[Bug]: Add custom model from UI is confusing and not working #2
Description
What happened?
Adding custom models should be simple. Specify the endpoint, automatically retrieves from /v1/models.
For some reasons I keep getting error. In the test requests, sometimes LiteLLM sends /v1/chat/completions/, which doesn't work with vLLM, sometimes it sends /v1/chat/completions, which should be fine, but I'm getting connection issues.
Relevant log output
Are you a ML Ops Team?
No
What LiteLLM version are you on ?
v1.71.1-stable.patch1
Twitter / LinkedIn details
No response