Georgi Gerganov ee1a0ec9cb llama : add option for greedy sampling with probs (#3813) il y a 2 ans
..
CMakeLists.txt 47068e5170 speculative : PoC for speeding-up inference via speculative sampling (#2926) il y a 2 ans
speculative.cpp ee1a0ec9cb llama : add option for greedy sampling with probs (#3813) il y a 2 ans