Georgi Gerganov e92d53b29e sampling : optimize samplers by reusing bucket sort (#15665) 4 ヶ月 前
..
CMakeLists.txt 7cc2d2c889 ggml : move AMX to the CPU backend (#10570) 1 年間 前
README.md 68ff663a04 repo : update links to new url (#11886) 11 ヶ月 前
speculative.cpp e92d53b29e sampling : optimize samplers by reusing bucket sort (#15665) 4 ヶ月 前

README.md

llama.cpp/examples/speculative

Demonstration of speculative decoding and tree-based speculative decoding techniques

More info: