:py:mod:`neural_compressor.experimental.strategy.utils.tuning_space`
====================================================================

.. py:module:: neural_compressor.experimental.strategy.utils.tuning_space

.. autoapi-nested-parse::

   Tuning space.



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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.experimental.strategy.utils.tuning_space.TuningItem
   neural_compressor.experimental.strategy.utils.tuning_space.TuningSpace



Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.experimental.strategy.utils.tuning_space.pattern_to_internal
   neural_compressor.experimental.strategy.utils.tuning_space.pattern_to_path
   neural_compressor.experimental.strategy.utils.tuning_space.quant_mode_from_pattern
   neural_compressor.experimental.strategy.utils.tuning_space.initial_tuning_cfg_with_quant_mode



.. py:class:: TuningItem(name, options=[], item_type=None)


   Not displayed in API Docs.


.. py:class:: TuningSpace(capability, conf, framework=None)


   Not displayed in API Docs.

   1) capability -> internal format -> merge -> tuning space (tree)


.. py:function:: pattern_to_internal(pattern, default_dtype='int8')

   Convert pattern to internal format.

   'static' -> ('static', (('int8'),('int8')))
   'dynamic' -> ('dynamic', (('int8'),('int8')))
   'fp32' -> ('precision', (('fp32'), ('fp32')))
   'bf16' -> ('precision', (('bf16'), ('bf16')))
   ('static', 'int8') -> ('static', (('int8'),('int8')))
   ('dynamic', 'int8') -> ('dynamic', (('int8'),('int8')))
   ('precision', 'fp32') -> ('precision', (('fp32'), ('fp32')))) # (('fp32'), ('fp32')) or ('fp32', 'fp32')
   #TODO to add the support for mixed data type of weight and activation


.. py:function:: pattern_to_path(pattern)

   Convert pattern to path.


.. py:function:: quant_mode_from_pattern(internal_pattern)

   Get quant mode from internal pattern.


.. py:function:: initial_tuning_cfg_with_quant_mode(op_name_type, quant_mode, tuning_space: TuningSpace) -> neural_compressor.experimental.strategy.utils.tuning_structs.OpTuningConfig

   Initialize the tuning cfg.

   :param op_name_type: (op name, op type)
   :param quant_mode: dynamic/static/fp32/bf16/fp16
   :param tuning_space: tuning space.

   step1, convert the quant_mode into internal format.
   step2, complete the path based.
   step3, get the mode item.
   step4, use the first option as value for method.
   step5, create the op tuning config.

   :returns: The initial tuning config.