Georgi Gerganov b3964c1e89 metal : optimize FA vec for large sequences and BS <= 8 (#15566) ... * metal : optmize FA vec for large heads and sequences * metal : adjust small-batch mul mv kernels ggml-ci * batched-bench : fix total speed computation ggml-ci * cont : add comments ggml-ci		2025-08-26 14:22:14 +03:00
..
CMakeLists.txt	ci : disable fast-math for Metal GHA CI (#14478)	2025-07-01 18:04:08 +03:00
ggml-metal-impl.h	metal : optimize FA vec for large sequences and BS <= 8 (#15566)	2025-08-26 14:22:14 +03:00
ggml-metal.m	metal : optimize FA vec for large sequences and BS <= 8 (#15566)	2025-08-26 14:22:14 +03:00
ggml-metal.metal	metal : optimize FA vec for large sequences and BS <= 8 (#15566)	2025-08-26 14:22:14 +03:00