-
-
Notifications
You must be signed in to change notification settings - Fork 11.5k
[V0 Deprecation] Remove AsyncLLMEngine #25025
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Signed-off-by: Woosuk Kwon <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code Review
This pull request effectively removes the deprecated V0 AsyncLLMEngine and its related components, which is a great cleanup. The changes are mostly straightforward removals of files and code blocks. However, I've identified a critical issue in vllm/entrypoints/openai/api_server.py where the removal of the V0 engine fallback path now leads to an unhelpful AssertionError if a configuration unsupported by the V1 engine is used. My review includes a suggestion to replace this with a more informative error to improve user experience.
Signed-off-by: Woosuk Kwon <[email protected]>
|
This pull request has merge conflicts that must be resolved before it can be |
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
|
Is there a migration guide for existing code which uses the |
|
@cadedaniel Please correct me if I'm wrong, but no action should be needed because from vllm import AsyncLLMEngine
e = AsyncLLMEngine.from_engine_args(...)will just work (and create a V1 engine). |
Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: charlifu <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: xuebwang-amd <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: Woosuk Kwon <[email protected]> Signed-off-by: xuebwang-amd <[email protected]>
No description provided.