The legacy LLMEngine in offline inference #14822
RookieChenTaoYu
announced in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
In the v1 version: /vllm/vllm/v1/engine/llm_engine.py this file, where written under the class LLMEngine:"Legacy LLMEngine for backwards compatibility.". So if this file llm_engine.py is legacy, then what will be used for the offline inference in vllm?
Beta Was this translation helpful? Give feedback.
All reactions