NVIDIA / NVIDIA/TransformerEngine

Dequantization support for the grouped tensor - NVFP4

Open
#2,726 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.5k
Forks
831
Avg merge
3d 11h
Merged PRs (30d)
65

Description

Support for the dequantization of grouped tensor in NVFP4 format when the scaling factors are not swizzled.

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

The issue names no files, tests, or entry points. Start by locating the NVFP4 grouped-tensor dequantization path and its handling of unswizzled scaling factors. Done means grouped tensors in NVFP4 format can be dequantized when the scaling factors are not swizzled.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.