aarch64: conv: disable s8/u8 -> s32 brg conv for SVE256 #4312
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
s8/u8 -> s32 brg conv is causing unit test failures for PyTorch. Disable these until a permanent fix can be found
github-actions
bot
added
the
platform:cpu-aarch64
Sqvid
approved these changes
Nov 12, 2025
Contributor
|
Do we have any more information about what is failing? What did we try to fix it? Is there a bug ticket somewhere? |
Contributor
Author
|
It looks like brgconv is requesting an unsupported format for reorders. I tried to narrow down the issue through PyTorch and to oneDNN but there is a request to get this triaged urgently for PyTorch so we need this temporary fix. I've created a separate issue to fix the underlying problem: #4313 @jondea |
Contributor
|
Please check #4313 (comment) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
s8/u8 -> s32 brg conv is causing unit test failures for PyTorch. Disable these until a permanent fix can be found