LICENSE
README.md
pyproject.toml
setup.cfg
setup.py
third-party-programs.txt
neural_compressor/__init__.py
neural_compressor/version.py
neural_compressor.egg-info/PKG-INFO
neural_compressor.egg-info/SOURCES.txt
neural_compressor.egg-info/dependency_links.txt
neural_compressor.egg-info/requires.txt
neural_compressor.egg-info/top_level.txt
neural_compressor/common/__init__.py
neural_compressor/common/base_config.py
neural_compressor/common/base_tuning.py
neural_compressor/common/tuning_param.py
neural_compressor/common/version.py
neural_compressor/common/utils/__init__.py
neural_compressor/common/utils/constants.py
neural_compressor/common/utils/logger.py
neural_compressor/common/utils/save_load.py
neural_compressor/common/utils/utility.py
neural_compressor/evaluation/__init__.py
neural_compressor/evaluation/bigcode_eval/__init__.py
neural_compressor/evaluation/bigcode_eval/evaluator.py
neural_compressor/evaluation/hf_eval/__init__.py
neural_compressor/evaluation/hf_eval/evaluator.py
neural_compressor/evaluation/hf_eval/hf_datasets/__init__.py
neural_compressor/evaluation/hf_eval/hf_datasets/cnn_dailymail.py
neural_compressor/evaluation/lm_eval/__init__.py
neural_compressor/evaluation/lm_eval/accuracy.py
neural_compressor/evaluation/lm_eval/utils.py
neural_compressor/evaluation/lm_eval/models/__init__.py
neural_compressor/evaluation/lm_eval/models/huggingface.py
neural_compressor/jax/__init__.py
neural_compressor/jax/algorithms/__init__.py
neural_compressor/jax/algorithms/dynamic.py
neural_compressor/jax/algorithms/static.py
neural_compressor/jax/quantization/__init__.py
neural_compressor/jax/quantization/config.py
neural_compressor/jax/quantization/layers_dynamic.py
neural_compressor/jax/quantization/layers_static.py
neural_compressor/jax/quantization/quantize.py
neural_compressor/jax/quantization/saving.py
neural_compressor/jax/utils/__init__.py
neural_compressor/jax/utils/utility.py
neural_compressor/tensorflow/__init__.py
neural_compressor/tensorflow/algorithms/__init__.py
neural_compressor/tensorflow/algorithms/smoother/__init__.py
neural_compressor/tensorflow/algorithms/smoother/calibration.py
neural_compressor/tensorflow/algorithms/smoother/core.py
neural_compressor/tensorflow/algorithms/smoother/scaler.py
neural_compressor/tensorflow/algorithms/static_quant/__init__.py
neural_compressor/tensorflow/algorithms/static_quant/keras.py
neural_compressor/tensorflow/algorithms/static_quant/keras.yaml
neural_compressor/tensorflow/algorithms/static_quant/tensorflow.py
neural_compressor/tensorflow/algorithms/static_quant/tensorflow.yaml
neural_compressor/tensorflow/algorithms/static_quant/tensorflow_itex.yaml
neural_compressor/tensorflow/keras/__init__.py
neural_compressor/tensorflow/keras/layers/__init__.py
neural_compressor/tensorflow/keras/layers/conv2d.py
neural_compressor/tensorflow/keras/layers/dense.py
neural_compressor/tensorflow/keras/layers/depthwise_conv2d.py
neural_compressor/tensorflow/keras/layers/layer_initializer.py
neural_compressor/tensorflow/keras/layers/pool2d.py
neural_compressor/tensorflow/keras/layers/separable_conv2d.py
neural_compressor/tensorflow/keras/quantization/__init__.py
neural_compressor/tensorflow/keras/quantization/config.py
neural_compressor/tensorflow/quantization/__init__.py
neural_compressor/tensorflow/quantization/algorithm_entry.py
neural_compressor/tensorflow/quantization/autotune.py
neural_compressor/tensorflow/quantization/config.py
neural_compressor/tensorflow/quantization/quantize.py
neural_compressor/tensorflow/quantization/utils/__init__.py
neural_compressor/tensorflow/quantization/utils/graph_converter.py
neural_compressor/tensorflow/quantization/utils/graph_util.py
neural_compressor/tensorflow/quantization/utils/quantize_graph_common.py
neural_compressor/tensorflow/quantization/utils/utility.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/__init__.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/graph_base.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/__init__.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/bf16_convert.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/bf16/dequantize_cast_optimizer.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/__init__.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_add_to_biasadd.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_layout.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_leakyrelu.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_nan_to_random.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/convert_placeholder_to_const.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dilated_contraction.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/dummy_biasadd.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/expanddims_optimizer.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fetch_weight_from_reshape.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_batch_norm.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fold_constant.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_biasadd_add.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_column_wise_mul.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_conv_with_math.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_bn.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_decomposed_in.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_gelu.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_layer_norm.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_conv.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_pad_with_fp32_conv.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/fuse_reshape_transpose.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/graph_cse_optimizer.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/grappler_pass.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/insert_print_node.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/move_squeeze_after_relu.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/pre_optimize.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/remove_training_nodes.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/rename_batch_norm.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/split_shared_input.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_equivalent_nodes.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/strip_unused_nodes.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/generic/switch_optimizer.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/__init__.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_fake_quant.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/freeze_value.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_redundant_dequantize.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_conv_requantize.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/fuse_matmul_requantize.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/meta_op_optimizer.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_hostconst_converter.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/post_quantized_op_cse.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/int8/scale_propagation.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/__init__.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/insert_qdq_pattern.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/merge_duplicated_qdq.py
neural_compressor/tensorflow/quantization/utils/graph_rewriter/qdq/share_qdq_y_pattern.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/__init__.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_base.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_bn.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_concatv2.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_conv.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_for_intel_cpu.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_matmul.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/quantize_graph_pooling.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/__init__.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_bn.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_concatv2.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_conv.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_deconv.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_in.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_matmul.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/fuse_qdq_pooling.py
neural_compressor/tensorflow/quantization/utils/quantize_graph/qdq/optimize_qdq.py
neural_compressor/tensorflow/quantization/utils/transform_graph/__init__.py
neural_compressor/tensorflow/quantization/utils/transform_graph/bias_correction.py
neural_compressor/tensorflow/quantization/utils/transform_graph/graph_transform_base.py
neural_compressor/tensorflow/quantization/utils/transform_graph/insert_logging.py
neural_compressor/tensorflow/quantization/utils/transform_graph/rerange_quantized_concat.py
neural_compressor/tensorflow/utils/__init__.py
neural_compressor/tensorflow/utils/constants.py
neural_compressor/tensorflow/utils/data.py
neural_compressor/tensorflow/utils/model.py
neural_compressor/tensorflow/utils/model_wrappers.py
neural_compressor/tensorflow/utils/utility.py
neural_compressor/torch/__init__.py
neural_compressor/torch/algorithms/__init__.py
neural_compressor/torch/algorithms/base_algorithm.py
neural_compressor/torch/algorithms/autoround/__init__.py
neural_compressor/torch/algorithms/autoround/autoround.py
neural_compressor/torch/algorithms/fp8_quant/__init__.py
neural_compressor/torch/algorithms/fp8_quant/common.py
neural_compressor/torch/algorithms/fp8_quant/model_configs.py
neural_compressor/torch/algorithms/fp8_quant/observer.py
neural_compressor/torch/algorithms/fp8_quant/patched_module_base.py
neural_compressor/torch/algorithms/fp8_quant/quantizer.py
neural_compressor/torch/algorithms/fp8_quant/save_load.py
neural_compressor/torch/algorithms/fp8_quant/scaling_method_base.py
neural_compressor/torch/algorithms/fp8_quant/_core/__init__.py
neural_compressor/torch/algorithms/fp8_quant/_core/common.py
neural_compressor/torch/algorithms/fp8_quant/_core/external_func_impl.py
neural_compressor/torch/algorithms/fp8_quant/_core/fp_utils.py
neural_compressor/torch/algorithms/fp8_quant/_core/measure.py
neural_compressor/torch/algorithms/fp8_quant/_core/patching_common.py
neural_compressor/torch/algorithms/fp8_quant/_core/quant_dequant.py
neural_compressor/torch/algorithms/fp8_quant/_core/quantize.py
neural_compressor/torch/algorithms/fp8_quant/_core/scale.py
neural_compressor/torch/algorithms/fp8_quant/_core/scale_handler.py
neural_compressor/torch/algorithms/fp8_quant/_core/utils.py
neural_compressor/torch/algorithms/fp8_quant/_core/quantized_func_wrappers/__init__.py
neural_compressor/torch/algorithms/fp8_quant/_core/quantized_func_wrappers/quantized_func_wrapper.py
neural_compressor/torch/algorithms/fp8_quant/_core/quantized_func_wrappers/quantized_func_wrapper_api.py
neural_compressor/torch/algorithms/fp8_quant/_core/quantized_func_wrappers/cpu/__init__.py
neural_compressor/torch/algorithms/fp8_quant/_core/quantized_func_wrappers/cpu/cpu_quantized_func_wrapper.py
neural_compressor/torch/algorithms/fp8_quant/_core/quantized_func_wrappers/hpu/__init__.py
neural_compressor/torch/algorithms/fp8_quant/_core/quantized_func_wrappers/hpu/hpu_quantized_func_wrapper.py
neural_compressor/torch/algorithms/fp8_quant/_core/quantized_func_wrappers/xpu/__init__.py
neural_compressor/torch/algorithms/fp8_quant/_core/quantized_func_wrappers/xpu/xpu_quantized_func_wrapper.py
neural_compressor/torch/algorithms/fp8_quant/_core/save_measure/__init__.py
neural_compressor/torch/algorithms/fp8_quant/_core/save_measure/hook_logic.py
neural_compressor/torch/algorithms/fp8_quant/_core/save_measure/save_file_proccess.py
neural_compressor/torch/algorithms/fp8_quant/_core/save_measure/save_files.py
neural_compressor/torch/algorithms/fp8_quant/_core/scale_methods/__init__.py
neural_compressor/torch/algorithms/fp8_quant/_core/scale_methods/ops_quantizer.py
neural_compressor/torch/algorithms/fp8_quant/_core/scale_methods/round_scales_function.py
neural_compressor/torch/algorithms/fp8_quant/_core/scale_methods/scale_method_config.py
neural_compressor/torch/algorithms/fp8_quant/_core/scale_methods/scale_method_factory.py
neural_compressor/torch/algorithms/fp8_quant/_core/scale_methods/scale_method_parser.py
neural_compressor/torch/algorithms/fp8_quant/_core/scale_methods/scales_method.py
neural_compressor/torch/algorithms/fp8_quant/_quant_common/__init__.py
neural_compressor/torch/algorithms/fp8_quant/_quant_common/helper_modules.py
neural_compressor/torch/algorithms/fp8_quant/_quant_common/quant_config.py
neural_compressor/torch/algorithms/fp8_quant/custom_config/__init__.py
neural_compressor/torch/algorithms/fp8_quant/custom_config/custom_example.json
neural_compressor/torch/algorithms/fp8_quant/custom_config/llama_measure.json
neural_compressor/torch/algorithms/fp8_quant/custom_config/llama_quant.json
neural_compressor/torch/algorithms/fp8_quant/custom_config/measure_config.json
neural_compressor/torch/algorithms/fp8_quant/custom_config/quant_config.json
neural_compressor/torch/algorithms/fp8_quant/prepare_quant/__init__.py
neural_compressor/torch/algorithms/fp8_quant/prepare_quant/prepare_model.py
neural_compressor/torch/algorithms/fp8_quant/scripts/__init__.py
neural_compressor/torch/algorithms/fp8_quant/scripts/postprocessing_vllm_measurements.py
neural_compressor/torch/algorithms/fp8_quant/utils/__init__.py
neural_compressor/torch/algorithms/fp8_quant/utils/logger.py
neural_compressor/torch/algorithms/layer_wise/__init__.py
neural_compressor/torch/algorithms/layer_wise/load.py
neural_compressor/torch/algorithms/layer_wise/modified_pickle.py
neural_compressor/torch/algorithms/layer_wise/utils.py
neural_compressor/torch/algorithms/mixed_low_precision/__init__.py
neural_compressor/torch/algorithms/mixed_low_precision/maxabs_quant.json
neural_compressor/torch/algorithms/mixed_low_precision/modules.py
neural_compressor/torch/algorithms/mixed_low_precision/quantizer.py
neural_compressor/torch/algorithms/mixed_low_precision/custom_methods/__init__.py
neural_compressor/torch/algorithms/mixed_low_precision/custom_methods/gptq.py
neural_compressor/torch/algorithms/mixed_low_precision/custom_methods/quarot.py
neural_compressor/torch/algorithms/mixed_low_precision/custom_methods/quarot_utils.py
neural_compressor/torch/algorithms/mixed_precision/__init__.py
neural_compressor/torch/algorithms/mixed_precision/half_precision_convert.py
neural_compressor/torch/algorithms/mixed_precision/module_wrappers.py
neural_compressor/torch/algorithms/mx_quant/__init__.py
neural_compressor/torch/algorithms/mx_quant/mx.py
neural_compressor/torch/algorithms/mx_quant/utils.py
neural_compressor/torch/algorithms/pt2e_quant/__init__.py
neural_compressor/torch/algorithms/pt2e_quant/core.py
neural_compressor/torch/algorithms/pt2e_quant/half_precision_rewriter.py
neural_compressor/torch/algorithms/pt2e_quant/pt2e_compat.py
neural_compressor/torch/algorithms/pt2e_quant/save_load.py
neural_compressor/torch/algorithms/pt2e_quant/utility.py
neural_compressor/torch/algorithms/qat/__init__.py
neural_compressor/torch/algorithms/qat/quant_linear.py
neural_compressor/torch/algorithms/qat/quant_utils.py
neural_compressor/torch/algorithms/qat/tensor_quantizer.py
neural_compressor/torch/algorithms/smooth_quant/__init__.py
neural_compressor/torch/algorithms/smooth_quant/save_load.py
neural_compressor/torch/algorithms/smooth_quant/smooth_quant.py
neural_compressor/torch/algorithms/smooth_quant/utility.py
neural_compressor/torch/algorithms/static_quant/__init__.py
neural_compressor/torch/algorithms/static_quant/save_load.py
neural_compressor/torch/algorithms/static_quant/static_quant.py
neural_compressor/torch/algorithms/static_quant/utility.py
neural_compressor/torch/algorithms/weight_only/__init__.py
neural_compressor/torch/algorithms/weight_only/awq.py
neural_compressor/torch/algorithms/weight_only/gptq.py
neural_compressor/torch/algorithms/weight_only/modules.py
neural_compressor/torch/algorithms/weight_only/rtn.py
neural_compressor/torch/algorithms/weight_only/save_load.py
neural_compressor/torch/algorithms/weight_only/teq.py
neural_compressor/torch/algorithms/weight_only/utility.py
neural_compressor/torch/algorithms/weight_only/hqq/__init__.py
neural_compressor/torch/algorithms/weight_only/hqq/bitpack.py
neural_compressor/torch/algorithms/weight_only/hqq/config.py
neural_compressor/torch/algorithms/weight_only/hqq/core.py
neural_compressor/torch/algorithms/weight_only/hqq/optimizer.py
neural_compressor/torch/algorithms/weight_only/hqq/qtensor.py
neural_compressor/torch/algorithms/weight_only/hqq/quantizer.py
neural_compressor/torch/export/__init__.py
neural_compressor/torch/export/export_hf.py
neural_compressor/torch/export/pt2e_export.py
neural_compressor/torch/quantization/__init__.py
neural_compressor/torch/quantization/algorithm_entry.py
neural_compressor/torch/quantization/autotune.py
neural_compressor/torch/quantization/config.py
neural_compressor/torch/quantization/quantize.py
neural_compressor/torch/quantization/save_load_entry.py
neural_compressor/torch/utils/__init__.py
neural_compressor/torch/utils/auto_accelerator.py
neural_compressor/torch/utils/bit_packer.py
neural_compressor/torch/utils/block_wise.py
neural_compressor/torch/utils/constants.py
neural_compressor/torch/utils/environ.py
neural_compressor/torch/utils/llm_utility.py
neural_compressor/torch/utils/utility.py
neural_compressor/transformers/__init__.py
neural_compressor/transformers/generation/__init__.py
neural_compressor/transformers/generation/beam_search.py
neural_compressor/transformers/generation/greedy_search.py
neural_compressor/transformers/models/__init__.py
neural_compressor/transformers/models/modeling_auto.py
neural_compressor/transformers/quantization/__init__.py
neural_compressor/transformers/quantization/utils.py
neural_compressor/transformers/utils/__init__.py
neural_compressor/transformers/utils/quantization_config.py