How about unsing vLLM frame instead of InferyLLM ?

#13
by youaaa - opened

just wonder which is fast?

Does anyone know it? really appreciate it

You can use vLLM, performance will not be as good as with Infery-LLM. (DeciLM is documented in the vLLM readme).

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment