Public
  1. Public

onnxruntime

Public

Commits

David FanGitHub
02dc270242c
David Fan authored and GitHub committed 5803a1465af
Exclude node quantization in RTN (#23683)

### Description
Exclude node quantization in RTN



### Motivation and Context
We want to do mixed quantization. Tested locally with success.
I originally submitted a PR
https://github.com/intel/neural-compressor/pull/2114
But they suggested me to add `nodes_to_exclude` into `weight_config`
when we call the API