llama.cpp/examples/speculative
2024-04-20 16:52:03 +03:00
..
CMakeLists.txt build : link against build info instead of compiling against it (#3879) 2023-11-02 08:50:16 +02:00
README.md speculative : implement stochastic speculative sampling (#5625) 2024-03-04 20:24:00 +02:00
speculative.cpp llama : add llama_token_is_eog() 2024-04-20 16:52:03 +03:00

llama.cpp/examples/speculative

Demonstration of speculative decoding and tree-based speculative decoding techniques

More info: