:orphan:

:py:mod:`neural_compressor.torch.algorithms.smooth_quant.smooth_quant`
======================================================================

.. py:module:: neural_compressor.torch.algorithms.smooth_quant.smooth_quant


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


Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.torch.algorithms.smooth_quant.smooth_quant.smooth_quantize



.. py:function:: smooth_quantize(model, tune_cfg, run_fn, example_inputs, inplace=True)

   Execute the quantize process on the specified model.

   :param model: a float model to be quantized.
   :param tune_cfg: quantization config for ops.
   :param run_fn: a calibration function for calibrating the model.
   :param example_inputs: used to trace torch model.
   :param inplace: whether to carry out model transformations in-place.

   :returns: A quantized model.