[FEA][AI Foundry][NetApp]- BF16 quantization support for indexing
Open
Nobody has claimed this yet.
feature request
- Dominant language
- Cuda
- Stars
- 854
- Forks
- 236
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 62
Description
NetApp requesting for BF16 quantization support for indexing
Describe alternatives you've considered
NetApp looking to provide its customers flexibility on FP32, FP16, BF16, INT8, and binary support for extreme vectorDB space savings.
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
The issue names no file, test, or entry point. Start by locating the indexing quantization implementation and the existing FP32, FP16, INT8, and binary paths, then clarify BF16 behavior and acceptance criteria with maintainers. Done means BF16 indexing support is implemented and covered by appropriate tests.
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