cturan/llama.cpp @ d02e98cde035d91ed8032ab943d1d504fe9da394

peilaus alkaen https://github.com/cturan/llama.cpp

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