cturan/llama.cpp

镜像来自 https://github.com/cturan/llama.cpp

作者	SHA1 備註	提交日期
Piotr Wilkin (ilintar)	34fcc5a4ac model : Apertus model implementation (#15852)	3 月之前
Piotr	3cb203c89f llama-chat : Do not throw when tool parsing fails (#14012)	7 月之前
Georgi Gerganov	53f925074d sync : vendor (#13901)	7 月之前
Olivier Chafik	03f582ae8f server: fix streaming crashes (#13786)	7 月之前
Olivier Chafik	f5cd27b71d `server`: streaming of tool calls and thoughts when `--jinja` is on (#12379)	7 月之前