John Paul comments

Repositories
Issues
Comments

Results 4 comments of


                                            John Paul

[QNN-EP] Add MatMulNBits translation for GPU

@edgchen1 Please holdoff on merging this pull request. There might be an issue with this change.

[QNN-EP] Add MatMulNBits translation for GPU

We are seeing NaN outputs for Qwen and DeepSeek 1.5B using MatmulNBits that was triaged to this change.

[QNN-EP] Add MatMulNBits translation for GPU

> > We are seeing NaN outputs for Qwen and DeepSeek 1.5B using MatmulNBits that was triaged to this change. > > The NaN issue is identified and fixed from...

[QNN-EP] Add MatMulNBits translation for GPU

> @edgchen1 Please holdoff on merging this pull request. There might be an issue with this change. @edgchen1 Thanks for holding off. This issue is verified as fixed with QNN...