:py:mod:`neural_compressor.torch.algorithms.weight_only.modules`
================================================================

.. py:module:: neural_compressor.torch.algorithms.weight_only.modules

.. autoapi-nested-parse::

   Torch.nn.Module Class Definition.



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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.torch.algorithms.weight_only.modules.FakeAffineTensorQuantFunction
   neural_compressor.torch.algorithms.weight_only.modules.TEQLinearFakeQuant
   neural_compressor.torch.algorithms.weight_only.modules.MulLinear




.. py:class:: FakeAffineTensorQuantFunction




   Fake version of affine quantization.


.. py:class:: TEQLinearFakeQuant(orig_layer, alpha=None, num_bits=4, group_size=-1, scheme='asym')




   Wrapper quantization linear.


.. py:class:: MulLinear(module, input_scale=None)




   Linear wrapper to apply scale to input.