:orphan:

:py:mod:`neural_compressor.adaptor.torch_utils.awq`
===================================================

.. py:module:: neural_compressor.adaptor.torch_utils.awq


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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.adaptor.torch_utils.awq.ActAwareWeightQuant




.. py:class:: ActAwareWeightQuant(model, example_inputs=None, calib_func=None, dataloader=None, n_samples=128, data_type='int', bits=4, group_size=32, scheme='asym', enable_full_range=False, weight_config={})


   Implementation of Activation-aware Weight quantization (AWQ) algo.