Include stories with qnn in benchinfra

[guangy10]

No description provided.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/4995

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

✅ You can merge normally! (1 Unrelated Failure)

As of commit 0fd2529 with merge base ff4a736 ():

FLAKY - The following job failed but was likely due to flakiness present on trunk:

• android-perf / benchmark-on-device (stories110M, qnn, arn:aws:devicefarm:us-west-2:308535385114:devicepool:02a2c... / mobile-job (android) (gh) (detected as infra flaky with no log or failing log classifier)

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[guangy10]

Adding the tinyllama+QNN to the android-perf, the benchmark-on-device step fails with the following error:

[PyTorch] Marking the test suite as failed because it failed to load the model

@kirklandsign So I think the LlamaDemoApp we are currently using in the workflow doesn't build with QNN enabled? If yes, the failure is expected. Once we have the generic app, it should build with QNN enabled as well.

[facebook-github-bot]

@guangy10 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.