ROCm / ROCm/AMDMIGraphX

Refactor `generic_float` to handle `E8M0` type

Open
#4,305 0 comments 0 reactions 1 assignee View on GitHub

@CharlieL7 is already working on this.

Since Sep 18, 2025.

Dominant language
C++
Stars
333
Forks
150
Avg merge
4d 19h
Merged PRs (30d)
54

Description

DOR (Definition of Ready)

Ready.

Description
  • Need to support E8M0 type for better handling of MX block scales in MIGX.
  • Current generic_float implementation doesn't allow for having zero mantissa bits and no sign bit.
  • Discussed refactor of generic_float to have a specialization for this case and similar ones.
DOD (Definition of Done)
  • E8M0 type handed in MIGX through generic_float

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.