CUDA: use 1 thread if model is fully offloaded#2915

Merged

ggerganov merged 1 commit intoggml-org:masterfrom JohannesGaessler:cuda-n-threads-fix

Sep 21, 2023

+9

Commits on Sep 18, 2023

CUDA: use only 1 thread if fully offloaded
JohannesGaessler
committed