[FEA] Add lucene-HNSW and lucene-CAGRA-HNSW in 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
Users require a way to create paretos to compare CAGRA acceleration in lucene with HNSW.
Integrating https://github.com/rapidsai/cuvs-lucene (CPU: lucene-HNSW and GPU: Lucene-CAGRA-HNSW) with cuvs-bench would help create a single source of truth for benchmarks across cuvs integrations.
We will also use this cuvs bench run to write the cuvs-lucene blog and share results with users.
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 examining the cuvs-bench integration points and the linked cuvs-lucene project to understand how lucene-HNSW and lucene-CAGRA-HNSW are exposed. Done means cuvs-bench can run both CPU and GPU implementations and produce comparable Pareto benchmark results.
Written by the indexing model from the issue text.
Assessment
- Domain
- performance, search
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100