Qualcomm AI Engine Direct - HF LLM CI

[winskuo-quic]

Summary

[PLEASE REMOVE] See CONTRIBUTING.md's Pull Requests for ExecuTorch PR guidelines.

[PLEASE REMOVE] If this PR closes an issue, please add a Fixes #<issue-id> line.

[PLEASE REMOVE] If this PR introduces a fix or feature that should be the upcoming release notes, please add a "Release notes: " label. For a list of available release notes labels, check out CONTRIBUTING.md's Pull Requests.

Test plan

[PLEASE REMOVE] How did you test this PR? Please write down any manual commands you used and note down tests that you have written if applicable.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14433

• 📄 Preview Python docs built from this PR

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

❌ 3 New Failures, 1 Cancelled Job, 3 Unrelated Failures

As of commit 93f6d84 with merge base 7ce78c0 ():

NEW FAILURES - The following jobs have failed:

• pull / test-moshi-linux / linux-job (gh)
  test_mimi
• pull / test-samsung-models-linux / linux-job (gh)
  RuntimeError: Command docker exec -t ae0f2aa1074298abea13a0171cbd7868303b6fe9b17ceebae536cadf9f08042f /exec failed with exit code 1
• Test Metal Backend / export-voxtral-metal-artifact / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 2

CANCELLED JOB - The following job was cancelled. Please retry:

• Test CoreML Backend / test-coreml / test-backend-macos (coreml_static_int8, operators) / macos-job (gh)
  ##[error]The operation was canceled.

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

• trunk / unittest-release / linux / linux-job (gh) (matched linux rule in flaky-rules.json)
  The runner has received a shutdown signal. This can happen when the runner service is stopped, or a manually started runner is canceled.

BROKEN TRUNK - The following jobs failed but was present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• pull / unittest / linux / linux-job (gh) (trunk failure)
• pull / unittest-editable / linux / linux-job (gh) (trunk failure)

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

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[winskuo-quic]

Hi @cccclai,
This is the PR to enable LLM Decoder CI, please notice that we are using x86 emulator for QNN execution. Therefore, I am guessing it will take at least 8-10 hours to finish, so I think it will be better to place it under nightly.
This PR is still WIP and I will let you know when it is ready.
Thanks

[winskuo-quic]

Hi @cccclai,
This PR is to support community CI to eval PPL scores for static HF decoder models.
I have chosen the smallest HF decoder model for ppl evaluation.
The total time to taken to finish execution is about 5.5 hours.
I would like to confirm on the following:

1. Is this taking too long and we should move it to nightly.yml.
2. Is using linux.24xlarge to run CI a concern?

[cccclai]

Hi @cccclai, This is the PR to enable LLM Decoder CI, please notice that we are using x86 emulator for QNN execution. Therefore, I am guessing it will take at least 8-10 hours to finish, so I think it will be better to place it under nightly. This PR is still WIP and I will let you know when it is ready. Thanks

Thanks for adding CI, this is definately helpful and can help prevent regression early. Yeah nightly will be better, 8-10 hours are quite long. Will need to read which task you're trying.

[winskuo-quic]

Thanks for adding CI, this is definately helpful and can help prevent regression early. Yeah nightly will be better, 8-10 hours are quite long. Will need to read which task you're trying.

Sure. The total time actually takes about 5.5 hours to finish, but I have moved it to nightly.yml for now. Could you please help me trigger the nightly.yml test? Thanks

[cccclai]

Thanks for adding CI, this is definately helpful and can help prevent regression early. Yeah nightly will be better, 8-10 hours are quite long. Will need to read which task you're trying.

Sure. The total time actually takes about 5.5 hours to finish, but I have moved it to nightly.yml for now. Could you please help me trigger the nightly.yml test? Thanks

Yeah just trigger

[cccclai]

Thank you for adding the CI