cturan/llama.cpp

Автор	SHA1 Съобщение	Дата
Piotr Wilkin (ilintar)	34fcc5a4ac model : Apertus model implementation (#15852)	преди 3 месеца
Sachin Desai	3db4da56a5 chat : support Granite model reasoning and tool call (#14864)	преди 5 месеца
Piotr	3cb203c89f llama-chat : Do not throw when tool parsing fails (#14012)	преди 7 месеца
Olivier Chafik	e15898d1c7 server: allow unclosed thinking tags (#13931)	преди 7 месеца
Olivier Chafik	03f582ae8f server: fix streaming crashes (#13786)	преди 7 месеца
Olivier Chafik	f5cd27b71d `server`: streaming of tool calls and thoughts when `--jinja` is on (#12379)	преди 7 месеца