cturan/llama.cpp

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

Auteur	SHA1 Message	Date
Olivier Chafik	e121edc432 `server`: add `--reasoning-budget 0` to disable thinking (incl. qwen3 w/ enable_thinking:false) (#13771)	il y a 7 mois
Olivier Chafik	d785f9c1fd server: fix/test add_generation_prompt (#13770)	il y a 8 mois
Olivier Chafik	aa48e373f2 `server`: inject date_string in llama 3.x template + fix date for firefunction v2 (#12802)	il y a 8 mois