:orphan:

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

.. py:module:: neural_compressor.adaptor.torch_utils.teq


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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.adaptor.torch_utils.teq.TEQuantizer




.. py:class:: TEQuantizer(model, weight_config={}, absorb_to_layer={}, extra_config={}, example_inputs=None)


   Weight-only quantization, Trainable Equivalent Transformation (TEQ): linear wrapper to apply scale to input.