Eve 0533e7fb38 vulkan: Dynamic subgroup size support for Q6_K mat_vec (#10536) ...

* subgroup 64 version with subgroup add. 15% faster

scalable version

tested for subgroup sizes 16-128

* check for subgroup multiple of 16 and greater than 16

* subgroup sizes are always a power of 2 (https://github.com/KhronosGroup/GLSL/issues/45)

* force 16 sequential threads per block

* make 16 subgroup size a constant

2024-11-30 08:00:02 +01:00

..

include

ggml : move AMX to the CPU backend (#10570)

2024-11-29 21:54:58 +01:00

src

vulkan: Dynamic subgroup size support for Q6_K mat_vec (#10536)

2024-11-30 08:00:02 +01:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

ggml : move AMX to the CPU backend (#10570)

2024-11-29 21:54:58 +01:00