Do online fp8 quantization while loading weights instead of in process_weights_after_loading, reducing memory overhead#17945
Open
fxmarty-amd wants to merge 17 commits intosgl-project:mainfrom
Commits
Commits on Jan 28, 2026
Commits on Jan 29, 2026
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
Commits on Jan 30, 2026
Commits on Feb 4, 2026
- committed