NVIDIA / NVIDIA/cuvs

[FEA] BBQ / RaBitQ Dataset

Open
#2,175 0 comments 0 reactions 1 assignee View on GitHub

@lowener is already working on this.

Since Jul 8, 2026.

feature request
Dominant language
Cuda
Stars
854
Forks
236
Avg merge
3d 3h
Merged PRs (30d)
62

Description

BBQ or Better BInary Quantization is based on RaBitQ and it's the current algorithm supported in Lucene and Elasticsearch. We are being asked by multiple Lucene users to accept a "dataset" of vectors in the CAGRA build() API. The challenge is that the BBQ algorithm requires some additional state to be carried along for correction codes, which need to be considered during search. This means the dataset needs to be specialized for a BBQ quantizer.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.