Skip to content

Add ModelOpt FP8 Transformers inference cookbook - #300

Open
KrzysztofTomala wants to merge 1 commit into
NVIDIA:mainfrom
KrzysztofTomala:docs/modelopt-fp8-transformers-cookbook
Open

Add ModelOpt FP8 Transformers inference cookbook#300
KrzysztofTomala wants to merge 1 commit into
NVIDIA:mainfrom
KrzysztofTomala:docs/modelopt-fp8-transformers-cookbook

Conversation

@KrzysztofTomala

@KrzysztofTomala KrzysztofTomala commented Jul 30, 2026

Copy link
Copy Markdown
Collaborator

A small addition of how to use FP8 checkpoint in the transformers

Signed-off-by: Krzysztof Tomala <ktomala@nvidia.com>
@KrzysztofTomala
KrzysztofTomala marked this pull request as draft July 30, 2026 15:00
@KrzysztofTomala
KrzysztofTomala force-pushed the docs/modelopt-fp8-transformers-cookbook branch 2 times, most recently from 2298ba2 to 177a7cf Compare July 31, 2026 13:28
@KrzysztofTomala
KrzysztofTomala marked this pull request as ready for review July 31, 2026 13:56

@wkutak wkutak left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Cookbook works, inference works properly.
Cosmetic issue: warning logs about unexpected weights in quantized checkpoint.

@wkutak
wkutak self-requested a review August 10, 2026 17:13
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants