ROCm / ROCm/AMDMIGraphX

Allow parsing of E4M3FN models using scales manipulation

Open
#2,533 2 comments 1 reaction 1 assignee View on GitHub

@ahsan-ca is already working on this.

Since Dec 7, 2023.

FP8
Dominant language
C++
Stars
333
Forks
150
Avg merge
4d 19h
Merged PRs (30d)
54

Description

If the E4M3FN model is quantized using QDQ pairs then, it can be converted into E4M3FNUZ types by multiplying scales with some constants.

This would allow using E4M3FN models inside MIGraphX.

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.