Georgi Gerganov 8c00b7a6ff 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

2023-09-15 19:06:03 +03:00

..

CMakeLists.txt

llama : add benchmark example (#2626)

2023-08-18 12:44:58 +02:00

llama-bench.cpp

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

2023-09-15 19:06:03 +03:00