:orphan:

:py:mod:`neural_compressor.onnxrt.algorithms.layer_wise.core`
=============================================================

.. py:module:: neural_compressor.onnxrt.algorithms.layer_wise.core


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


Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.onnxrt.algorithms.layer_wise.core.layer_wise_quant



.. py:function:: layer_wise_quant(model: Union[onnx.ModelProto, neural_compressor.onnxrt.utils.onnx_model.ONNXModel, pathlib.Path, str], quant_func: Callable, weight_config: dict, data_reader: neural_compressor.onnxrt.quantization.calibrate.CalibrationDataReader = None, *args, **kwargs) -> neural_compressor.onnxrt.utils.onnx_model.ONNXModel

   Quantize model layer by layer to save memory.

   :param model: onnx model.
   :type model: Union[onnx.ModelProto, ONNXModel, Path, str]
   :param quant_func: quantization algo function.
   :type quant_func: Callable
   :param weight_config: quantization config.
   :type weight_config: dict
   :param data_reader: data_reader for calibration. Defaults to None.
   :type data_reader: CalibrationDataReader, optional

   :returns: _description_
   :rtype: _type_