NVIDIA / NVIDIA/TransformerEngine

Enable post-RHT amax estimation

Open
#2,578 0 comments 0 reactions 1 assignee View on GitHub

@negvet is already working on this.

Since Jan 8, 2026.

  • #2521 by @negvet — open
enhancement fp4
Dominant language
Python
Stars
3.5k
Forks
831
Avg merge
3d 11h
Merged PRs (30d)
65

Description

Is your feature request related to a problem? Please describe.

RHT+amax kernel prevents fusion.

Describe the solution you'd like

Estimate post rht amax from pre rht amax with a linear function. This eliminates rht+amax kernel. Make this feature optional. Make hyperparameters (amax estimation scale) to be tunable.

Validation

Validate lm loss with dense/moe models. Ensure the convergence is the same or better.

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.