Public
  1. Public

onnxruntime

Public

Commits

Adrian LizarragaGitHub
8540ac4f78b
Adrian Lizarraga authored and GitHub committed 4b8f6dcbb69
[QNN EP] Improve INT4 accuracy (#21582)

### Description
Masks off top 4-bits of INT4 weights, improving accuracy.



### Motivation and Context
This is a workaround as the QNN docs state masking is not required.