Public
  1. Public

onnxruntime

Public

Commits

Adrian LizarragaGitHub
0b7048e7d62
Adrian Lizarraga authored and GitHub committed 8d5ecc4dae0
[Quantization] Fix scale/zero-point for 16-bit QDQ Softmax (#18589)

### Description
Sets the appropriate scale and zero-point values for 16-bit QDQ Softmax.
Previously, the scale/zp were set to fixed values that were specific to 8-bit quantization.

### Motivation and Context
Generate more accurate 16-bit QDQ models that contain Softmax.