feat: Add RMS QK Norm#214
Closed
kinggongzilla wants to merge 1 commit into
Closed
Conversation
kinggongzilla
requested review from
HennerM,
MauritsBleeker and
Ndles
as code owners
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
There was a problem hiding this comment.
Claude Code Review
This repository is configured for manual code reviews. Comment @claude review to trigger a review and subscribe this PR to future pushes, or @claude review once for a one-time review.
Tip: disable this comment in your organization's Code Review settings.
HennerM
reviewed
May 12, 2026
| self.k = nn.Linear(config.hidden_dim, config.hidden_dim, bias=config.bias) | ||
| self.v = nn.Linear(config.hidden_dim, config.hidden_dim, bias=config.bias) | ||
| self.proj = nn.Linear(config.hidden_dim, config.hidden_dim, bias=config.bias) | ||
| self.qk_norm = nn.RMSNorm(self.head_dim, elementwise_affine=True, eps=1e-6) |
Collaborator
There was a problem hiding this comment.
I think we want a individual norm for both Q and K, such that they can learn individual scale per dimension
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds RMS QK norm in
DotProductAttentionMagic numbers from tests need to be updated after merging #213 , since the combined change of RMS norm plus WK norm will affect these again.