ik_llama_opt/ggml
Kawrakow 86b5d076c5
Gemma4 MTP: avoid casting KV cache to f32 (#1786)
2026-05-13 09:11:27 +03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Gemma4 MTP: avoid casting KV cache to f32 (#1786) 2026-05-13 09:11:27 +03:00
src Gemma4 MTP: avoid casting KV cache to f32 (#1786) 2026-05-13 09:11:27 +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