Skip to content

Fix NF4 dequantize when the scales span more than one int8 group - #2421

Open
rootkiller6788 wants to merge 2 commits into
NVIDIA:mainfrom
rootkiller6788:fix-nf4-multigroup-scale-dequant
Open

Fix NF4 dequantize when the scales span more than one int8 group#2421
rootkiller6788 wants to merge 2 commits into
NVIDIA:mainfrom
rootkiller6788:fix-nf4-multigroup-scale-dequant

Add CPU tests for NF4 double quant with several scale groups

5997f79
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Sep 12, 2026 in 1s

DCO

All commits are signed off!

View more details on DCO