[Question] Can DiskANN support dataset larger than uint32?
Open
@suri-kumkaran is already working on this.
Since Feb 8, 2026.
question
- Dominant language
- Rust
- Stars
- 1.9k
- Forks
- 454
- Avg merge
- 3d 22h
- Merged PRs (30d)
- 35
Description
I see that diskann mainly uses uint32_t to manipulate data (like in .bin file), so the maximum dataset diskann can supoprt is 4 billions. I wonder if there's a way to support dataset larger than 4 billions?
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.
Assessment
This issue has not been assessed yet.