GGML/llama.cpp: Add scaled GEMMs for more robust NVFP4 support - #23484
Closed
ORippler wants to merge 4 commits into
Closed
GGML/llama.cpp: Add scaled GEMMs for more robust NVFP4 support#23484ORippler wants to merge 4 commits into
ORippler wants to merge 4 commits into
background
wait
wait-all
cancel
parallel
Loading