NVIDIA / NVIDIA/cuvs

[FEA] Migrate RBC to new k selection routines

Open
#310 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

RBC is the final algorithm that relies on FAISS' k-selection routines, even though we now have new routines right in cuVS for doing warp- and block-level k-selection. The FAISS routines are impacting the compile times and binary size, since the number of instantiations increases. We should migrate over to the new routines.

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.

Research direction

Locate the RBC implementation and its FAISS k-selection call sites first, then read the cuVS warp- and block-level k-selection routines. Done means RBC no longer relies on FAISS k-selection and the resulting compile-time and binary-size impact can be checked.

Written by the indexing model from the issue text.

Assessment

Domain
performance, search
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.