cturan/llama.cpp @ b6ae75afb49b23db3dfbc2b01e8aabfb047e6880

Mirror von https://github.com/cturan/llama.cpp

Daniel Bevenius b6ae75afb4 ggml : bump version to 0.9.3 (ggml/1353)		vor 4 Monaten
..
cmake	9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094)	vor 6 Monaten
include	e789095502 llama: print memory breakdown on exit (#15860)	vor 4 Monaten
src	02463ab27b ggml-backend : add root cause in error message if loading backend library fails (#16172)	vor 4 Monaten
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	vor 1 Jahr
CMakeLists.txt	b6ae75afb4 ggml : bump version to 0.9.3 (ggml/1353)	vor 4 Monaten