WIP: Optimize CAGRA and/or CAGRA_HNSW FBIN bulk indexing
Open
Nobody has claimed this yet.
- Dominant language
- Cuda
- Stars
- 854
- Forks
- 236
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 62
Description
Optimize CAGRA and/or CAGRA_HNSW FBIN bulk indexing
relevant PRs include:
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 reviewing PRs 2481, 2594, and 2597, which the issue identifies as relevant to CAGRA and CAGRA_HNSW FBIN bulk indexing. Compare their approaches and establish the indexing performance target before determining what work remains; done means the selected bulk-indexing path is measurably optimized.
Written by the indexing model from the issue text.
Assessment
- Domain
- performance, search
- Issue type
- Refactor
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100