Fix Lumina model GQA compatibility with comfy_kitchen RoPE #11679
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
The comfy_kitchen apply_rope function requires xq and xk to have identical shapes, but Lumina uses Grouped Query Attention where query and key tensors can have different head counts. This adds a shape check to use apply_rope1 separately when shapes differ, maintaining compatibility with both standard attention and GQA. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
keejkrej
requested review from
Kosinkadink,
comfyanonymous and
guill
as code owners
Author
|
Related to #11678 |
Member
|
This should be fixed with the updates to comfy-kitchen! |
Author
|
Implemented in Comfy-Org/comfy-kitchen@876670c |
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Outdated suggestions cannot be applied.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.
The comfy_kitchen apply_rope function requires xq and xk to have identical shapes, but Lumina uses Grouped Query Attention where query and key tensors can have different head counts. This adds a shape check to use apply_rope1 separately when shapes differ, maintaining compatibility with both standard attention and GQA.
🤖 Generated with Claude Code