Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[QNN EP] Apply workaround for Conv validation bug when bias input is implicit #21764

Merged
merged 5 commits into from
Aug 22, 2024

Conversation

adrianlizarraga
Copy link
Contributor

@adrianlizarraga adrianlizarraga commented Aug 16, 2024

Description

  • Adds a dummy bias of all zeros when translating a Conv without an explicit bias input. This is a workaround for a QNN validation issue that fails when the optional bias input is not provided.
  • Corrects logic for unpacking of non-zero int4 zero-points. Bug does not impact models because we currently only support int4 zero-points equal to 0 (symmetric quant). But this would become an issue in the future if/when QNN supports non-zero int4 zero-points (so good to fix now).

Motivation and Context

Support Conv operators without a bias input on QNN EP with the latest QNN SDK.

@adrianlizarraga adrianlizarraga added the ep:QNN issues related to QNN exeution provider label Aug 16, 2024
@adrianlizarraga adrianlizarraga marked this pull request as ready for review August 20, 2024 00:40
@adrianlizarraga adrianlizarraga merged commit 514b469 into main Aug 22, 2024
95 of 97 checks passed
@adrianlizarraga adrianlizarraga deleted the adrianl/qnn_conv_validation_workaround branch August 22, 2024 17:38
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ep:QNN issues related to QNN exeution provider
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants