NVIDIA / NVIDIA/cuvs

[FEA] Combine KMeans and ANN Batch Loaders

Open
#2,581 0 comments 0 reactions 1 assignee View on GitHub

@viclafargue is already working on this.

Since Sep 10, 2026.

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

Description

https://github.com/NVIDIA/cuvs/pull/2538 brings a new batch loader with a recycle feature and CUDA events. We should try to combine it with the ANN loader (we can even see if we can improve the behavior inside ANN loader from stream syncs to events).
cc @viclafargue

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.