llama.cpp/ggml
Simon Redman 31f6032f1b
Refactor vk_semaphore to be a shared_ptr object.
This resolves a bug with semaphore creation. Previously, we would try to return the pointer to the vector's memory. This is prone to change if the vector resized which, indeed, it is prone to do.
2026-01-29 22:55:29 -05:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include ggml: new backend for Virglrenderer API Remoting acceleration (v2) (#18718) 2026-01-28 17:49:40 +08:00
src Refactor vk_semaphore to be a shared_ptr object. 2026-01-29 22:55:29 -05:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml: new backend for Virglrenderer API Remoting acceleration (v2) (#18718) 2026-01-28 17:49:40 +08:00