This repository was archived by the owner on Feb 15, 2025. It is now read-only.
Context Cancellation #139
Labels
bug
Something isn't working
enhancement
New feature or request
good first issue
Good for newcomers
help wanted
Extra attention is needed
cc @DayOfThePenguin
One issue right now is even if gRPC gets cancelled, backend models will continue generating into the void. This can cause model servers to seemingly hang while the thread is blocked.
We need some sort of async cancellation mechanism to stop a generation.
The text was updated successfully, but these errors were encountered: