Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

return 503 for inference request if there are no available workers #2333

Open
lxning opened this issue May 10, 2023 · 0 comments
Open

return 503 for inference request if there are no available workers #2333

lxning opened this issue May 10, 2023 · 0 comments
Assignees
@lxning
Labels
enhancement New feature or request
Milestone
v0.8.1

Comments

@lxning
Copy link
Collaborator

lxning commented May 10, 2023 •
edited
Loading

🚀 The feature

An inference request is accepted only if there are available workers; otherwise, return 503 immediately.

Motivation, pitch

This feature is used in the use case when the inference request SLA is sensitive where the request must be either immediately served or immediately returned.

Alternatives

No response

Additional context

No response
@lxning lxning self-assigned this May 19, 2023
@lxning lxning added the enhancement New feature or request label May 19, 2023
@lxning lxning added this to the v0.8.1 milestone May 19, 2023
@lxning lxning mentioned this issue May 19, 2023
Merged
8 tasks
@lxning lxning changed the title return 503 for inference request if job queue is full return 503 for inference request if there are no available workers May 25, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@lxning lxning

Labels
enhancement New feature or request
Projects
None yet
Milestone
v0.8.1
Development

No branches or pull requests
1 participant
@lxning