neural_compressor.jax.quantization.quantize
===========================================

.. py:module:: neural_compressor.jax.quantization.quantize

.. autoapi-nested-parse::

   Intel Neural Compressor JAX quantization base API.



Functions
---------

.. autoapisummary::

   neural_compressor.jax.quantization.quantize.need_apply
   neural_compressor.jax.quantization.quantize.quantize_model


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

.. py:function:: need_apply(configs_mapping: Dict[Tuple[str, callable], neural_compressor.common.base_config.BaseConfig], algo_name)

   Determine whether a quantization algorithm should be applied.

   :param configs_mapping: Mapping of layer identifiers to configs.
   :type configs_mapping: Dict[Tuple[str, callable], BaseConfig]
   :param algo_name: Algorithm name to check.
   :type algo_name: str

   :returns: True if any config matches the algorithm name.
   :rtype: bool


.. py:function:: quantize_model(model: keras.Model, quant_config: neural_compressor.common.base_config.BaseConfig, calib_function: Callable = None, inplace: bool = True)

   Return a quantized Keras model according to the given configuration.

   :param model: FP32 Keras model to be quantized.
   :type model: keras.Model
   :param quant_config: Quantization configuration.
   :type quant_config: BaseConfig
   :param calib_function: Function used for model calibration, required for static quantization.
   :type calib_function: Callable, optional
   :param inplace: When True, the original model is modified in-place and should not be used afterward. A value of
                   False is not yet supported.
   :type inplace: bool

   :returns: The quantized model.
   :rtype: keras.Model