Eve dafae66cc2

vulkan: dynamic subgroup size for the remaining k quants (#10745) ...

* q5_k

q4_k

q3_k

q2_k

q6_k multi row example

* revert as multi row isnt faster for k quants

2024-12-10 20:33:23 +01:00

..

include

ggml : refactor online repacking (#10446)

2024-12-07 14:37:50 +02:00

src

vulkan: dynamic subgroup size for the remaining k quants (#10745)

2024-12-10 20:33:23 +01:00

.gitignore

vulkan : cmake integration (#8119)

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

CMakeLists.txt

ggml : add predefined list of CPU backend variants to build (#10626)

2024-12-04 14:45:40 +01:00