[Core][BugFix] Fix thread safety issue in RequestOutputCollector

[22quinn]

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.

Purpose

We need to safely set asyncio.Event() from a different thread otherwise it could lead to hang issue in some cases where await self.ready.wait() remains blocked although the event was set.

Test Plan

Tested with a vendor setup.

Test Result

Tested with a vendor setup.

(Optional) Documentation Update

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[gemini-code-assist]

Code Review

This pull request correctly addresses a critical thread-safety issue in RequestOutputCollector. By using loop.call_soon_threadsafe(), it ensures that the asyncio.Event is set safely from a different thread, preventing potential deadlocks. This is the standard and correct approach for such cross-thread communication with asyncio. The change is well-implemented and effectively resolves the race condition.

[robertgshaw2-redhat]

When does this need to be called from a separate thread? There is only one thread in the AsyncLLM IIUC

[22quinn]

When does this need to be called from a separate thread? There is only one thread in the AsyncLLM IIUC

Seems some nuance in our complex setup caused this and it's consistently reproducible. I've been trying to construct a small repro but not able yet

[njhill]

@22quinn yes this should not be required. It would only be needed if the put method was called from outside the asyncio event loop, but that should never be the case. This is the same for similar asyncio utilities such as asyncio.Queue.