cebtenzzre b12fa0d1c1 build : link against build info instead of compiling against it (#3879) 2 лет назад
..
CMakeLists.txt b12fa0d1c1 build : link against build info instead of compiling against it (#3879) 2 лет назад
README.md ec893798b7 llama : custom attention mask + parallel decoding + no context swaps (#3228) 2 лет назад
parallel.cpp b12fa0d1c1 build : link against build info instead of compiling against it (#3879) 2 лет назад

README.md

llama.cpp/example/parallel

Simplified simluation for serving incoming requests in parallel