Jeff Bolz 330c3d2d21 vulkan: optimize mul_mat_id loading row ids into shared memory (#15427) ...

- Spread the work across the whole workgroup. Using more threads seems to
far outweigh the synchronization overhead.
- Specialize the code for when the division is by a power of two.

2025-08-23 08:31:54 +02:00

..

cmake

ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094)

2025-08-07 13:45:41 +02:00

include

ggml: add conv3d op (#15182)

2025-08-22 15:33:15 +02:00

src

vulkan: optimize mul_mat_id loading row ids into shared memory (#15427)

2025-08-23 08:31:54 +02:00

.gitignore

vulkan : cmake integration (#8119)

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

CMakeLists.txt

CUDA: replace GGML_CUDA_F16 with CUDA arch checks (#15433)

2025-08-20 16:58:49 +02:00