llama.cpp/ggml
dickbird 4475a373d8 refactor(common): use generic backend API for VRAM heuristic
Replaces Vulkan-specific calls with ggml_backend_dev_memory to be backend-agnostic. Reverts changes to ggml-vulkan.cpp/h and removes vk_device_info example to comply with reviewer feedback.
2025-11-29 11:59:45 -05:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include refactor(common): use generic backend API for VRAM heuristic 2025-11-29 11:59:45 -05:00
src refactor(common): use generic backend API for VRAM heuristic 2025-11-29 11:59:45 -05:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml : remove dirty flag from version string (ggml/1391) 2025-11-24 15:26:31 +02:00