Kerfuffle 70c29da118 common : fix mirostat state when using multiple sequences (#3543) 2 år sedan
..
CMakeLists.txt ec893798b7 llama : custom attention mask + parallel decoding + no context swaps (#3228) 2 år sedan
README.md ec893798b7 llama : custom attention mask + parallel decoding + no context swaps (#3228) 2 år sedan
parallel.cpp 70c29da118 common : fix mirostat state when using multiple sequences (#3543) 2 år sedan

README.md

llama.cpp/example/parallel

Simplified simluation for serving incoming requests in parallel