NVIDIA / NVIDIA/raft

[FEA] Add Epsilla's ANN index to `raft-ann-bench`

Open
#1,900 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request Vector Search
Dominant language
Cuda
Stars
1k
Forks
251
Avg merge
1d 8h
Merged PRs (30d)
31

Description

Epsilla is showing to be a fairly promising CPU-based solution and it natively uses multiple threads to parallelize even single queries (similar to CAGRA). We should add it to raft-ann-bench so we can evaluate it against HNSW and our GPU implementations.

If it proves to be as competitive as they claim, we should also explore the potential for using their search implementation on the CAGRA graph (cc @divyegala).

Contributor guide

No contributing guide indexed for this repository

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

Start by locating the raft-ann-bench entry point and its existing HNSW and GPU implementation integrations. Add Epsilla as a benchmarked ANN implementation, then verify that results can be compared against those existing implementations; the issue does not name specific files or tests.

Written by the indexing model from the issue text.

Assessment

Domain
search
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.