llama.cpp/ggml
Jeff Bolz d0061be838
vulkan: split mul_mat into multiple dispatches to avoid overflow (#19509)
* vulkan: split mul_mat into multiple dispatches to avoid overflow

The batch dimensions can be greater than the max workgroup count limit,
in which case we need to split into multiple dispatches and pass the base
index through a push constant.

Fall back for the less common p021 and nc variants.

* address feedback
2026-02-18 10:47:10 +01:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include ggml : make `ggml_is_view` as API (#19539) 2026-02-16 17:43:34 +02:00
src vulkan: split mul_mat into multiple dispatches to avoid overflow (#19509) 2026-02-18 10:47:10 +01:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml : bump version to 0.9.7 (ggml/1425) 2026-02-15 22:24:29 +02:00