Skip to content

Conversation

@GregoryComer
Copy link
Member

@GregoryComer GregoryComer commented Jan 16, 2026

Summary: Older versions of the XNNPACK library don't properly support fp16 GeLU. Disable partitioning until we pull in a newer version of XNNPACK (tracking in #16679).

Fixes #16672.

Differential Revision: D90899836

@pytorch-bot
Copy link

pytorch-bot bot commented Jan 16, 2026

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16680

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

❌ 1 New Failure

As of commit ebae7bd with merge base 8d29b22 (image):

NEW FAILURE - The following job has failed:

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 Jan 16, 2026
@meta-codesync
Copy link
Contributor

meta-codesync bot commented Jan 16, 2026

@GregoryComer has exported this pull request. If you are a Meta employee, you can view the originating Diff in D90899836.

@GregoryComer GregoryComer added the release notes: xnnpack Changes to the XNNPack backend delegate label Jan 16, 2026
Summary: Older versions of the XNNPACK library don't properly support fp16 GeLU. Disable partitioning until we pull in a newer version of XNNPACK (tracking in pytorch#16679).

Differential Revision: D90899836
@GregoryComer
Copy link
Member Author

Rebasing and re-running CI, since there is a bunch of noise. Will merge once green.

@meta-codesync
Copy link
Contributor

meta-codesync bot commented Jan 21, 2026

@GregoryComer has imported this pull request. If you are a Meta employee, you can view this in D90899836.

@GregoryComer GregoryComer merged commit becb25c into pytorch:main Jan 21, 2026
144 of 147 checks passed
NickJLange pushed a commit to NickJLange/executorch that referenced this pull request Jan 21, 2026
Summary: Older versions of the XNNPACK library don't properly support
fp16 GeLU. Disable partitioning until we pull in a newer version of
XNNPACK (tracking in pytorch#16679).

Fixes [pytorch#16672](pytorch#16672).

Differential Revision: D90899836
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. fb-exported meta-exported release notes: xnnpack Changes to the XNNPack backend delegate

Projects

None yet

Development

Successfully merging this pull request may close these issues.

XNNPACK test_fp16_gelu is producing a bug

2 participants