llama.cpp/ggml
David Friehs 4515987c95 avx2: shift and mask in __m128i then pack to save on permutes 2026-02-16 22:21:19 +01:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include ggml-virtgpu: make the code thread safe (#19204) 2026-02-04 10:46:18 +08:00
src avx2: shift and mask in __m128i then pack to save on permutes 2026-02-16 22:21:19 +01:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml : bump version to 0.9.7 (ggml/1425) 2026-02-15 22:24:29 +02:00