NVIDIA / NVIDIA/cuvs

[FEA] Add `pgvector` to `cuvs-bench`

Open
#759 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

pgvector has a capability to page very large (e.g. 1B-scale) indexes in and out of disk. We are beginning to work towards this capability in cuVS, using pgvector as a baseline, so we need to add it to cuvs-bench.

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 locating the cuvs-bench implementation and existing benchmark integrations, then review how pgvector provides paging of large indexes for the baseline. Add pgvector as a benchmarked option, with results comparable to the existing cuVS work; the issue does not name specific files or tests.

Written by the indexing model from the issue text.

Assessment

Tech stack
postgresql
Domain
databases, testing-qa, tooling
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.