R
|
3d26a09dc7
server : add thinking content blocks to Anthropic Messages API (#18551)
|
3 weeks ago |
Daniel Bevenius
|
d3dce4e0a5
sampling : add support for backend sampling (#17004)
|
3 weeks ago |
Xuan-Son Nguyen
|
6ce863c803
server: prevent data race from HTTP threads (#18263)
|
1 month ago |
Xuan-Son Nguyen
|
3997c78e33
server: fix data race in to_json_anthropic (#18283)
|
1 month ago |
Georgi Gerganov
|
2bc96931d2
server : make cache_reuse configurable per request (#17858)
|
1 month ago |
Xuan-Son Nguyen
|
c42712b056
server: support multiple generations from one prompt (OAI "n" option) (#17775)
|
1 month ago |
Xuan-Son Nguyen
|
c4c10bfb86
server: move msg diffs tracking to HTTP thread (#17740)
|
1 month ago |
Aldehir Rojas
|
0a8026e768
common : introduce composable PEG parser combinators for chat parsing (#17136)
|
1 month ago |
Xuan-Son Nguyen
|
5d6bd842ea
server: remove default "gpt-3.5-turbo" model name (#17668)
|
1 month ago |
Fredrik Hultin
|
ddf9f94389
server : add Anthropic Messages API support (#17570)
|
2 months ago |
Xuan-Son Nguyen
|
b8372eecd9
server: split server.cpp code into server/common/task/queue (#17362)
|
2 months ago |