Closed jonastemplestein closed 3 months ago
I think I've fixed it in #4028 but would appreciate if somebody could double check as I don't really know what I'm doing 🤣
@jonastemplestein Do you use it for codeshell-vscode ? I tried your PR but it seems not working for deepseek coder - server closed itself when trying completion
sorry if not related
I don't think that's related. I just fixed the bug where you had to pass in a prompt to the infill endpoint, even though the code then did nothing with it
@jonastemplestein ok then
@x4080 @jonastemplestein Seems it's related. In server.cpp/request_completion(), there's a check
if(task.data.at("prompt").size(), will throw error and cause 500
and codeshell extension won't sent a prompt paramter when using /infill
Could you guys check if https://github.com/ggerganov/llama.cpp/pull/4833 fixes the issue?
Could you guys check if #4833 fixes the issue?
yeap it is.
This issue was closed because it has been inactive for 14 days since being marked as stale.
I'm running the server like this using a quantised code llama
The following curl always instantly responds with any empty
"content"
key in the JSON response:If I add a non-empty "prompt" key to my request, the generation succeeds. But this is contrary to the documentation that says the prompt key is ignored.