NVIDIA / NVIDIA/cuvs

[FEA] KMeans Instantiation for Reduced Precision Types

Open
#1,946 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Hierarchical kmeans supports byte types (int8 and uint8). But Lloyd's (kmeans.cuh) only has support for float and double types. We should consider adding int8, uint8 and (potentially) half support.

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.

Research direction

Start with kmeans.cuh and compare Lloyd's implementation with the existing hierarchical KMeans support for byte types. Determine the intended instantiations for int8 and uint8, and whether half is in scope. Done means Lloyd's KMeans supports the agreed reduced-precision types with coverage matching the existing behavior.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.