mirror of
https://github.com/RYDE-WORK/llama.cpp.git
synced 2026-01-20 21:53:39 +08:00
* ggml : move AMX to the CPU backend --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
llama.cpp/examples/lookahead
Demonstration of lookahead decoding technique: