Pedro Cuenca b97bc3966e llama : support Llama 3 HF conversion (#6745) 1 year ago
..
CMakeLists.txt b12fa0d1c1 build : link against build info instead of compiling against it (#3879) 2 years ago
README.md 6d341ab6c5 speculative : implement stochastic speculative sampling (#5625) 1 year ago
speculative.cpp b97bc3966e llama : support Llama 3 HF conversion (#6745) 1 year ago

README.md

llama.cpp/examples/speculative

Demonstration of speculative decoding and tree-based speculative decoding techniques

More info: