Serverless vllm running but still downloading?

Title says it all and this shouldn't happen
No description
No description
No description
13 Replies
nerdylive
nerdyliveOP3mo ago
still
No description
nerdylive
nerdyliveOP3mo ago
anyways, how to replicate: create a vllm endpoint, then create a network storage, then attach ONLY after its created and all ready Then send requests when 1 worker is ready in the latest workers, to openAI endpoint
sandwich
sandwich2mo ago
@nerdylive I encountered this issue as well, particularly with endpoints created after the update. Has anyone filed a support ticket or found a solution for this?
nerdylive
nerdyliveOP2mo ago
@yhlong00000
Poddy
Poddy2mo ago
@nerdylive
Escalated To Zendesk
The thread has been escalated to Zendesk!
nerdylive
nerdyliveOP2mo ago
i'll try to
River
River2mo ago
Hi there. This is not optimized behavior, but it is expected behavior., Since when you switch to using a network volume, all the running containers need to be removed, and need to be changed to be from the same data center the network volume is in I'll speak to the team about optimizing this behavior, but this is an edge case do we likely will take some time to do this. Nonetheless, the downloading new data occurs because we need to change all the Workers to be only from the data center connected to the network volume.
sandwich
sandwich2mo ago
Thank you for response. I noticed that when this issue occurs, the Docker pull process runs again each time, resulting in delay that take significantly longer than expected. As a workaround, would switching all the workers to the same data center reduce the frequency of this issue?
No description
No description
River
River2mo ago
Yup that should work, Keep it in the same data centre as uh the network volume
sandwich
sandwich2mo ago
I tried your suggested approach of consolidating the serverless workers in a single data center for one day, but the issue still occurred. It also happens even when we rely solely on container disks instead of a network volume. When the issue occurs, we see a “still fetching image” message.
No description
No description
sandwich
sandwich2mo ago
Is there a behavior where the worker’s Docker image is periodically removed after it remains inactive for a certain period of time? If this, too, is expected behavior, I apologize .
River
River2mo ago
would you just be able to always use the network volume hre?
sandwich
sandwich2mo ago
Understood. I'll try it while keeping the Active Worker running. Thank you!

Did you find this page helpful?