Georgi Gerganov 4301e27319 common : restore grammar-based rejection sampling (#18137) 1 month ago
..
CMakeLists.txt 7cc2d2c889 ggml : move AMX to the CPU backend (#10570) 1 year ago
README.md 68ff663a04 repo : update links to new url (#11886) 11 months ago
speculative.cpp 4301e27319 common : restore grammar-based rejection sampling (#18137) 1 month ago

README.md

llama.cpp/examples/speculative

Demonstration of speculative decoding and tree-based speculative decoding techniques

More info: