Lightning-AI / Lightning-AI/lightning-thunder

[TE] Explore supporting newer recipes in TE like Float8BlockScaling

Open
#2,476 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement TransformerEngine
Dominant language
Python
Stars
1.5k
Forks
121
PR merge metrics
No merged PRs in 30d

Description

TE has added support for Float8BlockScaling and Float8CurrentScaling, we should investigate their usage and explore if TE executor should support them - https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/api/common.html#

NOTE: Float8BlockScaling recipe is the default on SM120+

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

Start by reading the linked Transformer Engine recipe documentation and locating the TE executor entry point that handles recipes. Compare the existing executor behavior with Float8BlockScaling and Float8CurrentScaling, then determine whether support is needed and how completion should be validated; the issue names no files or tests.

Written by the indexing model from the issue text.

Assessment

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.