compilade 557410b8f0 llama : greatly reduce output buffer memory usage (#6122) il y a 1 an
..
CMakeLists.txt b12fa0d1c1 build : link against build info instead of compiling against it (#3879) il y a 2 ans
README.md 6d341ab6c5 speculative : implement stochastic speculative sampling (#5625) il y a 1 an
speculative.cpp 557410b8f0 llama : greatly reduce output buffer memory usage (#6122) il y a 1 an

README.md

llama.cpp/examples/speculative

Demonstration of speculative decoding and tree-based speculative decoding techniques

More info: