llama.cpp/common/arg.cpp at 9d8bd143cc8ca4a7896ff4a79664ffe808ee129d - llama.cpp - Gitea: Git with a cup of tea

upstream-archive/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-06 10:00:48 -05:00

Files

Ruben Ortlam 01649e61c7 llama: add new default load-mode auto which picks mmap unless a non-Metal iGPU is used

2026-08-05 08:03:41 +02:00

207 KiB

Raw Blame History

View Raw