Skip to content

Fix EngineDeadError in Server/SingleStream scenarios#2482

Open
ssam18 wants to merge 6 commits intomlcommons:masterfrom
ssam18:fix/engine-dead-error-2341
Open

Fix EngineDeadError in Server/SingleStream scenarios#2482
ssam18 wants to merge 6 commits intomlcommons:masterfrom
ssam18:fix/engine-dead-error-2341

Conversation

@ssam18
Copy link
Copy Markdown
Contributor

@ssam18 ssam18 commented Feb 3, 2026

Use a persistent event loop instead of creating new ones per query.
This prevents asyncio loop conflicts with vLLM's AsyncLLMEngine.

Fixes #2341

Use a persistent event loop instead of creating new ones per query.
This prevents asyncio loop conflicts with vLLM's AsyncLLMEngine.

Fixes mlcommons#2341
@ssam18 ssam18 requested a review from a team as a code owner February 3, 2026 02:41
@github-actions
Copy link
Copy Markdown
Contributor

github-actions bot commented Feb 3, 2026

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

@ssam18
Copy link
Copy Markdown
Contributor Author

ssam18 commented Feb 4, 2026

Hello,
Please review this PR and let me know if there is comment?

@ssam18
Copy link
Copy Markdown
Contributor Author

ssam18 commented Apr 2, 2026

@mlcommons/wg-inference - Please review this PR.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[BUG] Llama 3.1 8b Server and SingleStream Scenario fail

2 participants