How to edit the vLLM settings on a serverless instance originally created with "quick deploy"?
I'm trying to figure out how to change vLLM settings on a serverless instance that isn't working quite right. There's a ton of tunables on the quick deploy dialog but I can't figure out where to change them on an existing endpoint.
Solution:Jump to solution
Hmm, use the quick deploy again and see the env, or check vllm worker github repository for the env variables
2 Replies