RunPod

R

RunPod

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

Join

⚡|serverless

⛅|pods

Port forwarding understanding

Greetings, I have been a user of vast ai, and there they have a list of ports alreadt assigned to it and they map to exactly same one on your machine. But in runpod they map to a different one. I have to run a miner and I need to tell two of my ports to it, now should I be telling it my external or internal ports and how would they map to internal ones? I am also attaching picture of vast ports and yours as well...
No description

Problems starting my pod with and without GPU.

Container LOGs (ID: tb7bqtktnwh9gy) 2024-11-02T18:47:01.634671114Z [SSH] Configuring SSH to allow root login with a password... 2024-11-02T18:47:01.720536800Z * Starting periodic command scheduler cron 2024-11-02T18:47:01.809391559Z ...done. 2024-11-02T18:47:01.926771417Z * Restarting OpenBSD Secure Shell server sshd...

Is there something wrong in US-OR-1?

There seemed to be issues on Thu 10/31 making my ComfyUI pod unusable (Comfy taking 20+ minutes to start and be available, throwing errors when it ran, web terminal challenging for auth and continuously rejecting valid creds). Are these issues ongoing? I went to start a pod today (11/1) and it seemed to exhibit the same issues so I backed away before I burned more credits.

Money on new account

Hey everyone, I’m a new user and I was trying to put money on my account but my card got declined for no reasons. Anyone experienced this problem and knows how to bypass it? Thank you!

Is there a way to launch a pod and then setup cloud sync (from Google Drive) via API/SDK?

The document doesn't seem to have any GraphQL to configure Cloud Sync at launch of a pod. Is this not supported yet?

ComfyUI: Diagnosing errors like "Syntax error: Unexpected token '>'" by logging to file?

All of my ComfyUI workflows stopped working on all instances with a syntax error when i try to run my workflow. The System and Container logs that I can access through the RunPod UI say nothing. Is there a way for me to start ComfyUI manually so I can see errors in the console and log it to a file?

Python SDK resume_pod

Hi, I'm using the Python SDK to resume a pod. However, I can't resume a pod with 0 gpu runpod.resume_pod( pod_id=pod_id, gpu_count=0...

Network Volume as Storage for images

Hi, I am building an image generation application which will store images to a database for which I was thinking RunPod's network volumes attached with a CPU pod sending and fetching images from the volume. Will network volumes be worth it?

Network Volume Integrity

Ever since last night every pod I deploy on my network volume: fpomddpaq0 there are certain files that I cannot open (I believe they have been corrupted). I get a 'launcher error 524' (timeout) when I try to open these specific files (.ipynb). I have tried changing images to the latest pytorch image but that did not help. I have cross checked with a fresh volume in the same region and the error does not occur there. I have now confirmed the issue using the file command via web terminal but...

Stable diffusion checkpoint list empty with Better Forge template

Following the instructions here: https://blog.runpod.io/introducing-better-forge-spin-up-new-stable-diffusion-pods-quicker-than-before/ which were written just last month... I have downloaded two different checkpoints from civit into the stable-diffusion-webui-forge/models/Stable-diffusion folder. However the dropdown list of checkpoints in the webui is empty. I have tried clicking the refresh button, refreshing the page, and restarting the pod, but no matter what I do the models will not show up. What is going on?...

Can't select 2x GPU for my old pod, while I could start a new pod with the same GPU setup

Might be a stupid question, but I had a pod running yesterday with 2 H100 PCIe and I can start my pod only with 0 or 1 GPU, which looks like an availability issue. But If I want to deploy a new pod, I can choose 2 H100 PCIe and the availability is medium.

Udp ports

Hi, currently trying to run a webrtc based streaming application on runpod. The application would connect to a client using webrtc udp connection. Is this something possible to do with runpod?...

Cannot set TCP-Port 3000 for Dreambooth

Hi all, i want to use Dreambooth, and i tryed to set the Port via Fuser and in the Configuration of the pod, but its notpossible to open the port. Fuser throws permission denied (fuser -k 3000/tcp). Any suggestions for me, please?? 😦

A40 availability

There are a couple of >1 month old posts about this but it seems to be an issue again, A40s have become pretty much entirely unavailable other than at weird times (~7am GMT) and it's been like this for about a week now, what's going on? Availability seems unusually poor, I've never known it like this, I've got quite a lot of credit that I can't use.

SGLANG load LLM Model

I am trying to load LLM model using Pods by using sglang template. Here is my config: When I start the pod, it did not loading the model instead the container log keep showing cuda things(license,version). May I know what is the reason?...
No description

Unable to start pod using GraphQL

I am trying to create a pod using the GraphQL endpoint but I am getting 400 status response, here are the request and response for the same. Please let me know how to get this working. ``` Sending GraphQL query: mutation {...

Differentiating between the pod state, "starting" vs "stopping"

When I start a pod and fetch it's details through the grapQL api, the "runtime" is None but when I stop it, the "runtime" is None as well. Is there a way to differentiate between these two states ?