Aldehir Rojas
|
2c301e91ab
common : handle unicode during partial json parsing (#16526)
|
3 månader sedan |
Pascal
|
12bbc3fa50
refactor: centralize CoT parsing in backend for streaming mode (#16394)
|
3 månader sedan |
Piotr Wilkin (ilintar)
|
34fcc5a4ac
model : Apertus model implementation (#15852)
|
3 månader sedan |
Sachin Desai
|
3db4da56a5
chat : support Granite model reasoning and tool call (#14864)
|
5 månader sedan |
Piotr
|
3cb203c89f
llama-chat : Do not throw when tool parsing fails (#14012)
|
7 månader sedan |
Olivier Chafik
|
e15898d1c7
server: allow unclosed thinking tags (#13931)
|
7 månader sedan |
Olivier Chafik
|
03f582ae8f
server: fix streaming crashes (#13786)
|
7 månader sedan |
Olivier Chafik
|
f5cd27b71d
`server`: streaming of tool calls and thoughts when `--jinja` is on (#12379)
|
7 månader sedan |