Runpod•15mo ago

Worker keeps running after finishing job, burning money?

Hi!
Since around one week ago, i've started seeing 3-4 examples of a worker displaying 10 hours, or 3 days running while there are no active jobs running.
Is it spending the credits as well?

I've caught an example :

MihályOP•10/17/24, 7:59 AM

Endpoint : 7ulss2nvn75c9j
Worker : pkeld0w61xqtw0
I've killed it for now to stop potentially spending credits.

DannyB•10/17/24, 9:41 AM

This also happened to me

furkan.huudle•10/18/24, 9:32 AM

its happened as same as to me. I built a whisperX container, and it run twice all the time.
Edit for more info:

Im using serverless
Im not using runpod cli, just deploy via dasboard
worker count: 3
selected regions: all
image: nvidia/cuda:11.7.1-cudnn8-runtime-ubuntu20.04

DDannyB This also happened to me

yhlong00000•10/19/24, 11:35 AM

We’ve reverted a recent change, which should help mitigate this problem. Could you share the worker ID with me?

Worker keeps running after finishing job, burning money?

Similar Threads

Similar Threads

Similar Threads