ComfyUI and Jupyter not starting up
I've deployed a pod with A40 and 120gb of network volume and proceeded to use the template ComfyUI with Flux.1 dev one-click but after multiple attempts I am stuck here with the pod not responding
Pod not connecting server issue - ComfyUI AI Dock
I have been trying to connect comfyUI AI Dock on Runpod A40 GPU on two servers(EU-SE-1 and CA-MLT-1) but it is not connevcting, shows connection open in logs but ComfyUI not connecting bad gateway and on new network volume also it connected and while installing nodes stopped saying error.
Mi300x NCCL Issue
I’m experiencing an issue with the MI300X pod. Two GPUs are configured, but I’m unable to run the basic all_reduce_perf test on the pod.
...
S3FS / Creating a pod with special docker parameters
Hello, im not very familiar with docker, is it possible to launch a pod with
--cap-add SYS_ADMIN flags? I would like to get s3fs working in my podSolution:
its not possible in runpod
Message Not Public
Sign In & Join Server To View
Stripe is declining my payments
Hello I'm having problems with all my cards being declined by stripe. I've contacted support, but still nothing is on its way.
Could you help me out ASAP? This payment issue is seriously hurting my startup's progress......
New UI tail logs no longer working
With the new UI, when you click on logs it does not tail the logs. The setting to tail the logs is auto selected but had no effect. The only way is to close and reopen the log tab
Security issue: Attackers Scanning Runpod pods?
Hello, over the past month or so, I have been noticing that whenever I spin up a new pod, I instantly start seeing these pings:
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
INFO: 100.64.0.33:33194 - "GET /v1/models HTTP/1.1" 200 OK
ERROR 01-10 08:39:01 serving_chat.py:114] Error with model object='error' message='The model
vllm-vl does not exist.' type='NotFoundError' param=None code=404...Billing per User/Audit Logs
Is there a way to know total monthly cost linked to a user in team account?
How to Terminate a Pod via GraphQL?
Hi everyone,
I'm trying to figure out how to terminate a pod using GraphQL on RunPod. However, I couldn't find any related documentation or examples that explain the mutation or process for this.
Does anyone know the correct way to terminate a pod through the GraphQL API? If possible, please share the mutation syntax or any tips for handling this process....
How to setup?
Hi I've started a RTX 3090 pod. The issue I'm faacing is im not able to setup a tgi for llama 3.5 on the pod. I've tried to debug the issue and looks like it says I dont not have permissions or not allowed to. Am I even allwoed to do that on this pod? Like isnt this pod a docker instance how to get the privileges to do so?
Billing not clear
How does pods payment work? Did I understand correctly that if I launched the pod and it worked for 20 minutes, then I will pay for an hour? Or how does it work? I just have a task to turn on the sub for less than an hour several times during the day, for example, 4 times for 20 minutes or 40 minutes, how will payment work in this format?
Solution:
Message Not Public
Sign In & Join Server To View
Billing unclear to me
Hi,
Is there somebody that understands billing?
I want to experiment with running ComfyUI very incidentally (because I have other things dto do besides this) and need low monthly running costs.
7 dollars per month seems resoanlable to me and so I have created a runpod disk of 100 gb at 7 dollar per month.
But I seem to be paying 1.80 dollar per day now, and I don’t quite understand why....
Terrible Network Speed at CA-MTL-1
At this moment, the network speed of all the pods I created is very poor, about 100kb/s, and I can't pull the image or install the dependencies.
The pod is not exposed externally.
I followed RunPod's documentation to run a web server using FastAPI + Uvicorn on port 8000.
I also specified port 8000 in the Expose HTTP Ports field in the Pod config.
RUN uvicorn main:app --reload --host 0.0.0.0 --port 8000
...Do any official templates include sftp setup?
Besides using cloud sync for data syncing, do any official templates, like runpod/stable-diffusion:comfy-ui-5.0.0, include sftp?
Networking Issue with CA-MTL-1
We experienced slow/unusable connection with our A40 pod in CA-MTL-1. For instance, we can't connect via SSH over exposed TCP and connection from the Pod to our Tailscale network was very spotty. We resolved this by moving to EU-SE-1.
From our monitoring, we see that this issue started roughly ~10:57 UTC....
Network volume and transfer to new pod
Previous pods had network volume (enough to cover what I'd uploaded). Got the pod but no GPU, so need to move.
I cannot see the way to move that stuff (sorry to get technical) to a new pod. Is there a process, button outside my field of vision, or magic spell for this?...
treat blocked Trojan:Script/Wacatac.B!ml found wile downloading my envoirment and dataset folders
webfile:XXXXX\envoirment v8\datasets.zip|https://y104dysa4kdwee-8888.proxy.runpod.net/directories/workspace/fluxgym/datasets?archiveToken=werej28yrpt3h5egnqrg&archiveFormat=zip&followSymlinks=true&downloadHidden=false&_xsrf=2%7C8c636d52%7Ccd8c63d7865fb9741bf0335bfdfe269c%7C1736266023|pid:35960,ProcessStart:133807398345745321
How to handle these WebSocket connections?
I set up an HTTP service on my Runpod, but there are continuous WebSocket connection requests coming in. I want to understand why these requests are occurring and how to stop them. My service is being significantly disrupted by these requests.They seem to share the same internal IP and client ID: INFO: ('***', 55730) - "WebSocket /ws?clientId=6d901a86659e4e78bfcc32b69bd5f68f" 403
INFO: connection rejected (403 Forbidden)
INFO: connection closed
INFO: ('100.64.0.32', 39206) - "WebSocket /ws?clientId=6d901a86659e4e78bfcc32b69bd5f68f" 403
INFO: connection rejected (403 Forbidden)...
How to set ContainerRegistryAuth for `podRentInterruptable`
When renting interruptable pods using GraphQL, like so:
```graphql
mutation {
podRentInterruptable( input: { ...