Gemma3n and Gemma4 cannot use rotary kernel#45564
Merged
Merged
Conversation
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: gemma3n, gemma4 |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Collaborator
ArthurZucker
left a comment
ArthurZucker
left a comment
There was a problem hiding this comment.
we can't standardize their rope for transpose etc?
vasqu
approved these changes
Apr 22, 2026
Contributor
vasqu
left a comment
vasqu
left a comment
There was a problem hiding this comment.
I think it's good to reference #45489 (comment) for context @ArthurZucker
We would need to rewrite the kernels to allow single tensor application. Atm, this is not the case and hence not a valid usage for the kernels
Contributor
|
Shouldn't be too hard to allow maybe 🤔 same for interleaved and partial layouts imo. It just needs to be properly defined |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
As per the title. Some layers need to apply the rotary only to
q, so it cannot use the kernel.cc @vasqu