Gpu obj ipc #1
Draft
Gpu obj ipc #1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
SumanthRH
reviewed
Nov 7, 2025
Comment on lines
+432
to
+435
| if model_config is None: | ||
| # Defer OpenAI serving setup if model_config requires awaiting in this vLLM version | ||
| # (we cannot await inside Ray's running event loop here). Chat endpoint will be disabled. | ||
| return engine |
There was a problem hiding this comment.
This is pretty bad. We definitley want to have the openAI chat completions endpoint regardless of weight syncing backend. Is there an open issue in the ray repo to track this limitation? Why do we change things regarding the event loop in the main thread
Owner
Author
There was a problem hiding this comment.
Sorry, I left the PR in a very unorganized state since I didn't get to finish everything before I left. I think this logic may not actually be needed- I just had some version conflict errors with vLLM and I was using this as a workaround. I think figuring out some compatible versions may eliminate the need for this code change.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.