neural_compressor.torch.quantization.modules
============================================

.. py:module:: neural_compressor.torch.quantization.modules

.. autoapi-nested-parse::

   Torch.nn.Module Class Definition.



Classes
-------

.. autoapisummary::

   neural_compressor.torch.quantization.modules.FakeAffineTensorQuantFunction
   neural_compressor.torch.quantization.modules.TEQLinearFakeQuant
   neural_compressor.torch.quantization.modules.MulLinear


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

.. 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.