R
RunPod•2mo ago
PolarRobin11

4090 GPUs in EU-RO-1 not available or with full memory

When starting up 4090s on this server region they get either stuck in "waiting for logs" before I can access them or their memory is full. please fix asap 🙏
3 Replies
PolarRobin11
PolarRobin11•2mo ago
ok seems memory bug is fixed but how come this happens when I start up 4x 4090? It just gets stuck indefinitely
No description
XeviaN
XeviaN•2mo ago
Hmm i'm not able to start my 4090 pod in the same region because of no gpu availability since yesterday...
PolarRobin11
PolarRobin11•2mo ago
Oh just saw actually the problem is not fixed, but I managed to get 2 empty ones. But when I then started 4x 4090s again to try it out they were already full
No description
Want results from more Discord servers?
Add your server
More Posts
While runnning a python file in my pod, I encounter a ModuleNotFound Error for tkinterI have installed tkinter using pip and through `apt-get install python3-tk` . Still getting the errogoogle colab imageI used the colab image available at us-docker.pkg.dev/colab-images/public/runtime:latest , the imageModel loadtime affected if PODs are running on the same serverI was trying to debug the latency on my test PODs and now I figured that PODs running on the same phSwitch off pod after 2 hoursHello, I'm new with runpod, It seems like I didn't turn off my pod and it used up all my credit. Hohow to expose my own http port and keep the custom HTTP response?I want to use my own function and image directly. But I cannot find any guides about how to define aCannot open 7860 port with Oobabooga Text Generation WebUI templateI cannot open 7860 port with Oobabooga Text Generation WebUI template.Need password when connect to pod using SSHwhen I create a pod I try to connect to it using SSH, I follow the tutorial in the site Doc, when I confusing serverless endpoint issueAfter a successful call through run or runsync, i get my handler's success json. after about 5 seco"Error saving template. Please contact support or try again later." when using vLLM Quick DeployI managed to launch two endpoints successfully. The third endpoint displays the error above when I cjupyter notebookWill connecting to the port of GPU instance show the same progress and jupyter notebook I am running