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] Re-enable several disabled QNN-EP UTs #23799

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

kuanyul-quic
Copy link

Description

  1. Re-enable UTs which passed 2.30
  2. Fix conv and resize UTs
    • Make conv's weight as initializer to let graph.NumberOfNodes() match ep_nodes, which should be 1.
    • Update resize UT because "round_prefer_floor" is no longer supported in QNN SDK since 2.21.

Motivation and Context

  1. Make the UT of QNN EP pass as much as possible to improve the test coverage.

### Description
1. Re-enable UTs which passed 2.30
2. Fix conv and resize UTs
   - Make conv's weight as initializer to let graph.NumberOfNodes()
     match ep_nodes, which should be 1.
   - Update resize UT because "round_prefer_floor" is no longer
     supported in QNN SDK since 2.21.

### Motivation and Context
1. Make the UT of QNN EP pass as much as possible to improve the test
   coverage.
@kuanyul-quic
Copy link
Author

@microsoft-github-policy-service agree company="Qualcomm"

TestInputDef<float> input_def({1, 2, 5, 5}, false, GetFloatDataInRange(-10.0f, 10.0f, 50));
TestInputDef<float> weight_def({1, 2, 3, 3}, false, GetFloatDataInRange(-1.0f, 5.0f, 18));
TestInputDef<float> weight_def({1, 2, 3, 3}, true, GetFloatDataInRange(-1.0f, 5.0f, 18));
Copy link
Contributor

Choose a reason for hiding this comment

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

Does that mean for some Conv case, the weight has to be static? Should we identify such cases and do the validation in ConvOpBuilder in QNN EP to place these nodes on CPU EP instead of QNN EP?

@HectorSVC
Copy link
Contributor

/azp run Linux QNN CI Pipeline,Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Linux Android Emulator QNN CI Pipeline

@HectorSVC HectorSVC added the ep:QNN issues related to QNN exeution provider label Feb 24, 2025
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