LICENSE
README.md
pyproject.toml
setup.cfg
setup.py
third-party-programs.txt
neural_compressor/__init__.py
neural_compressor/benchmark.py
neural_compressor/config.py
neural_compressor/mix_precision.py
neural_compressor/objective.py
neural_compressor/quantization.py
neural_compressor/training.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/entry_points.txt
neural_compressor.egg-info/requires.txt
neural_compressor.egg-info/top_level.txt
neural_compressor/adaptor/__init__.py
neural_compressor/adaptor/adaptor.py
neural_compressor/adaptor/keras.py
neural_compressor/adaptor/keras.yaml
neural_compressor/adaptor/mxnet.py
neural_compressor/adaptor/mxnet.yaml
neural_compressor/adaptor/onnxrt.py
neural_compressor/adaptor/onnxrt.yaml
neural_compressor/adaptor/onnxrt_cuda.yaml
neural_compressor/adaptor/onnxrt_dml.yaml
neural_compressor/adaptor/onnxrt_dnnl.yaml
neural_compressor/adaptor/onnxrt_trt.yaml
neural_compressor/adaptor/pytorch.py
neural_compressor/adaptor/pytorch_cpu.yaml
neural_compressor/adaptor/pytorch_gpu.yaml
neural_compressor/adaptor/pytorch_ipex.yaml
neural_compressor/adaptor/query.py
neural_compressor/adaptor/tensorflow.py
neural_compressor/adaptor/tensorflow.yaml
neural_compressor/adaptor/tensorflow_itex.yaml
neural_compressor/adaptor/keras_utils/__init__.py
neural_compressor/adaptor/keras_utils/conv2d.py
neural_compressor/adaptor/keras_utils/dense.py
neural_compressor/adaptor/keras_utils/depthwise_conv2d.py
neural_compressor/adaptor/keras_utils/pool2d.py
neural_compressor/adaptor/keras_utils/quantizer.py
neural_compressor/adaptor/keras_utils/separable_conv2d.py
neural_compressor/adaptor/mxnet_utils/__init__.py
neural_compressor/adaptor/mxnet_utils/util.py
neural_compressor/adaptor/ox_utils/__init__.py
neural_compressor/adaptor/ox_utils/calibration.py
neural_compressor/adaptor/ox_utils/calibrator.py
neural_compressor/adaptor/ox_utils/quantizer.py
neural_compressor/adaptor/ox_utils/smooth_quant.py
neural_compressor/adaptor/ox_utils/util.py
neural_compressor/adaptor/ox_utils/weight_only.py
neural_compressor/adaptor/ox_utils/operators/__init__.py
neural_compressor/adaptor/ox_utils/operators/activation.py
neural_compressor/adaptor/ox_utils/operators/argmax.py
neural_compressor/adaptor/ox_utils/operators/attention.py
neural_compressor/adaptor/ox_utils/operators/binary_op.py
neural_compressor/adaptor/ox_utils/operators/concat.py
neural_compressor/adaptor/ox_utils/operators/conv.py
neural_compressor/adaptor/ox_utils/operators/direct_q8.py
neural_compressor/adaptor/ox_utils/operators/embed_layernorm.py
neural_compressor/adaptor/ox_utils/operators/gather.py
neural_compressor/adaptor/ox_utils/operators/gavgpool.py
neural_compressor/adaptor/ox_utils/operators/gemm.py
neural_compressor/adaptor/ox_utils/operators/lstm.py
neural_compressor/adaptor/ox_utils/operators/matmul.py
neural_compressor/adaptor/ox_utils/operators/maxpool.py
neural_compressor/adaptor/ox_utils/operators/norm.py
neural_compressor/adaptor/ox_utils/operators/ops.py
neural_compressor/adaptor/ox_utils/operators/pad.py
neural_compressor/adaptor/ox_utils/operators/pooling.py
neural_compressor/adaptor/ox_utils/operators/reduce.py
neural_compressor/adaptor/ox_utils/operators/resize.py
neural_compressor/adaptor/ox_utils/operators/split.py
neural_compressor/adaptor/ox_utils/operators/unary_op.py
neural_compressor/adaptor/tf_utils/__init__.py
neural_compressor/adaptor/tf_utils/graph_converter.py
neural_compressor/adaptor/tf_utils/graph_converter_without_calib.py
neural_compressor/adaptor/tf_utils/graph_util.py
neural_compressor/adaptor/tf_utils/quantize_graph_common.py
neural_compressor/adaptor/tf_utils/smooth_quant_calibration.py
neural_compressor/adaptor/tf_utils/smooth_quant_scaler.py
neural_compressor/adaptor/tf_utils/tf2onnx_converter.py
neural_compressor/adaptor/tf_utils/util.py
neural_compressor/adaptor/tf_utils/graph_rewriter/__init__.py
neural_compressor/adaptor/tf_utils/graph_rewriter/graph_base.py
neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/__init__.py
neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/bf16_convert.py
neural_compressor/adaptor/tf_utils/graph_rewriter/bf16/dequantize_cast_optimizer.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/__init__.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_add_to_biasadd.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_layout.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_leakyrelu.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_nan_to_random.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/convert_placeholder_to_const.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dilated_contraction.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/dummy_biasadd.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/expanddims_optimizer.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fetch_weight_from_reshape.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_batch_norm.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fold_constant.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_biasadd_add.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_column_wise_mul.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_conv_with_math.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_bn.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_decomposed_in.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_gelu.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_layer_norm.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_conv.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_pad_with_fp32_conv.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/fuse_reshape_transpose.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/graph_cse_optimizer.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/grappler_pass.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/insert_print_node.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/move_squeeze_after_relu.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/pre_optimize.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/remove_training_nodes.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/rename_batch_norm.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/split_shared_input.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_equivalent_nodes.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/strip_unused_nodes.py
neural_compressor/adaptor/tf_utils/graph_rewriter/generic/switch_optimizer.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/__init__.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_fake_quant.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/freeze_value_without_calib.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_redundant_dequantize.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_conv_requantize.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_redundant_dequantize.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/fuse_matmul_requantize.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/meta_op_optimizer.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_hostconst_converter.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/post_quantized_op_cse.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/rnn_convert.py
neural_compressor/adaptor/tf_utils/graph_rewriter/int8/scale_propagation.py
neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/__init__.py
neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_graph.py
neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_node.py
neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/onnx_schema.py
neural_compressor/adaptor/tf_utils/graph_rewriter/onnx/tf2onnx_utils.py
neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/__init__.py
neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/insert_qdq_pattern.py
neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/merge_duplicated_qdq.py
neural_compressor/adaptor/tf_utils/graph_rewriter/qdq/share_qdq_y_pattern.py
neural_compressor/adaptor/tf_utils/quantize_graph/__init__.py
neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_base.py
neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_bn.py
neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_concatv2.py
neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_conv.py
neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_for_intel_cpu.py
neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_matmul.py
neural_compressor/adaptor/tf_utils/quantize_graph/quantize_graph_pooling.py
neural_compressor/adaptor/tf_utils/quantize_graph/qat/__init__.py
neural_compressor/adaptor/tf_utils/quantize_graph/qat/fake_quantize.py
neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_config.py
neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_helper.py
neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_wrapper.py
neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/__init__.py
neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/optimize_layer.py
neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_add.py
neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_base.py
neural_compressor/adaptor/tf_utils/quantize_graph/qat/quantize_layers/quantize_layer_bn.py
neural_compressor/adaptor/tf_utils/quantize_graph/qdq/__init__.py
neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_bn.py
neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_concatv2.py
neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_conv.py
neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_deconv.py
neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_in.py
neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_matmul.py
neural_compressor/adaptor/tf_utils/quantize_graph/qdq/fuse_qdq_pooling.py
neural_compressor/adaptor/tf_utils/quantize_graph/qdq/optimize_qdq.py
neural_compressor/adaptor/tf_utils/transform_graph/__init__.py
neural_compressor/adaptor/tf_utils/transform_graph/bias_correction.py
neural_compressor/adaptor/tf_utils/transform_graph/graph_transform_base.py
neural_compressor/adaptor/tf_utils/transform_graph/insert_logging.py
neural_compressor/adaptor/tf_utils/transform_graph/rerange_quantized_concat.py
neural_compressor/adaptor/torch_utils/__init__.py
neural_compressor/adaptor/torch_utils/auto_round.py
neural_compressor/adaptor/torch_utils/awq.py
neural_compressor/adaptor/torch_utils/bf16_convert.py
neural_compressor/adaptor/torch_utils/gptq.py
neural_compressor/adaptor/torch_utils/hawq_metric.py
neural_compressor/adaptor/torch_utils/mixed_precision.py
neural_compressor/adaptor/torch_utils/model_wrapper.py
neural_compressor/adaptor/torch_utils/pattern_detector.py
neural_compressor/adaptor/torch_utils/symbolic_trace.py
neural_compressor/adaptor/torch_utils/teq.py
neural_compressor/adaptor/torch_utils/util.py
neural_compressor/adaptor/torch_utils/weight_only.py
neural_compressor/adaptor/torch_utils/layer_wise_quant/__init__.py
neural_compressor/adaptor/torch_utils/layer_wise_quant/modified_pickle.py
neural_compressor/adaptor/torch_utils/layer_wise_quant/quantize.py
neural_compressor/adaptor/torch_utils/layer_wise_quant/torch_load.py
neural_compressor/adaptor/torch_utils/layer_wise_quant/utils.py
neural_compressor/adaptor/torch_utils/waq/__init__.py
neural_compressor/adaptor/torch_utils/waq/auto_alpha.py
neural_compressor/adaptor/torch_utils/waq/calibration.py
neural_compressor/adaptor/torch_utils/waq/graph_trace.py
neural_compressor/adaptor/torch_utils/waq/smooth_quant.py
neural_compressor/adaptor/torch_utils/waq/utils.py
neural_compressor/algorithm/__init__.py
neural_compressor/algorithm/algorithm.py
neural_compressor/algorithm/fast_bias_correction.py
neural_compressor/algorithm/smooth_quant.py
neural_compressor/algorithm/weight_correction.py
neural_compressor/common/__init__.py
neural_compressor/common/base_config.py
neural_compressor/common/base_tuning.py
neural_compressor/common/benchmark.py
neural_compressor/common/tuning_param.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/compression/__init__.py
neural_compressor/compression/callbacks.py
neural_compressor/compression/distillation/__init__.py
neural_compressor/compression/distillation/criterions.py
neural_compressor/compression/distillation/optimizers.py
neural_compressor/compression/distillation/utility.py
neural_compressor/compression/hpo/__init__.py
neural_compressor/compression/hpo/sa_optimizer.py
neural_compressor/compression/hpo/search_algorithms.py
neural_compressor/compression/hpo/search_space.py
neural_compressor/compression/pruner/__init__.py
neural_compressor/compression/pruner/criteria.py
neural_compressor/compression/pruner/dsnot.py
neural_compressor/compression/pruner/pruning.py
neural_compressor/compression/pruner/regs.py
neural_compressor/compression/pruner/schedulers.py
neural_compressor/compression/pruner/tf_criteria.py
neural_compressor/compression/pruner/utils.py
neural_compressor/compression/pruner/model_slim/__init__.py
neural_compressor/compression/pruner/model_slim/auto_slim.py
neural_compressor/compression/pruner/model_slim/pattern_analyzer.py
neural_compressor/compression/pruner/model_slim/weight_slim.py
neural_compressor/compression/pruner/patterns/__init__.py
neural_compressor/compression/pruner/patterns/base.py
neural_compressor/compression/pruner/patterns/mha.py
neural_compressor/compression/pruner/patterns/ninm.py
neural_compressor/compression/pruner/patterns/nxm.py
neural_compressor/compression/pruner/pruners/__init__.py
neural_compressor/compression/pruner/pruners/base.py
neural_compressor/compression/pruner/pruners/basic.py
neural_compressor/compression/pruner/pruners/block_mask.py
neural_compressor/compression/pruner/pruners/mha.py
neural_compressor/compression/pruner/pruners/pattern_lock.py
neural_compressor/compression/pruner/pruners/progressive.py
neural_compressor/compression/pruner/pruners/retrain_free.py
neural_compressor/compression/pruner/pruners/sparse_gpt.py
neural_compressor/compression/pruner/wanda/__init__.py
neural_compressor/compression/pruner/wanda/prune.py
neural_compressor/compression/pruner/wanda/utils.py
neural_compressor/compression/pruner/wanda/wrapper.py
neural_compressor/contrib/__init__.py
neural_compressor/contrib/strategy/__init__.py
neural_compressor/contrib/strategy/sigopt.py
neural_compressor/contrib/strategy/tpe.py
neural_compressor/data/__init__.py
neural_compressor/data/dataloaders/__init__.py
neural_compressor/data/dataloaders/base_dataloader.py
neural_compressor/data/dataloaders/dataloader.py
neural_compressor/data/dataloaders/default_dataloader.py
neural_compressor/data/dataloaders/fetcher.py
neural_compressor/data/dataloaders/mxnet_dataloader.py
neural_compressor/data/dataloaders/onnxrt_dataloader.py
neural_compressor/data/dataloaders/pytorch_dataloader.py
neural_compressor/data/dataloaders/sampler.py
neural_compressor/data/dataloaders/tensorflow_dataloader.py
neural_compressor/data/datasets/__init__.py
neural_compressor/data/datasets/bert_dataset.py
neural_compressor/data/datasets/coco_dataset.py
neural_compressor/data/datasets/dataset.py
neural_compressor/data/datasets/dummy_dataset.py
neural_compressor/data/datasets/dummy_dataset_v2.py
neural_compressor/data/datasets/imagenet_dataset.py
neural_compressor/data/datasets/style_transfer_dataset.py
neural_compressor/data/filters/__init__.py
neural_compressor/data/filters/coco_filter.py
neural_compressor/data/filters/filter.py
neural_compressor/data/transforms/__init__.py
neural_compressor/data/transforms/coco_transform.py
neural_compressor/data/transforms/imagenet_transform.py
neural_compressor/data/transforms/postprocess.py
neural_compressor/data/transforms/tokenization.py
neural_compressor/data/transforms/transform.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/metric/__init__.py
neural_compressor/metric/bleu.py
neural_compressor/metric/bleu_util.py
neural_compressor/metric/coco_label_map.py
neural_compressor/metric/coco_tools.py
neural_compressor/metric/evaluate_squad.py
neural_compressor/metric/f1.py
neural_compressor/metric/metric.py
neural_compressor/model/__init__.py
neural_compressor/model/base_model.py
neural_compressor/model/keras_model.py
neural_compressor/model/model.py
neural_compressor/model/mxnet_model.py
neural_compressor/model/nets_factory.py
neural_compressor/model/onnx_model.py
neural_compressor/model/tensorflow_model.py
neural_compressor/model/torch_model.py
neural_compressor/profiling/__init__.py
neural_compressor/profiling/parser/__init__.py
neural_compressor/profiling/parser/factory.py
neural_compressor/profiling/parser/parser.py
neural_compressor/profiling/parser/result.py
neural_compressor/profiling/parser/onnx_parser/__init__.py
neural_compressor/profiling/parser/onnx_parser/factory.py
neural_compressor/profiling/parser/onnx_parser/parser.py
neural_compressor/profiling/parser/tensorflow_parser/__init__.py
neural_compressor/profiling/parser/tensorflow_parser/factory.py
neural_compressor/profiling/parser/tensorflow_parser/parser.py
neural_compressor/profiling/profiler/__init__.py
neural_compressor/profiling/profiler/factory.py
neural_compressor/profiling/profiler/profiler.py
neural_compressor/profiling/profiler/onnxrt_profiler/__init__.py
neural_compressor/profiling/profiler/onnxrt_profiler/factory.py
neural_compressor/profiling/profiler/onnxrt_profiler/profiler.py
neural_compressor/profiling/profiler/onnxrt_profiler/utils.py
neural_compressor/profiling/profiler/tensorflow_profiler/__init__.py
neural_compressor/profiling/profiler/tensorflow_profiler/factory.py
neural_compressor/profiling/profiler/tensorflow_profiler/profiler.py
neural_compressor/profiling/profiler/tensorflow_profiler/utils.py
neural_compressor/strategy/__init__.py
neural_compressor/strategy/auto.py
neural_compressor/strategy/auto_mixed_precision.py
neural_compressor/strategy/basic.py
neural_compressor/strategy/bayesian.py
neural_compressor/strategy/conservative.py
neural_compressor/strategy/exhaustive.py
neural_compressor/strategy/hawq_v2.py
neural_compressor/strategy/mse.py
neural_compressor/strategy/mse_v2.py
neural_compressor/strategy/random.py
neural_compressor/strategy/strategy.py
neural_compressor/strategy/utils/__init__.py
neural_compressor/strategy/utils/constant.py
neural_compressor/strategy/utils/tuning_sampler.py
neural_compressor/strategy/utils/tuning_space.py
neural_compressor/strategy/utils/tuning_structs.py
neural_compressor/strategy/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/fp8_quant/__init__.py
neural_compressor/torch/algorithms/fp8_quant/common.py
neural_compressor/torch/algorithms/fp8_quant/fp8_quant.py
neural_compressor/torch/algorithms/fp8_quant/helper_modules.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/fp_utils.py
neural_compressor/torch/algorithms/fp8_quant/_core/measure.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/scale_methods/__init__.py
neural_compressor/torch/algorithms/fp8_quant/_core/scale_methods/max_abs.py
neural_compressor/torch/algorithms/fp8_quant/_core/scale_methods/single_scale.py
neural_compressor/torch/algorithms/fp8_quant/_core/scale_methods/smooth_quant.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/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/fix_measurements.py
neural_compressor/torch/algorithms/fp8_quant/scripts/regression_detection/__init__.py
neural_compressor/torch/algorithms/fp8_quant/scripts/regression_detection/regression_detection.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/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/save_load.py
neural_compressor/torch/algorithms/pt2e_quant/utility.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/autoround.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/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/load_entry.py
neural_compressor/torch/quantization/quantize.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/constants.py
neural_compressor/torch/utils/environ.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
neural_compressor/utils/__init__.py
neural_compressor/utils/collect_layer_histogram.py
neural_compressor/utils/constant.py
neural_compressor/utils/create_obj_from_config.py
neural_compressor/utils/kl_divergence.py
neural_compressor/utils/load_huggingface.py
neural_compressor/utils/logger.py
neural_compressor/utils/options.py
neural_compressor/utils/pytorch.py
neural_compressor/utils/utility.py
neural_compressor/utils/weights_details.py
neural_compressor/utils/export/__init__.py
neural_compressor/utils/export/qlinear2qdq.py
neural_compressor/utils/export/tf2onnx.py
neural_compressor/utils/export/torch2onnx.py