NVIDIA / NVIDIA/cuvs

[FEA] Batched indexes

Open
#189 1 comment 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

I have a use case where there are multiple indexes on one device. The queries are also batched. For example, if there are N indexes, the query matrix has shape (N, Q, D). The expected return reshape is (N, Q, K).

The brute-force algorithm is pretty easy with numpy/cupy/torch. But is there a plan to implement this for IVF or more algorithms? Also, is there a guide for parallelizing this process using CPU threads?

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

Start by clarifying whether the requested scope covers batched IVF and other index algorithms, or only the brute-force case described with numpy/cupy/torch. Define the expected (N, Q, D) to (N, Q, K) behavior and whether CPU-thread parallelization belongs in this feature before identifying an implementation entry point.

Written by the indexing model from the issue text.

Assessment

Tech stack
numpy
Domain
data
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.