NVIDIA / NVIDIA/warp

[REQ] Support for bfloat16, fp8, fp4

Open
#591 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request language
Dominant language
Python
Stars
7.1k
Forks
624
Avg merge
3d 17h
Merged PRs (30d)
5

Description

Description

Hi, are there plans to support bfloat16, fp8, fp4?

Context

Numerical stability from bfloat16 and performance boosts from fp8, fp4

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

No files, tests, entry points, or acceptance criteria are named. First identify where Warp defines supported numeric types and how GPU compilation represents them, then review existing precision tests and define coverage for bfloat16, fp8, and fp4 before implementation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.