Runpod

R

Runpod

We're a community of enthusiasts, engineers, and enterprises, all sharing insights on AI, Machine Learning and GPUs!

Join

⚡|serverless

⛅|pods

🔧|api-opensource

📡|instant-clusters

🗂|hub

Overcharging

How do I reduce the charges Im getting from my pod. Im not using it most days but getting charged $20 per day when it's $0.87/hr

'd like to share my recent experience using the RunPod service to set up a ComfyUI environment.

Hello everyone, I'd like to share my recent experience using the RunPod service to set up a ComfyUI environment. I loaded $10 intending to use the platform for my project, but unfortunately, I encountered severe instability issues and ended up losing $8. The main problem was constant environment instability and frequent disconnections, which made it impossible to work or use the service for its intended purpose....
No description

Request Windows GPU Template for Unreal Engine

I would like to request a Windows template with GPU support to run Unreal Engine (with MetaHumans) do you have something can help me on this?...

The WanVideoWrapper plugin takes more than 10 seconds to start up. Can this be optimized?

Hello everyone, I’ve been using pod and serverless for quite a while, and I’m currently facing an issue where the WanVideoWrapper plugin starts very slowly when launching ComfyUI. It’s slow both in pods and in serverless environments. This is abnormal and causes significant extra costs, I'm sure that it should only takes 1 seconds to start. I also asked the author of the WanVideoWrapper plugin, and he confirmed that it should only take about 1 seconds to start. And I also tested it on other GPU platforms similar to runpod, and it only took 1 second too. I installed this plugin normally through the plugin manager. ...
No description

File Browser Password

What are the login credentials for File Browser?

12.1 CUDA device assigned w/ 12.8 filter enabled

I filtered pods by CUDA version 12.8 & 12.9. When I spun up the 5090s on pod re8gs6sfkco6ql the installed version was 12.1

Quality Control Issues?

I've noticed this a lot and it's becoming very problematic in my workflows. When I have production GPUs, some of them are just objectively worse (and by a lot, like 3x worse in performance). Same GPU type, same number of CPUs, same template, same storage, same codebase, but it performs x3 slower per iteration in the same region and I can't even swap to a new one because some of the new ones have the same problem. I don't want to play casino when I boot up a GPU and hope that it matches the quali...

How do I know when my pod has the GPU available again?

Do I just keep refreshing the page? I moved away from a network volume because it slowed the speed of my ComfyUI generations, but now I can't pause pods because I'll lose my GPU...Is there a better way to have persistent storage while being able to leave and come back to GPU at max speed? I feel like i'm missing something here....
No description

How to connect CivitAI models to Runpod?

As the name states, how? And if theres multiple options, please let me know....

Is there a way to release without downtime?

If there is no downtime when publishing the image, is there an optimal time? Currently, the reset function seems to be able to achieve no downtime?

A40 pod in EU-SE-1 in weird state, showed GPU utilization at 100% despite no running processes.

Basically title, noticed the GPU was in a weird state. I've attached a screen shot of what nvidia-smi returned. Container template was runpod/pytorch:2.2.0-py3.10-cuda12.1.1-devel-ubuntu22.04, pod ID was 7d5lkyzaceqkq1

getting insufficient storage !

I have a 200GB network volume (ID: eghhav8xzy). And only 33GB of it is occupied (attach screenshot). But I cannot download a 16GB model from huggingface onto it for some reason!! I get the following error (see attached screenshot for complete msg) : "RuntimeError: Data processing error: CAS service error : IO Error: No space left on device (os error 28)". Please try to resolve this ASAP .....
No description

Secure Cloud: Jupyter not load ca. 50% of starts

If I create a new pod and start it. I have often the problem the jupyter lab doesnt open via the direct link.
Load errors in browser logs are this: lab:1 GET https://p2uet3rx491wcu-8888.proxy.runpod.net/static/lab/main.89b98d6484fcb68c324e.js?v=89b98d6484fcb68c324e net::ERR_ABORTED 404 (Not Found)...

Best ComfyUI Template for RunPod & Network Storage?

Hey everyone, I run a YouTube channel about AI in German. I’m planning a video on installing and using ComfyUI on RunPod. What’s the best template to use with network storage for this setup? Appreciate your suggestions!...

Refunds for nonfunctional community GPUs?

I went through multiple community GPUs to find one that was working.

"We have detected critical error on this machine..."

Hello everyone, Currently suffering from the problem
We have detected a critical error on this machine which may affect some pods. We are looking into the root cause and apologize for any inconvenience. We would recommend backing up your data and creating a new pod in the meantime....

Hey, I restarted my pod and now I can't start anything.

Where the ports are, usually I see ComfyUI and Jupiter File Manager - now they are gone and I only see the Ports, under the 'Connnect' tab. What can I do to fix this? And second question, how do I stopmy pod from taking money when I am not actually using it, I just terminate it?...
No description

I don't know how to access my Automatic1111

Hi everyone, I'm new to Run Diffusion and I'm having a problem. I don't know how to access my Automatic1111 interface because I'm stuck at the beginning where I see some blue folders on the right. Thank you very much, even though I'm embarrassed, but I need to learn how it works. Thanks and best regards!...

kohya_ss GUI logs

How do I see the logs for Kohya_ss GUI? A previous post said to check the readme file for instructions but I don't see anything in there for viewing logs. Also nothing seems to happen when I try to start training or do wd14 captioning. I've loaded my image folder and clicked 'Caption Images' but it's never produced any captions....

Error in starting New Pod

Whenever I am trying to create a new pod in the last 30 min, the system logs are showing this error. Tried multiple templates, still gives a similar daemon error each time. Any idea how to resolve this??? 'error starting container: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running prestart hook #0: exit status 1, stdout: , stderr: Auto-detected mode as 'legacy' nvidia-container-cli: requirement error: unsatisfied condition: cuda>=12.8, please update your driver to a newer version, or use an earlier cuda container: unknown'...