Skip to content

Cadence: Register missing portable ops (neg, exp, native_layer_norm)#18745

Merged
meta-codesync[bot] merged 1 commit intomainfrom
op-test-fixes
Apr 7, 2026
Merged

Cadence: Register missing portable ops (neg, exp, native_layer_norm)#18745
meta-codesync[bot] merged 1 commit intomainfrom
op-test-fixes

Conversation

@aliafzal
Copy link
Copy Markdown
Contributor

@aliafzal aliafzal commented Apr 7, 2026

Summary

  • Register neg.out, exp.out, and native_layer_norm.out in the cadence backend by adding them to functions.yaml, functions_hifi.yaml, and the corresponding CMakeLists.txt files
  • Remove invalid run_and_compare=False workaround from test_add_op.py
  • All 357 operator tests under examples/cadence/operators/ now pass

Test plan

  • Ran python -m pytest examples/cadence/operators/ -n auto — 357 passed

cc @mcremon-meta

These three operators had portable kernel implementations but were not
registered or compiled in the cadence backend, causing runtime failures
in operator tests. Also removes the invalid run_and_compare=False
workaround from test_add_op.py.
@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Apr 7, 2026

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18745

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

⏳ 1 Pending, 2 Unrelated Failures

As of commit 984bdf3 with merge base bd99b2a (image):

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

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

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

@meta-cla meta-cla Bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Apr 7, 2026
@github-actions
Copy link
Copy Markdown

github-actions Bot commented Apr 7, 2026

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.

@aliafzal aliafzal requested review from mcremon-meta and zonglinpeng and removed request for kirklandsign and larryliu0820 April 7, 2026 18:27
@meta-codesync
Copy link
Copy Markdown
Contributor

meta-codesync Bot commented Apr 7, 2026

@aliafzal has imported this pull request. If you are a Meta employee, you can view this in D99870895.

@aliafzal aliafzal requested a review from abeakkas April 7, 2026 18:35
@aliafzal aliafzal added the module: cadence Issues related to the Cadence/Xtensa backend label Apr 7, 2026
@meta-codesync meta-codesync Bot merged commit cd1f005 into main Apr 7, 2026
170 of 180 checks passed
@meta-codesync meta-codesync Bot deleted the op-test-fixes branch April 7, 2026 21:29
jpiat pushed a commit to jpiat/executorch that referenced this pull request Apr 14, 2026
Differential Revision: D99870895

Pull Request resolved: pytorch#18745
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. module: cadence Issues related to the Cadence/Xtensa backend

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants