llama.cpp/ggml
Johannes Gäßler 4227c9be42
CUDA: fix negative KV_max values in FA (#15321)
2025-08-14 23:21:24 +02:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include finetune: SGD optimizer, more CLI args (#13873) 2025-08-14 12:03:57 +02:00
src CUDA: fix negative KV_max values in FA (#15321) 2025-08-14 23:21:24 +02:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt HIP: add cmake option to enable compiler output of kernel resource usage metrics (#15103) 2025-08-07 16:44:14 +02:00