Introducing Google AI Edge Portal: Benchmark Edge AI at scale. Sign-up to request access during private preview.

TfLiteBlockwiseQuantization

#include <common.h>

Parameters for blockwise quantization across the output channels dimension.

Summary

For a particular value in quantized_dimension, quantized values can be converted back to float using: real_value = scale * (quantized_value - zero_point)

Public attributes
`blocksize`	`int32_t`
`quantized_dimension`	`int32_t`
`scale`	`int32_t`
`zero_point`	`int32_t`

Public attributes

blocksize

int32_t TfLiteBlockwiseQuantization::blocksize

quantized_dimension

int32_t TfLiteBlockwiseQuantization::quantized_dimension

scale

int32_t TfLiteBlockwiseQuantization::scale

zero_point

int32_t TfLiteBlockwiseQuantization::zero_point

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026-04-30 UTC.