neural_compressor.compression.pruner.pruners
============================================

.. py:module:: neural_compressor.compression.pruner.pruners

.. autoapi-nested-parse::

   Pruning patterns.



Submodules
----------

.. toctree::
   :maxdepth: 1

   /autoapi/neural_compressor/compression/pruner/pruners/base/index
   /autoapi/neural_compressor/compression/pruner/pruners/basic/index
   /autoapi/neural_compressor/compression/pruner/pruners/block_mask/index
   /autoapi/neural_compressor/compression/pruner/pruners/mha/index
   /autoapi/neural_compressor/compression/pruner/pruners/pattern_lock/index
   /autoapi/neural_compressor/compression/pruner/pruners/progressive/index
   /autoapi/neural_compressor/compression/pruner/pruners/retrain_free/index


Functions
---------

.. autoapisummary::

   neural_compressor.compression.pruner.pruners.parse_valid_pruner_types
   neural_compressor.compression.pruner.pruners.get_pruner


Package Contents
----------------

.. py:function:: parse_valid_pruner_types()

   Get all valid pruner names.


.. py:function:: get_pruner(config, modules, framework='pytorch')

   Get registered pruner class.

   Get a Pruner object from PRUNERS.

   :param modules: A dict {"module_name": Tensor} that stores the pruning modules' weights.
   :param config: A config dict object that contains the pruner information.

   :returns: A Pruner object.

   Raises: AssertionError: Currently only support pruners that have been registered in PRUNERS.