[FEA] Add `pgvector` to `cuvs-bench`
Open
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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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