NVME Disk for GPU Pod
When deploying a GPU Pod, how do I select NVME disk? I can see a disk type choice, but feels like it does nothing.

connection refused
I have created a new pod and am getting the below when i use terminal or lab to make the ssh key. any help is appreciated.
root@4d694e01154b:/workspace# root@4d694e01154b:/workspace# ssh [email protected] -p 40128 -i ~/.ssh/id_ed25519
Warning: Identity file /root/.ssh/id_ed25519 not accessible: No such file or directory.
ssh: connect to host 89.187.159.47 port 40128: Connection refused...
INFO:app_logger:Error generating output Connection to remote host was lost.
I have ofte got this error when working with Dough animation, is there any thing I can do to have securer renderings ?
The full error message: INFO:app_logger:Error generating output Connection to remote host was lost.
Traceback (most recent call last):
File "/workspace/Dough/comfy_runner/inf.py", line 735, in predict...
ssh password
I can t connect to ssh i keep getting asked for password. I tried to use pytorch 1.13.1 official template for my pod. i generated key put it in settings. no config file is created though. i manually created one but still password required
You must remove this network volume from all pods before deleting it.
But there are no pods associated with the volume. It is a rather large volume so I’m keen to purge it.
Solution:
Worked after I removed the serverless endpoint completely, wasn’t the only one with the issue apparently.
Trying to install Ollama: 'could not resolve host'
I've got a brand new 3 x H100 PCi, following instructions on runpod's blog. The pod starts up correctly, but I cannot install ollama. I get "Could not resolve host: ollama.com". I ran the same exact pod an hour earlier (except too little disk space) and it woekd without issue. Has anyone seen this? Should I just delete the pod and start over?
Network volume is read only
In EU-SE-1 I've got a network volume which was working nicely.
But today I've now tried already three times to create and run a pod using this network volume, which also mounts to /workspace, but it is mostly read-only.
I.e. I can create new files but they will stay with a size = 0. I can write stuff into them - but the file is still staying empty.
Can this please be solved? This is preventing me from starting a pod to do the work I need it to do...
Problems SSH-ing into instances suddenly
Around yesterday I suddenly started getting Connection Refused errors whenever attempting a direct SSH connect to Runpod pods, which has left me unable to copy files back or forth. I did not change anything about my ssh keys or setup on my end, and this is the exact same workflow I have used in the past, so something must've changed on Runpod's side?
Anyone else having this problem?
Here's some verbose SSH logging...
Quick Restart Tips for Pod Restarts?
I've been using the aitrepreneur/comfyui template, but restarting the pod takes a lot of time since it runs through the entire Docker script. Most of my setup—including requirements and models—is already installed on my network storage, so I’d prefer not to reinstall everything when restarting. Ideally, I’d like to configure the pod once, terminate it, and quickly restart it with all necessary services (Comfy, Jupyter, VSCode) running, without going through the setup process again. Does anyone h...
SD checkpoints not showing on ComfyUI
(as shown in the first screenshot) the base_path is set so all the checkpoints/loras/upscalers from my A1111 webui should be transferred over to Comfy UI, but it hasn't worked (as you can see on the second screenshot).

Killing Terminal Process
Often I need to cancel a terminal job. However, Shutting Down Terminal does not actually kill the process as I can see the VRAM is still in use. How can I make sure to kill that process without restarting my pod?
Runpod Research & Startup Sponsorship
How long does it take for verification/any response besides the standard "we've recieved your application"? I don't mean to be pushy, just want an update to see if I have been rejected or it's just a processing time period.
Enable UFW
hello - trying to setup a firewall on a gpu cluster but I can't get UFW enabled - if anyone is around to help, that would be great
Stable DIffusion Template WITH ControlNet models preloaded?
While the Stable Diffusion template i'm using does have ControlNet, it doesn't have any of the ControlNet models. I've found it difficult trying to install them.
Can someone tell me 1) a template with the Controlnet models preloaded or 2) how to quickly install ControlNet models?...
Pod hangs for git add command. Tried some memory loading and hangs indefinitely.
Pod hangs for all memory specific commands. Can't push code and move to other server. Can some one help Pod
ID: 7ukzipgyte46cg...
Terminal does not work in jupyter notebook.
Hei guys, for some reason the terminal in jupyter notebooks is not working anymore, when i open the terminal, i just get an empty window in which i can't type anything. I need to use the web terminal for any script executions
Hi,
I am trying to send a file from my local system to my pod volume using this command
rsync -e "ssh -p 10234 -i /home/dell/ssh_keys/ssh_key_dell_Latitude_A4213.txt" -avP /home/dell/exp10/conda_env.zip [email protected]:/workspace/testing/
but when I run this I get this error
ash: line 1: rsync: command not found
rsync: connection unexpectedly closed (0 bytes received so far) [sender]...
Jupyter notebook - does it keep on running?
I am using Jupyter notebook on my pod, can I close the tab, will it keep running?
Open-WebUI 404 Error
When using the Better Ollama CUDA 12 template, and following the instructions found here: blog.runpod.io/run-llama-3-1-405b-with-ollama-a-step-by-step-guide, getting an error when posting a query using open-webui: Ollama: 404, message='Not Found', url='https://<snip>-11434.proxy.runpod.net/api/chat'
Interestingly enough, replacing the open-webui localhost URL with the above URL works well with cURL using network diagnostics.
Wanted to replicate the issue on a less expensive server, but can no longer find the template....
