cturan/llama.cpp @ 6028bf74351d35a06bd98498624f8c2f029f7d1a

Oliver Simons 6028bf7435 CUDA: Optimize `reduce_rows_f32` kernel, leading up to 25x perf improvement on kernel-level and 10% perf increase for Gemma3n (#15132)		5 月之前
..
cmake	9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094)	5 月之前
include	fd1234cb46 llama : add gpt-oss (#15091)	5 月之前
src	6028bf7435 CUDA: Optimize `reduce_rows_f32` kernel, leading up to 25x perf improvement on kernel-level and 10% perf increase for Gemma3n (#15132)	5 月之前
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	1 年之前
CMakeLists.txt	7ad67ba9fe HIP: add cmake option to enable compiler output of kernel resource usage metrics (#15103)	5 月之前