Update RMSNorm.forward to accept 2D or 3D input shape#1221
Merged
jlarson4 merged 1 commit intoTransformerLensOrg:devfrom Apr 3, 2026
Merged
Conversation
7 tasks
Collaborator
|
A non-breaking alternative solution to this problem would be to adjust the type hint, to allow for this case of a 2D caller. I'd recommend establishing a custom Union type of |
RMSNorm.forward() has a jaxtyping hint expecting a 3D tensor (batch, pos, length), but _apply_qk_norm was reshaping to 2D (batch*pos*heads, d_head), causing a BeartypeCallHintParamViolation on Gemma 3 models. Update the type hint to allow 3D since the code only cares about the last dimension. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
brendanlong
force-pushed
the
brendanlong/gemma3-attention-shape
branch
from
378af45 to
4f7c0c2
Compare
brendanlong
changed the title
Contributor
Author
|
@jlarson4 I updated it to take that approach instead. |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
RMSNorm.forward() has a jaxtyping hint expecting a 3D tensor (batch, pos, length), but _apply_qk_norm was reshaping to 2D (batchposheads, d_head), causing a BeartypeCallHintParamViolation on Gemma 3 models.
RMSNorm only operators on the last dimension, so this updates the type to accept 2D as well as 3D.
Type of change
Checklist:
Note: I have new tests I'm working on in brendanlong#8 that failed due to this