Skip to content

Do online fp8 quantization while loading weights instead of in process_weights_after_loading, reducing memory overhead #17945

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
fxmarty-amd wants to merge 17 commits into
base: main
Choose a base branch
from

address constant comment

12cdf42
Select commit
Loading
Failed to load commit list.
Sign in for the full log view
Open

Do online fp8 quantization while loading weights instead of in process_weights_after_loading, reducing memory overhead #17945

address constant comment
12cdf42
Select commit
Loading
Failed to load commit list.
label
succeeded Feb 4, 2026 in 6s