:orphan:

:py:mod:`neural_compressor.common.base_config`
==============================================

.. py:module:: neural_compressor.common.base_config


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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.common.base_config.ConfigRegistry
   neural_compressor.common.base_config.BaseConfig
   neural_compressor.common.base_config.ComposableConfig



Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.common.base_config.register_config
   neural_compressor.common.base_config.get_all_config_set_from_config_registry
   neural_compressor.common.base_config.register_supported_configs_for_fwk



Attributes
~~~~~~~~~~

.. autoapisummary::

   neural_compressor.common.base_config.options



.. py:function:: register_config(framework_name: str, algo_name: str, priority: Union[float, int] = 0)

   Register config decorator.

   The register the configuration classes for different algorithms within specific frameworks.

   Usage example:
       @register_config(framework_name=FRAMEWORK_NAME, algo_name=ExampleAlgorithm, priority=100)
       class ExampleAlgorithmConfig:
           # Configuration details for the ExampleAlgorithm

   :param framework_name: the framework name.
   :param algo_name: the algorithm name.
   :param priority: the priority of the configuration. A larger number indicates a higher priority,
                    which will be tried first at the auto-tune stage. Defaults to 0.


.. py:class:: BaseConfig(white_list: Optional[List[neural_compressor.common.utils.OP_NAME_OR_MODULE_TYPE]] = DEFAULT_WHITE_LIST)




   The base config for all algorithm configs.


.. py:class:: ComposableConfig(configs: List[BaseConfig])




   The base config for all algorithm configs.



.. py:function:: register_supported_configs_for_fwk(fwk_name: str)

   Register supported configs for specific framework.

   :param fwk_name: the framework name.