ik_llama_opt/ggml
Jun Yamog 53cd4d0ff0
fix: use mmq for volta quantized matmuls (#1785)
2026-05-15 08:11:49 +03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include MTP: faster recurrent state restore (#1791) 2026-05-13 11:00:24 +03:00
src fix: use mmq for volta quantized matmuls (#1785) 2026-05-15 08:11:49 +03:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt ggml : default GGML_WIN_VER to 0x0A00 (Windows 10) (#1755) 2026-05-08 13:23:04 +03:00