-
Notifications
You must be signed in to change notification settings - Fork 689
Qualcomm AI Engine Direct - Suite Operator Test Support (Part1) #14618
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
Qualcomm AI Engine Direct - Suite Operator Test Support (Part1) #14618
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14618
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 5 New FailuresAs of commit d6c6a28 with merge base 5fd66ee ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
Support Conv3d and TransposeConv3d
1438a9f
to
d6c6a28
Compare
Hi @cccclai,
![]() |
@GregoryComer can you share the steps? |
@winskuo-quic from the latest run, it seems the number improves https://github.com/pytorch/executorch/actions/runs/18053810243 |
1 similar comment
@winskuo-quic from the latest run, it seems the number improves https://github.com/pytorch/executorch/actions/runs/18053810243 |
@pytorchbot cherry-pick --onto release/1.0 -c regression |
### Summary - Support Add/Sub with alpha values - Support Conv3d - Support TransposeConv3d ### Test plan UT added (cherry picked from commit dcc3978)
Cherry picking #14618The cherry pick PR is at #14742 and it is recommended to link a regression cherry pick PR with an issue. The following tracker issues are updated: Details for Dev Infra teamRaised by workflow job |
Thanks for the fixes! I updated the README here with some more repro examples: https://github.com/pytorch/executorch/blob/main/backends/test/suite/README.md. I've also updated to use pytest, which should make it easier to run the tests. Regarding skips on conv3d, that's effectively a pass. What's happening is that the operator or model has an undelegated conv3d, which we don't have a portable implementation for. If nothing is delegated, it gets considered a pass, as the backend worked as intended. If it's partially delegated and has missing portable ops, it's considered skipped as it can't test the model. But, from the backend perspective, it's passing. I should maybe just update the test logic to mark as pass instead of skip for this case. |
@GregoryComer yes let's do that |
Summary
Test plan
UT added