Skip to content

Conversation

@WoosukKwon
Copy link
Collaborator

No description provided.

@WoosukKwon WoosukKwon added the ready ONLY add when PR is ready to merge/full CI is needed label Sep 17, 2025
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a 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.

@mergify
Copy link

mergify bot commented Sep 17, 2025

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @WoosukKwon.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

@mergify mergify bot added the needs-rebase label Sep 17, 2025
Signed-off-by: Woosuk Kwon <[email protected]>
@mergify mergify bot removed the needs-rebase label Sep 17, 2025
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]>
@cadedaniel
Copy link
Collaborator

Is there a migration guide for existing code which uses the AsyncLLMEngine with V1 enabled?

@WoosukKwon
Copy link
Collaborator Author

@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).

@WoosukKwon WoosukKwon merged commit e19bce4 into main Sep 18, 2025
47 of 49 checks passed
@WoosukKwon WoosukKwon deleted the woosuk/remove-async-llm-engine branch September 18, 2025 18:07
debroy-rh pushed a commit to debroy-rh/vllm that referenced this pull request Sep 19, 2025
FeiDaLI pushed a commit to FeiDaLI/vllm that referenced this pull request Sep 25, 2025
charlifu pushed a commit to ROCm/vllm that referenced this pull request Sep 25, 2025
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: charlifu <[email protected]>
xuebwang-amd pushed a commit to xuebwang-amd/vllm that referenced this pull request Oct 10, 2025
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: xuebwang-amd <[email protected]>
choprahetarth pushed a commit to Tandemn-Labs/vllm that referenced this pull request Oct 11, 2025
lywa1998 pushed a commit to lywa1998/vllm that referenced this pull request Oct 20, 2025
xuebwang-amd pushed a commit to xuebwang-amd/vllm that referenced this pull request Oct 24, 2025
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: Woosuk Kwon <[email protected]>
Signed-off-by: xuebwang-amd <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ci/build frontend ready ONLY add when PR is ready to merge/full CI is needed v1

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants