Repository navigation
Conversation
BubbleCal
force-pushed
the
yang/layered-rq-fused-kernels
branch
from
October 9, 2026 14:13
51edac7 to
4f43856
Compare
BubbleCal
changed the base branch from
yang/layered-rq-cache-pins
to
yang/layered-rq-native-kernels
October 9, 2026 14:14
BubbleCal
force-pushed
the
yang/layered-rq-fused-kernels
branch
from
October 9, 2026 16:48
4f43856 to
a9f3adc
Compare
BubbleCal
force-pushed
the
yang/layered-rq-native-kernels
branch
from
October 9, 2026 18:55
c74090f to
de9ffbe
Compare
BubbleCal
force-pushed
the
yang/layered-rq-fused-kernels
branch
from
October 9, 2026 18:55
a9f3adc to
1a31588
Compare
BubbleCal
marked this pull request as ready for review
October 11, 2026 13:23
![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 for a one-time review, or @claude review always to subscribe this PR to a review on every future push.
Tip: disable this comment in your organization's Code Review settings.
This branch has not been deployed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 fused prefix ex-dot kernels for layered RaBitQ widths 3 through 9. Support the 1+1, 2+1, 2+2, 4+1, 4+2, 4+3 and 4+4 high/low splits, preserving each native kernel's floating-point accumulation order. Include scalar, NEON, AVX2 and AVX-512 parity coverage across padded dimensions and ordinary query values.
Dependencies
Independent PR targeting main, integrated with Lance main
b3c8619886b9, including its native four-chain kernels. Standalone benchmark/POC tools remain excluded.Validation
On Linux x86_64 with Rust 1.98.1, formatting, full-workspace clippy (--all --tests --benches -- -D warnings), and all 49 prefix-kernel parity cases passed. The same kernel source also passed 49 cases on macOS arm64 before main integration; the integrated composition passed full-workspace clippy and layered integration tests on arm64.
No new performance measurement is claimed. CI is not awaited.
Tracking
OSS-2345