llama.cpp/ggml
Gong-Mi cef48b4cbf ggml-vulkan: move ARM/Qualcomm mul_mat_l restriction to init block
Moves the logic that disables large matrix multiplication for ARM and Qualcomm devices from ggml_vk_load_shaders to the device initialization switch block.

This fixes stability issues (silent calculation errors) on Mali G720/Immortalis MC12 while adhering to the code structure requested in PR #18493 discussion.
2026-02-02 01:11:08 +08:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include ggml : add ggml_build_forward_select (#18550) 2026-01-19 20:03:19 +02:00
src ggml-vulkan: move ARM/Qualcomm mul_mat_l restriction to init block 2026-02-02 01:11:08 +08:00
.gitignore
CMakeLists.txt ggml : bump version to 0.9.5 (ggml/1410) 2025-12-31 18:54:43 +02:00