Commit Graph

6 Commits (ddb5fa718dafaed48fe31d2c034c3643c4908bf6)

Author SHA1 Message Date
AT 48275d0dcc
Dlopen backend 5 (#779)
Major change to the backend that allows for pluggable versions of llama.cpp/ggml. This was squashed merged from dlopen_backend_5 where the history is preserved.
1 year ago
Adam Treat 912cb2a842 Get rid of blocking behavior for regenerate response. 1 year ago
FoivosC 337c7fecac construct and return the correct reponse when the request is a chat completion 1 year ago
Adam Treat 748e7977ca Generate the new prompt/response pair before model loading in server mode. 1 year ago
Adam Treat b71c0ac3bd The server has different lifetime mgmt than the other chats. 1 year ago
Adam Treat 2989b74d43 httpserver 1 year ago