RunPod

R

RunPod

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

Join

⚡|serverless

⛅|pods

Deploying a PDF converter app to serverless

Hey I'm new to runpod, I'd like to run an app that utilizes some OCR models to convert pdf files to a different format. How can i deploy this app on runpod's serverless endpoint? and how do I manage file uploads to the serverless endpoint?

Managing savings plan using graphql API

Hi Runpod teams! I'm currently using multiple GPU pods in secure cloud and planning to utilize savings plan. We automate provisioning pods using graphql API and trying to integrate savings plan with this system. We frequently update model server running on runpod and our system handle this upgrade via delete and recreating new pod with new docker parameters. ...

"There are no longer any instances available with enough disk space" from graphql

This is the mutation I'm sending: mutation { podFindAndDeployOnDemand( input: { cloudType: SECURE...
Solution:
OK I figured it out - it works if I (redundantly) supply both containerDiskInGb: 5 and volumeInGb: 0 in the input body

How to use multiple GPUs for Kohya Training?

I am using 2x gpus for training using Kohya(Dreambooth). But it is not utilizing both the gpus and instead only 1 gpu is being utilized. I have tried following solutions: 1. added "set CUDA_VISIBLE_DEVICES=1" to gui.bat file of kohya_ss ...

question about reserving time

is it possible to reserve time for multiple gpus across the span of 1-2 weeks? ty

/opt/nvidia/nvidia_entrypoint.sh: line 67: exec: docker: not found

When trying to run docker with command. docker run --gpus all -it --rm -p 7860:7860 org/image:1.0.0 Without the command it seems to run fine but I cant use docker with this command in. Why is this?...
No description

(Not solved, needed to add a tag) Possible network flakiness with network volumes on EU-RO-1

Hello, I'm having issues with network volumes on EU-RO-1, file transfers breaking. Can anyone help?

My pod disk is full.

When I created the pod, I requested 1TB of disk space. However, when I only used less than 500GB, the system showed that there is almost no available space left.
No description

how exacly join to comunity POD as GPU provider

Hello i want join a comunity server with my hw.. i have 6x RTXA2000 12GB 6x RTXA4000 20GB and 12x Amd pro W5700.. How can i join a club to start earn.. suport chat is permanently offline, leave email not work obviously, and most DEV not answear.. So what api you use, whats real HW need for let sa i will set rig by 3gpu each give total 60gbvram in peak...

Can't Delete Storage Volume

I have a 150GB storage volume in EU-RO-1 that I want to delete, but it says that I need to remove it from all pods before I do so. This is in spite of the fact that I don't have any pods deployed and it's not attached to any serverless endpoints.

Issue uploading files to Jupyter

Hi, I'm trying to upload videos to ComfyUi, it has worked just fine in the past but since yesterday I've been getting Failed to Fetch error everytime I try to upload anything, even small photos. I'm using a network volume and there is plenty of memory, and I can't upload videos that I've uploaded previously. I tried to brew install Runpod locally on my mac but I get the following error: zsh: exec format error: runpodctl, and I tried to upload with Curl and that doesn't work, as Curl won't ope...

Kohya_ss: Syncing For >20 Minutes?

I tried running a pod for SDXL Lora training, and it was stuck on this for >20 minutes before I shut it off. How do I get it to not do this?
Solution:
Depends on whether you use secure cloud or community cloud, its not an issue, its normal.
No description

Can't upload videos, getting TypeError: Failed to fetch

I've been able to upload videos just fine before, up to 1080p quality, but all of a sudden it isn't working either in ComfyUI or Jupyter. I can't even upload a 45mb video or a bunch of other videos that I could previously - is there a length limit that I'm not aware of, or something else going on? I am using a network volume, and there is plenty of space. Any suggestions here?

Deploying yolov8 on RunPod

Hi team, we have a custom yolov8 model to deploy in RunPod to act as an inference endpoint which will run inferences on stream of images coming from a client and send the inference results to another log server. We would like to know the feasibility of this in RunPod. Let me know if you need more details. #yolov8...

Pod impossible to access

I am trying to access a pod with no joy whatsoever. Have glanced through it appears not widespread. Any idea what is going on here?
Solution:
Removing the s from http(s) appears to resolve the issue.
No description

Multiple Issues

I accidentally left my pod on for 4 hours and drained money by accident can I have some credit possibly? Sorry It wont happen again Also the http service is giving me constantly not ready when im trying to use Fooocus Templates? Are they bugged or something?...

Windows OS Available?

Hi, Can I run windows on a pod?
Solution:
This service is linux only. No windows

Custom Templates are not loading on Secure Cloud

I have some templates that are running without issue on Community Cloud but None of them work on Secure Cloud. And probably Serverless is suffering with the same issue as my custom endpoint do not load. Issue affects A5000 GPU, on Secure Cloud. ...

can’t run my own init script

Hi guys, after couple hours I give up and asking for help I use standard runpod/pytorch image my initial script is working in digital ocean test instances. ...

How do i create an encrypted volume programmatically?

https://blog.runpod.io/runpod-encrypted-volumes/ "If you would prefer to choose your own encryption key, you can deploy using the API." I can't find documentation on this process anywhere, can someone please tell me where I can find the API that supports this? We are very interested in doing something like this for our future deployments....