:py:mod:`neural_compressor.adaptor.tf_utils.smooth_quant_scaler`
================================================================

.. py:module:: neural_compressor.adaptor.tf_utils.smooth_quant_scaler

.. autoapi-nested-parse::

   Tensorflow scaling model weights and activations for Smooth Quantization.



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

Classes
~~~~~~~

.. autoapisummary::

   neural_compressor.adaptor.tf_utils.smooth_quant_scaler.SmoothQuantScaler
   neural_compressor.adaptor.tf_utils.smooth_quant_scaler.SmoothQuantScalerLLM




.. py:class:: SmoothQuantScaler(model, dataloader, alpha, scales_per_op)


   A class for scaling model weights using Smooth Quantization method.

   :param model: Tensorflow model to be scaled
   :param dataloader: Tensorflow dataloader for the dataset
   :param alpha: float, the scaling factor
   :param scales_per_op: bool, each op will have an individual scale or
                         ops with the same input will share a scale


.. py:class:: SmoothQuantScalerLLM(graph_def, alpha, scales_per_op, op_types)




   A class for scaling model weights for TF LLM models using Smooth Quantization method.

   :param graph_def: graph_def of the model to be scaled
   :param alpha: float, the scaling factor
   :param scales_per_op: bool, each op will have an individual scale or
                         ops with the same input will share a scale
   :param op_types: