R
RunPod•2mo ago
Ralph

Pods shutting down

Is it normal behaviour for a GPU cloud pod that is paid to be on 24/7 to require a cold boot every time it hasn't been used for a while? We have been paying for a GPU to be on all the time so it is quick to respond when we do demos of our software and it's always slow because the pod has to boot up
4 Replies
Madiator2011
Madiator2011•2mo ago
you talking about pod or serverless?
Ralph
Ralph•2mo ago
Pod. Cloud Pod
haris
haris•2mo ago
Hi @Ralph are you able to DM me the pod ID(s) that you are encountering this with?
Ralph
Ralph•2mo ago
DM'd the ID - it might have not been this one all the time as we have cancelled it and started it again to try and fix the error but I can send all our payment receipts
No description
Want results from more Discord servers?
Add your server
More Posts
Connection unexpectedly abortWe are running an GRPC server inside runpods and 1~2% of request abort unexpectedly. Our API's log cDownloading file/directory from remote to local using SCPHi when trying to download from the remote I get a password request is there a workaround ?2 active workers on serverless endpoint keep rebootingWe have 2 active workers on a serverless endpoint, sometimes the workers reboot at the same time forPOD's ERRORS :((((((This server has recently suffered a network outage and may have spotty network connectivity. We aim Billing increases last two days heavily from delay time in RTX 4000 AdaI checked my billing history and I saw that my serverless bills increased a lot and the culprit is tNvidia driver versionWhere can I see what driver versions pods use? Is it the same for all GPU types? I get this error evProfiling CUDA kernels in runpodHi! I'm trying to profile my kernel with nsight-compute and I'm getting error : "==ERROR== ERR_NVGPUInconsistency with volumesWe have an issue where when we startup a container/pod we run a script that should exists inside of Bug prevents changing a Serverless Pod to a GPU Podhttps://i.imgur.com/DNxVc1y.gifNo availability issueWhen renting some instances, the main screen says 'High availability', or etc.. yet it has none when