cturan/llama.cpp

miroir de https://github.com/cturan/llama.cpp

Auteur	SHA1 Message	Date
Marcus Dunn	5be6c803fa llama : remove token functions with `context` args in favor of `model` (#3720)	il y a 2 ans
Georgi Gerganov	d1031cf49c sampling : refactor init to use llama_sampling_params (#3696)	il y a 2 ans
Georgi Gerganov	0e89203b51 speculative : add tree-based sampling example (#3624)	il y a 2 ans
Kerfuffle	70c29da118 common : fix mirostat state when using multiple sequences (#3543)	il y a 2 ans