Add CapPress#234
Merged
Merged
Conversation
alessiodevoto
requested changes
Jun 8, 2026
alessiodevoto
left a comment
Collaborator
There was a problem hiding this comment.
Thanks for opening this, @jiamingyy ! The PR looks good overall! I left a few comments on things that need to be updated. Please take a look when you get a chance. Looping in @maxjeblick as well in case he has additional feedback.
119e373 to
bf55c89
Compare
Contributor
Author
|
I would like to thank @alessiodevoto for the valuable review. I have resolved all the issues raised. |
Collaborator
|
/ok to test cded71a |
Signed-off-by: jiamingyy <[email protected]>
) Signed-off-by: jiamingyy <[email protected]>
Signed-off-by: jiamingyy <[email protected]>
Signed-off-by: jiamingyy <[email protected]>
Collaborator
|
/ok to test 6817249 |
alessiodevoto
approved these changes
Jun 10, 2026
Collaborator
|
LGTM @jiamingyy ! Thank you for your contribution to KVPress 🎉 |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add CapPress, a new KV cache compression method implementing
CAPKVfrom paper (https://arxiv.org/abs/2604.25975). The press evicts tokens based on query-aware capacity scores computed from a log-determinant leverage proxy, using value vectors as output-direction proxies with historical-query anchoring.