llama.cpp

8c00b7a6 - sync : ggml (Metal F32 support + reduce ggml-alloc size) (#3192)

sync : ggml (Metal F32 support + reduce ggml-alloc size) (#3192) * sync : ggml (Metal F32 support + reduce ggml-alloc size) ggml-ci * llama-bench : fix ggml_cpu_has_metal() duplicate function ggml-ci