[FEA] Implement binary dataset and accept in CAGRA
Open
Nobody has claimed this yet.
feature request
- Dominant language
- Cuda
- Stars
- 854
- Forks
- 236
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 62
Description
This is a request from OpenSearch for CAGRA to accept binary quantized vectors which also have residual codes associated with them so that they can perform ADC (assymmetric distance computation). The new datasets API in https://github.com/rapidsai/cuvs/pull/1846 should enable the ability to use different datasets.
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 reading the new datasets API in cuVS pull request #1846 and tracing how CAGRA currently receives vector datasets. Define how binary quantized vectors with associated residual codes should be accepted for asymmetric distance computation; done means CAGRA can use this dataset form for ADC.
Written by the indexing model from the issue text.
Assessment
- Domain
- search
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100