llama.cpp/ggml
Aman Gupta 2f0ac21d4b cuda: add support for non-contig q,k,v 2026-02-13 14:12:09 +01:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include cpu: support for non-contig q,k,v 2026-02-12 21:51:51 +05:30
src cuda: add support for non-contig q,k,v 2026-02-13 14:12:09 +01:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt Bump cmake max version (needed for Windows on Snapdragon builds) (#19188) 2026-02-01 14:13:38 -08:00