Ruben Ortlam c36358cb3c Vulkan: Clean up mul_mm shader (llama/15987) ...

* vulkan: move mul_mm dequantization steps into a separate file and functions

* improve mul_mm vector load code

* fix debug mode issues and warnings

2025-09-20 13:45:29 +03:00

..

cmake

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

2025-08-18 20:30:45 +03:00

include

ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorrect zTensor free (llama/15839)

2025-09-20 13:45:28 +03:00

src

Vulkan: Clean up mul_mm shader (llama/15987)

2025-09-20 13:45:29 +03:00

.gitignore

…

CMakeLists.txt

ggml-cpu: drop support for nnpa intrinsics (llama/15821)

2025-09-20 13:42:50 +03:00