ik_llama_opt/ggml
Kawrakow 8687fca3ff Graph parallel: better PP performance for 3 and more GPUs (#1092)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-12-26 17:35:27 +01:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Fused norm (#1086) 2025-12-24 15:22:43 +01:00
src Graph parallel: better PP performance for 3 and more GPUs (#1092) 2025-12-26 17:35:27 +01:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt Graph parallel: the next generation (#1080) 2025-12-24 08:31:48 +01:00