llama: automatically set runtime parameters such as --n-gpu-layers to fit VRAM#14067

JohannesGaessler wants to merge 1 commit intoggml-org:masterggml-org/llama.cpp:masterfrom

JohannesGaessler:llama-ngl-opt-2JohannesGaessler/llama.cpp:llama-ngl-opt-2Copy head branch name to clipboard