llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization#16653

JohannesGaessler wants to merge 2 commits intoggml-org:masterggml-org/llama.cpp:masterfrom

JohannesGaessler:llama-memory-fit-9JohannesGaessler/llama.cpp:llama-memory-fit-9Copy head branch name to clipboard