Skip to content

Fake-quantize all HF fused NVFP4 experts in one kernel launch - #3011

Open
sychen52 wants to merge 3 commits into
NVIDIA:mainfrom
sychen52:QAD
Open

Fake-quantize all HF fused NVFP4 experts in one kernel launch#3011
sychen52 wants to merge 3 commits into
NVIDIA:mainfrom
sychen52:QAD

Add changelog entries for one-kernel fused-expert fake quant and the …

0c2474d
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Oct 25, 2026 in 1s

DCO

All commits are signed off!

View more details on DCO