Georgi Gerganov 0e89203b51 speculative : add tree-based sampling example (#3624)		2 vuotta sitten
..
CMakeLists.txt	ec893798b7 llama : custom attention mask + parallel decoding + no context swaps (#3228)	2 vuotta sitten
README.md	ec893798b7 llama : custom attention mask + parallel decoding + no context swaps (#3228)	2 vuotta sitten
parallel.cpp	0e89203b51 speculative : add tree-based sampling example (#3624)	2 vuotta sitten

llama.cpp/example/parallel

peilaus alkaen https://github.com/cturan/llama.cpp

Simplified simluation for serving incoming requests in parallel