Repository navigation
feat: use anchor kv-cache in chunked query inference - #227
Merged
Merged
Conversation
HennerM
requested review from
MauritsBleeker,
Ndles and
kinggongzilla
as code owners
May 26, 2026 13:13
![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.
Contributor
|
Ndles
approved these changes
May 29, 2026
HennerM
force-pushed
the
feat/query-eval-cache-anchors
branch
from
May 29, 2026 08:12
204b49c to
1f8d423
Compare
HennerM
force-pushed
the
feat/query-eval-cache-anchors
branch
from
May 29, 2026 08:50
1f8d423 to
548b5d4
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
We had support for Anchor KV caching for a while and have a good use case in the QueryInference callback: when iterating in chunks over the full geometry, we can reuse the anchors from the first chunk and thus avoid unnecessary compute. This is mathematically equivalent and speeds up inference by roughly 25% in my tests.