llama.cpp/ggml/src/ggml-metal
Georgi Gerganov f0995d28ce
metal : use FA-vec kernel up to batch size 20 (#13496)
* batched-bench : fix pp batch contents

* metal : optimize multi-sequence FA vec kernel

ggml-ci

* metal : use FA-vec kernel up to batch size 20

ggml-ci
2025-05-13 18:04:39 +03:00
..
CMakeLists.txt ggml : skip intermediate .air file when compiling .metallib (#12247) 2025-03-07 14:15:27 +01:00
ggml-metal-impl.h ggml : add mrope kernel for metal (#13457) 2025-05-12 10:29:13 +02:00
ggml-metal.m metal : use FA-vec kernel up to batch size 20 (#13496) 2025-05-13 18:04:39 +03:00
ggml-metal.metal metal : optimize multi-sequence FA vec kernel (#13493) 2025-05-13 18:04:00 +03:00