:orphan:

:py:mod:`neural_compressor.onnxrt.quantization.algorithm_entry`
===============================================================

.. py:module:: neural_compressor.onnxrt.quantization.algorithm_entry


Module Contents
---------------


Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.onnxrt.quantization.algorithm_entry.smooth_quant_entry
   neural_compressor.onnxrt.quantization.algorithm_entry.rtn_quantize_entry
   neural_compressor.onnxrt.quantization.algorithm_entry.gptq_quantize_entry
   neural_compressor.onnxrt.quantization.algorithm_entry.awq_quantize_entry



.. py:function:: smooth_quant_entry(model: Union[pathlib.Path, str], quant_config: neural_compressor.onnxrt.quantization.config.SmoohQuantConfig, calibration_data_reader: neural_compressor.onnxrt.quantization.calibrate.CalibrationDataReader, *args, **kwargs) -> onnx.ModelProto

   Apply smooth quant.


.. py:function:: rtn_quantize_entry(model: Union[pathlib.Path, str], quant_config: neural_compressor.onnxrt.quantization.config.RTNConfig, *args, **kwargs) -> onnx.ModelProto

   The main entry to apply rtn quantization.


.. py:function:: gptq_quantize_entry(model: Union[pathlib.Path, str], quant_config: neural_compressor.onnxrt.quantization.config.GPTQConfig, calibration_data_reader: neural_compressor.onnxrt.quantization.calibrate.CalibrationDataReader, *args, **kwargs) -> onnx.ModelProto

   The main entry to apply gptq quantization.


.. py:function:: awq_quantize_entry(model: Union[pathlib.Path, str], quant_config: neural_compressor.onnxrt.quantization.config.AWQConfig, calibration_data_reader: neural_compressor.onnxrt.quantization.calibrate.CalibrationDataReader, *args, **kwargs) -> onnx.ModelProto

   The main entry to apply awq quantization.