Tencent / Tencent/hpc-ops

FP4 / NVFP4 / MXFP4 support

Open
#25 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
1.2k
Forks
142
Avg merge
23h 15m
Merged PRs (30d)
8

Description

Hello,
first, let me say - amazing results, your work is very appreciated. How much work would it take to implement FP4 / NVFP4 / MXFP4 support?

Contributor guide

No contributing guide indexed for this repository

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

The issue names no files, tests, or entry points. Start by surveying the existing precision and quantization support in the C++ inference operators, then define the required FP4, NVFP4, and MXFP4 behavior and validation; completion criteria are not specified.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
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.