[FEA] Use "batched all-neighbors" for out of core CAGRA build on binary quantized vectors
Open
Nobody has claimed this yet.
feature request
- Dominant language
- Cuda
- Stars
- 854
- Forks
- 236
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 62
Description
Build a CAGRA index with the BitwiseHamming metric by building the graph out of core. Use batched nn descent for this.
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 CAGRA out-of-core build and the batched nn descent implementation. Verify how the BitwiseHamming metric is handled, then determine the build path needed to construct the graph from binary quantized vectors. Done means a CAGRA index builds out of core with BitwiseHamming using batched nn descent.
Written by the indexing model from the issue text.
Assessment
- Domain
- performance, search
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100