:orphan:

:py:mod:`neural_compressor.torch.quantization.algorithm_entry`
==============================================================

.. py:module:: neural_compressor.torch.quantization.algorithm_entry


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


Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.torch.quantization.algorithm_entry.rtn_entry



.. py:function:: rtn_entry(model: torch.nn.Module, configs_mapping: Dict[Tuple[str, callable], neural_compressor.torch.quantization.RTNConfig], mode: neural_compressor.common.utils.Mode = Mode.QUANTIZE, *args, **kwargs) -> torch.nn.Module

   The main entry to apply rtn quantization.