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

llama.cpp/example/parallel

огледало от https://github.com/cturan/llama.cpp

Simplified simluation for serving incoming requests in parallel