[BUG] KMeansPlusPlus significantly degrades kmeans performance
Open
@tarang-jain is already working on this.
Since Aug 11, 2026.
bug
- Dominant language
- Cuda
- Stars
- 854
- Forks
- 236
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 62
Description
We are trying to use the new pq API to speedup diskann /aisaq pq computation.
We see there's a big performance difference if using kmeans++ or random initialization.
For example for sift1m for 256k training dataset and 12 kmeans iterations - kmeans takes:
17.5 sec if using kmeans++
6.5 sec if using random.
On an A100 GPU.
We still need the kmeans++ method as it gives roughly 1-2%+ recall improvement
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.