Skip to content

[QNN EP] Fix 16x16 Conv translation #24729

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 2 commits into from
May 20, 2025
Merged

[QNN EP] Fix 16x16 Conv translation #24729

merged 2 commits into from
May 20, 2025

Conversation

quic-tirupath
Copy link
Contributor

  • QNN's 16x16 Conv doesn't support asymmetric int16 weight
  • Insert Convert Op to convert from asymmetric uint16 weight to symmetric int16 weight

Description

  • QNN' Conv op doesn't support asymmetric INT16 weights.
  • 16x16 Conv operators in ONNX models fallback to CPU execution provider and reporting higher inference times.
  • Insert a Convert Op to convert asymmetric uint16 weight to symmetric int16 weight to schedule 16x16 Conv's on QNN EP provider.

Motivation and Context

  • This fixes Graph execution failures for models contain 16x16 Conv op on QNN Execution provider
  • This also improves Inference times of model contain 16x16 Conv op

@quic-tirupath
[QNN EP] Fix 16x16 Conv translation
d784030 
 - QNN's 16x16 Conv doesn't support asymmetric int16 weight
 - Insert Convert Op to convert from asymmetric uint16 weight
   to symmetric int16 weight
@quic-tirupath
Copy link
Contributor Author

This commit should not impact WebGPU builds. Can someone help to re-trigger the checks?

@HectorSVC HectorSVC added the ep:QNN issues related to QNN exeution provider label May 13, 2025
@HectorSVC
Copy link
Contributor

/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows x64 QNN CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 5 pipeline(s).

@quic-tirupath
[QNN EP] Disable conv 16x16 unit tests for linux platforms
c3bc4e9 
 - Conv 16x16 is supported on few hardwares
 - Disable Conv 16x16 unit tests for linux platforms
@HectorSVC
Copy link
Contributor

/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows x64 QNN CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 5 pipeline(s).

HectorSVC
HectorSVC approved these changes May 20, 2025
View reviewed changes
Copy link
Contributor

@HectorSVC HectorSVC left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

:shipit:

@HectorSVC HectorSVC merged commit adb05e4 into microsoft:main May 20, 2025
81 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@HectorSVC HectorSVC

Assignees
No one assigned
Labels
ep:QNN issues related to QNN exeution provider
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@quic-tirupath @HectorSVC