NVIDIA / NVIDIA/cuvs

[FEA] Flash K-means Optimizations

Open
#2,173 0 comments 0 reactions 2 assignees View on GitHub

@divyegala is already working on this.

Since Aug 4, 2026.

feature request
Dominant language
Cuda
Stars
854
Forks
236
Avg merge
3d 3h
Merged PRs (30d)
62

Description

Flash k-means uses flash attention 2 fused distances + k-select kernels, along with cuTile optimized kernels to improve the performance of k-means.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.