quantization/quantize.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/utils/__init__.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/utils/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/utils/constants.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/utils/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/utils/data.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/utils/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/utils/model.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/utils/model_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/utils/model_wrappers.py -------------------------------------------------------------------------------- /neural_compressor/tensorflow/utils/utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/tensorflow/utils/utility.py -------------------------------------------------------------------------------- /neural_compressor/torch/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/__init__.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/__init__.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/base_algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/base_algorithm.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/fp8_quant/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/fp8_quant/__init__.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/fp8_quant/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/fp8_quant/common.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/fp8_quant/observer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/fp8_quant/observer.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/fp8_quant/quantizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/fp8_quant/quantizer.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/fp8_quant/save_load.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/fp8_quant/save_load.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/layer_wise/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/layer_wise/__init__.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/layer_wise/load.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/layer_wise/load.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/layer_wise/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/layer_wise/utils.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/mx_quant/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/mx_quant/__init__.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/mx_quant/mx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/mx_quant/mx.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/mx_quant/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/mx_quant/utils.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/pt2e_quant/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/pt2e_quant/__init__.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/pt2e_quant/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/pt2e_quant/core.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/pt2e_quant/utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/pt2e_quant/utility.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/qat/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/qat/__init__.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/qat/quant_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/qat/quant_linear.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/qat/quant_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/qat/quant_utils.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/weight_only/awq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/weight_only/awq.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/weight_only/gptq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/weight_only/gptq.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/weight_only/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/weight_only/modules.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/weight_only/rtn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/weight_only/rtn.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/weight_only/teq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/weight_only/teq.py -------------------------------------------------------------------------------- /neural_compressor/torch/algorithms/weight_only/utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/algorithms/weight_only/utility.py -------------------------------------------------------------------------------- /neural_compressor/torch/export/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/export/__init__.py -------------------------------------------------------------------------------- /neural_compressor/torch/export/export_hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/export/export_hf.py -------------------------------------------------------------------------------- /neural_compressor/torch/export/pt2e_export.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/export/pt2e_export.py -------------------------------------------------------------------------------- /neural_compressor/torch/quantization/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/quantization/__init__.py -------------------------------------------------------------------------------- /neural_compressor/torch/quantization/algorithm_entry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/quantization/algorithm_entry.py -------------------------------------------------------------------------------- /neural_compressor/torch/quantization/autotune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/quantization/autotune.py -------------------------------------------------------------------------------- /neural_compressor/torch/quantization/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/quantization/config.py -------------------------------------------------------------------------------- /neural_compressor/torch/quantization/quantize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/quantization/quantize.py -------------------------------------------------------------------------------- /neural_compressor/torch/quantization/save_load_entry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/quantization/save_load_entry.py -------------------------------------------------------------------------------- /neural_compressor/torch/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/utils/__init__.py -------------------------------------------------------------------------------- /neural_compressor/torch/utils/auto_accelerator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/utils/auto_accelerator.py -------------------------------------------------------------------------------- /neural_compressor/torch/utils/bit_packer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/utils/bit_packer.py -------------------------------------------------------------------------------- /neural_compressor/torch/utils/block_wise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/utils/block_wise.py -------------------------------------------------------------------------------- /neural_compressor/torch/utils/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/utils/constants.py -------------------------------------------------------------------------------- /neural_compressor/torch/utils/environ.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/utils/environ.py -------------------------------------------------------------------------------- /neural_compressor/torch/utils/llm_utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/utils/llm_utility.py -------------------------------------------------------------------------------- /neural_compressor/torch/utils/utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/torch/utils/utility.py -------------------------------------------------------------------------------- /neural_compressor/training.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/training.py -------------------------------------------------------------------------------- /neural_compressor/transformers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/transformers/__init__.py -------------------------------------------------------------------------------- /neural_compressor/transformers/generation/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/transformers/generation/__init__.py -------------------------------------------------------------------------------- /neural_compressor/transformers/generation/beam_search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/transformers/generation/beam_search.py -------------------------------------------------------------------------------- /neural_compressor/transformers/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/transformers/models/__init__.py -------------------------------------------------------------------------------- /neural_compressor/transformers/models/modeling_auto.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/transformers/models/modeling_auto.py -------------------------------------------------------------------------------- /neural_compressor/transformers/quantization/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/transformers/quantization/__init__.py -------------------------------------------------------------------------------- /neural_compressor/transformers/quantization/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/transformers/quantization/utils.py -------------------------------------------------------------------------------- /neural_compressor/transformers/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/transformers/utils/__init__.py -------------------------------------------------------------------------------- /neural_compressor/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/__init__.py -------------------------------------------------------------------------------- /neural_compressor/utils/collect_layer_histogram.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/collect_layer_histogram.py -------------------------------------------------------------------------------- /neural_compressor/utils/constant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/constant.py -------------------------------------------------------------------------------- /neural_compressor/utils/create_obj_from_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/create_obj_from_config.py -------------------------------------------------------------------------------- /neural_compressor/utils/export/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/export/__init__.py -------------------------------------------------------------------------------- /neural_compressor/utils/export/qlinear2qdq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/export/qlinear2qdq.py -------------------------------------------------------------------------------- /neural_compressor/utils/export/tf2onnx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/export/tf2onnx.py -------------------------------------------------------------------------------- /neural_compressor/utils/export/torch2onnx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/export/torch2onnx.py -------------------------------------------------------------------------------- /neural_compressor/utils/kl_divergence.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/kl_divergence.py -------------------------------------------------------------------------------- /neural_compressor/utils/load_huggingface.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/load_huggingface.py -------------------------------------------------------------------------------- /neural_compressor/utils/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/logger.py -------------------------------------------------------------------------------- /neural_compressor/utils/options.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/options.py -------------------------------------------------------------------------------- /neural_compressor/utils/pytorch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/pytorch.py -------------------------------------------------------------------------------- /neural_compressor/utils/utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/utility.py -------------------------------------------------------------------------------- /neural_compressor/utils/weights_details.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/utils/weights_details.py -------------------------------------------------------------------------------- /neural_compressor/version.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/neural_compressor/version.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/pyproject.toml -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/requirements.txt -------------------------------------------------------------------------------- /requirements_pt.txt: -------------------------------------------------------------------------------- 1 | numpy 2 | prettytable 3 | psutil 4 | py-cpuinfo 5 | pydantic 6 | -------------------------------------------------------------------------------- /requirements_tf.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/requirements_tf.txt -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/setup.cfg -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/setup.py -------------------------------------------------------------------------------- /test/3x/common/test_common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/common/test_common.py -------------------------------------------------------------------------------- /test/3x/common/test_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/common/test_logger.py -------------------------------------------------------------------------------- /test/3x/common/test_param.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/common/test_param.py -------------------------------------------------------------------------------- /test/3x/common/test_utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/common/test_utility.py -------------------------------------------------------------------------------- /test/3x/tensorflow/keras/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/keras/requirements.txt -------------------------------------------------------------------------------- /test/3x/tensorflow/keras/test_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/keras/test_config.py -------------------------------------------------------------------------------- /test/3x/tensorflow/keras/test_layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/keras/test_layers.py -------------------------------------------------------------------------------- /test/3x/tensorflow/keras/test_model_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/keras/test_model_wrappers.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/ptq/test_bf16_convert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/ptq/test_bf16_convert.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/ptq/test_data_pipline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/ptq/test_data_pipline.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/ptq/test_fold_const.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/ptq/test_fold_const.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/ptq/test_gpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/ptq/test_gpu.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/ptq/test_graph_cac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/ptq/test_graph_cac.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/ptq/test_graph_concat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/ptq/test_graph_concat.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/ptq/test_graph_fold_bn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/ptq/test_graph_fold_bn.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/ptq/test_graph_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/ptq/test_graph_util.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/ptq/test_grappler_pass.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/ptq/test_grappler_pass.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/ptq/test_query_yaml.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/ptq/test_query_yaml.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/ptq/test_rnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/ptq/test_rnn.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/ptq/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/ptq/test_utils.py -------------------------------------------------------------------------------- /test/3x/tensorflow/quantization/test_smooth_quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/quantization/test_smooth_quant.py -------------------------------------------------------------------------------- /test/3x/tensorflow/requirements.txt: -------------------------------------------------------------------------------- 1 | pytest 2 | -------------------------------------------------------------------------------- /test/3x/tensorflow/test_autotune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/test_autotune.py -------------------------------------------------------------------------------- /test/3x/tensorflow/test_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/test_config.py -------------------------------------------------------------------------------- /test/3x/tensorflow/test_model_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/test_model_wrappers.py -------------------------------------------------------------------------------- /test/3x/tensorflow/test_quantize_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/tensorflow/test_quantize_model.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/fp8_quant/__init__.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/fp8_quant/conftest.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/fp8_tests.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/fp8_quant/fp8_tests.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/pytest.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/fp8_quant/pytest.ini -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/test_basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/fp8_quant/test_basic.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/test_hpu_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/fp8_quant/test_hpu_utils.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/test_register_apis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/fp8_quant/test_register_apis.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/fp8_quant/test_utils.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/tester.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/fp8_quant/tester.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/unit_tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/fp8_quant/unit_tests/__init__.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/unit_tests/test_functions/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/unit_tests/test_layers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant/unit_tests/test_qdq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/fp8_quant/unit_tests/test_qdq.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/fp8_quant_xpu/unit_tests/aux_files/empty_measure_hooks_maxabs.npz: -------------------------------------------------------------------------------- 1 | {} -------------------------------------------------------------------------------- /test/3x/torch/algorithms/mx_quant/test_mx_utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/mx_quant/test_mx_utility.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/pt2e_quant/test_pt2e_w8a8.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/pt2e_quant/test_pt2e_w8a8.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/qat/test_qat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/qat/test_qat.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/qat/test_quant_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/qat/test_quant_utils.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/qat/test_quantizer_and_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/qat/test_quantizer_and_linear.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/smooth_quant/test_sq_utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/smooth_quant/test_sq_utility.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/weight_only/test_woq_module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/weight_only/test_woq_module.py -------------------------------------------------------------------------------- /test/3x/torch/algorithms/weight_only/test_woq_utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/algorithms/weight_only/test_woq_utility.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/fp8_quant/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/fp8_quant/conftest.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/fp8_quant/test_layer_wise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/fp8_quant/test_layer_wise.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/fp8_quant/test_save_load.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/fp8_quant/test_save_load.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/jsons/test_hw_quant.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/jsons/test_hw_quant.json -------------------------------------------------------------------------------- /test/3x/torch/quantization/test_mx_quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/test_mx_quant.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/test_pt2e_quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/test_pt2e_quant.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/test_smooth_quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/test_smooth_quant.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/test_static_quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/test_static_quant.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/weight_only/test_autoround.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/weight_only/test_autoround.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/weight_only/test_awq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/weight_only/test_awq.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/weight_only/test_gptq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/weight_only/test_gptq.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/weight_only/test_hqq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/weight_only/test_hqq.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/weight_only/test_load.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/weight_only/test_load.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/weight_only/test_rtn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/weight_only/test_rtn.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/weight_only/test_teq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/weight_only/test_teq.py -------------------------------------------------------------------------------- /test/3x/torch/quantization/weight_only/test_woq_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/quantization/weight_only/test_woq_utils.py -------------------------------------------------------------------------------- /test/3x/torch/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/requirements.txt -------------------------------------------------------------------------------- /test/3x/torch/test_autotune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/test_autotune.py -------------------------------------------------------------------------------- /test/3x/torch/test_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/test_config.py -------------------------------------------------------------------------------- /test/3x/torch/utils/test_auto_accelerator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/utils/test_auto_accelerator.py -------------------------------------------------------------------------------- /test/3x/torch/utils/test_torch_utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/3x/torch/utils/test_torch_utility.py -------------------------------------------------------------------------------- /test/adaptor/onnxrt_adaptor/test_adaptor_onnxrt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/adaptor/onnxrt_adaptor/test_adaptor_onnxrt.py -------------------------------------------------------------------------------- /test/adaptor/onnxrt_adaptor/test_layer_wise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/adaptor/onnxrt_adaptor/test_layer_wise.py -------------------------------------------------------------------------------- /test/adaptor/onnxrt_adaptor/test_onnxrt_augment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/adaptor/onnxrt_adaptor/test_onnxrt_augment.py -------------------------------------------------------------------------------- /test/adaptor/onnxrt_adaptor/test_onnxrt_operators.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/adaptor/onnxrt_adaptor/test_onnxrt_operators.py -------------------------------------------------------------------------------- /test/adaptor/pytorch_adaptor/test_adaptor_pytorch_2x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/adaptor/pytorch_adaptor/test_adaptor_pytorch_2x.py -------------------------------------------------------------------------------- /test/adaptor/pytorch_adaptor/test_adaptor_security.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/adaptor/pytorch_adaptor/test_adaptor_security.py -------------------------------------------------------------------------------- /test/adaptor/tensorflow_adaptor/test_bf16_convert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/adaptor/tensorflow_adaptor/test_bf16_convert.py -------------------------------------------------------------------------------- /test/adaptor/tensorflow_adaptor/test_smooth_quant_tf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/adaptor/tensorflow_adaptor/test_smooth_quant_tf.py -------------------------------------------------------------------------------- /test/adaptor/tensorflow_adaptor/test_tensorflow_gpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/adaptor/tensorflow_adaptor/test_tensorflow_gpu.py -------------------------------------------------------------------------------- /test/adaptor/tensorflow_adaptor/test_tensorflow_rnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/adaptor/tensorflow_adaptor/test_tensorflow_rnn.py -------------------------------------------------------------------------------- /test/adaptor/tensorflow_adaptor/test_tf_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/adaptor/tensorflow_adaptor/test_tf_util.py -------------------------------------------------------------------------------- /test/adaptor/test_pytorch_layer_scale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/adaptor/test_pytorch_layer_scale.py -------------------------------------------------------------------------------- /test/algorithm/ipex_config_tmp.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/algorithm/ipex_config_tmp.json -------------------------------------------------------------------------------- /test/algorithm/modeling_gptj.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/algorithm/modeling_gptj.py -------------------------------------------------------------------------------- /test/algorithm/test_layer_wise_quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/algorithm/test_layer_wise_quant.py -------------------------------------------------------------------------------- /test/algorithm/test_lwq_weight_only.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/algorithm/test_lwq_weight_only.py -------------------------------------------------------------------------------- /test/algorithm/test_smooth_quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/algorithm/test_smooth_quant.py -------------------------------------------------------------------------------- /test/algorithm/test_smooth_quant_onnx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/algorithm/test_smooth_quant_onnx.py -------------------------------------------------------------------------------- /test/config/test_config_2x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/config/test_config_2x.py -------------------------------------------------------------------------------- /test/data/test_dataloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/data/test_dataloader.py -------------------------------------------------------------------------------- /test/data/test_filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/data/test_filter.py -------------------------------------------------------------------------------- /test/data/test_transform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/data/test_transform.py -------------------------------------------------------------------------------- /test/distillation/test_distillation_2.x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/distillation/test_distillation_2.x.py -------------------------------------------------------------------------------- /test/distillation/test_self_distillation_2.x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/distillation/test_self_distillation_2.x.py -------------------------------------------------------------------------------- /test/distributed/test_distributed_tf_dataloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/distributed/test_distributed_tf_dataloader.py -------------------------------------------------------------------------------- /test/export/test_onnx_qlieanr_to_qdq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/export/test_onnx_qlieanr_to_qdq.py -------------------------------------------------------------------------------- /test/export/test_torch2onnx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/export/test_torch2onnx.py -------------------------------------------------------------------------------- /test/hpo/test_hpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/hpo/test_hpo.py -------------------------------------------------------------------------------- /test/images/cat.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/images/cat.jpg -------------------------------------------------------------------------------- /test/ipex/test_adaptor_ipex.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/ipex/test_adaptor_ipex.py -------------------------------------------------------------------------------- /test/itex/test_keras_in_keras_out.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/itex/test_keras_in_keras_out.py -------------------------------------------------------------------------------- /test/itex/test_smooth_quant_itex.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/itex/test_smooth_quant_itex.py -------------------------------------------------------------------------------- /test/itex/test_tensorflow_itex_2.x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/itex/test_tensorflow_itex_2.x.py -------------------------------------------------------------------------------- /test/itex/test_tensorflow_qdq_convert_to_onnx_qdq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/itex/test_tensorflow_qdq_convert_to_onnx_qdq.py -------------------------------------------------------------------------------- /test/metric/test_coco_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/metric/test_coco_tools.py -------------------------------------------------------------------------------- /test/metric/test_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/metric/test_metrics.py -------------------------------------------------------------------------------- /test/metric/test_metrics_2x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/metric/test_metrics_2x.py -------------------------------------------------------------------------------- /test/metric/test_mse_2x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/metric/test_mse_2x.py -------------------------------------------------------------------------------- /test/mixed_precision/test_mixed_precision.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/mixed_precision/test_mixed_precision.py -------------------------------------------------------------------------------- /test/mixed_precision/test_mixed_precision_keras_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/mixed_precision/test_mixed_precision_keras_model.py -------------------------------------------------------------------------------- /test/model/test_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/model/test_model.py -------------------------------------------------------------------------------- /test/model/test_model_pytorch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/model/test_model_pytorch.py -------------------------------------------------------------------------------- /test/model/test_onnx_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/model/test_onnx_model.py -------------------------------------------------------------------------------- /test/model/test_tensorflow_auto_input_output.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/model/test_tensorflow_auto_input_output.py -------------------------------------------------------------------------------- /test/objective/test_objective.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/objective/test_objective.py -------------------------------------------------------------------------------- /test/pruning_with_pt/pruning_2.x/test_auto_slim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/pruning_with_pt/pruning_2.x/test_auto_slim.py -------------------------------------------------------------------------------- /test/pruning_with_pt/pruning_2.x/test_conv_pruning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/pruning_with_pt/pruning_2.x/test_conv_pruning.py -------------------------------------------------------------------------------- /test/pruning_with_pt/pruning_2.x/test_pruning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/pruning_with_pt/pruning_2.x/test_pruning.py -------------------------------------------------------------------------------- /test/pruning_with_pt/pruning_2.x/test_pruning_block.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/pruning_with_pt/pruning_2.x/test_pruning_block.py -------------------------------------------------------------------------------- /test/pruning_with_pt/pruning_2.x/test_pruning_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/pruning_with_pt/pruning_2.x/test_pruning_config.py -------------------------------------------------------------------------------- /test/pruning_with_pt/pruning_2.x/test_pruning_criteria.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/pruning_with_pt/pruning_2.x/test_pruning_criteria.py -------------------------------------------------------------------------------- /test/pruning_with_pt/pruning_2.x/test_pruning_patterns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/pruning_with_pt/pruning_2.x/test_pruning_patterns.py -------------------------------------------------------------------------------- /test/pruning_with_pt/pruning_2.x/test_pruning_regs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/pruning_with_pt/pruning_2.x/test_pruning_regs.py -------------------------------------------------------------------------------- /test/pruning_with_pt/pruning_2.x/test_pruning_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/pruning_with_pt/pruning_2.x/test_pruning_types.py -------------------------------------------------------------------------------- /test/pruning_with_pt/pruning_2_plus.x/test_pruning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/pruning_with_pt/pruning_2_plus.x/test_pruning.py -------------------------------------------------------------------------------- /test/pruning_with_pt/pruning_2_plus.x/test_wanda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/pruning_with_pt/pruning_2_plus.x/test_wanda.py -------------------------------------------------------------------------------- /test/pruning_with_tf/pruning_2.x/test_pruning_keras.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/pruning_with_tf/pruning_2.x/test_pruning_keras.py -------------------------------------------------------------------------------- /test/quantization/test_tensorflow_qat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/quantization/test_tensorflow_qat.py -------------------------------------------------------------------------------- /test/quantization/test_weight_only_quantization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/quantization/test_weight_only_quantization.py -------------------------------------------------------------------------------- /test/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/requirements.txt -------------------------------------------------------------------------------- /test/strategy/test_basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_basic.py -------------------------------------------------------------------------------- /test/strategy/test_bayesian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_bayesian.py -------------------------------------------------------------------------------- /test/strategy/test_distributed_tuning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_distributed_tuning.py -------------------------------------------------------------------------------- /test/strategy/test_exhaustive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_exhaustive.py -------------------------------------------------------------------------------- /test/strategy/test_hawq_v2_2x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_hawq_v2_2x.py -------------------------------------------------------------------------------- /test/strategy/test_lower_bit_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_lower_bit_sampler.py -------------------------------------------------------------------------------- /test/strategy/test_mse.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_mse.py -------------------------------------------------------------------------------- /test/strategy/test_mse_v2_2x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_mse_v2_2x.py -------------------------------------------------------------------------------- /test/strategy/test_new_datatype.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_new_datatype.py -------------------------------------------------------------------------------- /test/strategy/test_quant_level.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_quant_level.py -------------------------------------------------------------------------------- /test/strategy/test_random.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_random.py -------------------------------------------------------------------------------- /test/strategy/test_tpe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_tpe.py -------------------------------------------------------------------------------- /test/strategy/test_tuning_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_tuning_sampler.py -------------------------------------------------------------------------------- /test/strategy/test_tuning_space.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_tuning_space.py -------------------------------------------------------------------------------- /test/strategy/test_tuning_space_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_tuning_space_v2.py -------------------------------------------------------------------------------- /test/strategy/test_utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/strategy/test_utility.py -------------------------------------------------------------------------------- /test/tfnewapi/test_big_saved_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/tfnewapi/test_big_saved_model.py -------------------------------------------------------------------------------- /test/tfnewapi/test_smooth_quant_newapi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/tfnewapi/test_smooth_quant_newapi.py -------------------------------------------------------------------------------- /test/utils/test_cpu_info.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/utils/test_cpu_info.py -------------------------------------------------------------------------------- /test/utils/test_huggingface.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/utils/test_huggingface.py -------------------------------------------------------------------------------- /test/utils/test_layer_histogram.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/utils/test_layer_histogram.py -------------------------------------------------------------------------------- /test/utils/test_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/test/utils/test_logger.py -------------------------------------------------------------------------------- /third-party-programs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/intel/neural-compressor/HEAD/third-party-programs.txt --------------------------------------------------------------------------------