Home Explore Help
Sign In
cturan
/
llama.cpp
mirror of https://github.com/cturan/llama.cpp
1
0
Fork 0
Files Issues 0 Wiki
Tree: 8e4d678528
Branches Tags
llama.cpp
/
ggml
Jeff Bolz 07a10c1090 vulkan: Allow non-pow2 n_experts in topk_moe (#17872) 1 month ago
..
cmake 9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 5 months ago
include 51604435e8 ggml-cpu : fix RISC-V Q4_0 repack select and RVV feature reporting (#17951) 1 month ago
src 07a10c1090 vulkan: Allow non-pow2 n_experts in topk_moe (#17872) 1 month ago
.gitignore 17eb6aa8a9 vulkan : cmake integration (#8119) 1 year ago
CMakeLists.txt 79d61896d3 ggml-cpu: add ggml_thread_cpu_relax with Zihintpause support (#17784) 1 month ago