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

임주형
임주형
View on Discord
6/3/2025

How i run ipynb on vscode

hello, I opend ipynb file on runpod ssh with vscode, bun when run the cell, I get failed message. 'need ipykernel package for run the cell' I use the command, '/bin/python3.10 -m pip install ipykernel -U --user --force-reinstall', then i get message that '/bin/python3.10: No module named pip.'...
pelak
pelak
View on Discord
6/2/2025

The pod is crashing while rendering a video in hunyuan

100% mem used, the comfy workflow is stopping when all the steps in hunyuan video sampler are done, can't do anything but restart the pod I'm using A40 gpu...
No description
selectedpixel
selectedpixel
View on Discord
6/2/2025

Connect to Pod via CloudFlare

Hello, I'm attempting to map my Pod's connection URL in my CloudFlare DNS settings but I keep getting this error. CNAME Cross-User Banned | Cloudflare...
Flynn
Flynn
View on Discord
6/2/2025

Auto-downloading straight to local

So, all the images I generate go straight to /output folder. Then it takes ages to download that big output folder. Is there a way instead to download my generations straight to my PC?
Abdelrhman Nile
Abdelrhman Nile
View on Discord
6/2/2025

Is it possible to run a grpc service on a pod?

I cannot communicate with a grpc service that i deployed on a pod, i opened 50051 http port and 443 tcp port. this is what i receive: ``` grpc._channel._InactiveRpcError: <_InactiveRpcError of RPC that terminated with:...
si_senior
si_senior
View on Discord
6/2/2025

Help me understand a productive workflow

Hi, I'm new to running remote jobs in containers, and wondering what the recommended workflow would be if I want to code in my IDE locally and run all processing remotely I was able to connect with jupyter running in vscode, but it seems I have to manually copy my files to the server. Is this the best way? Is there a flow that people generally follow when doing machine learning development / running models remotely ? thank you...
RoughSlayer- Newbility
RoughSlayer- Newbility
View on Discord
6/1/2025

I am ssh into one pod and my drives are on a different pod. I only have one pod. UG

yes look here I ssh using one and it brings me to the new server prompt C:\Users\steve>ssh onvrxxxxxxxk-644xx5@ssh.runpod.io -i ~/.ssh/idexxx519 -- RUNPOD.IO -- Enjoy your Pod #onxxxxxxw1k ^^
(__ \ ( \ | |...
Igor Zinovyev[MTSK]
Igor Zinovyev[MTSK]
View on Discord
6/1/2025

Unable to SSH into a pod via open TCP port

Hi! I'm having a problem SSH-ing into a running pod using the open TCP port. While the proxied SSH works fine, the TCP gives me this: ``` $ ssh root@69.30.85.137 -vvvp 22058 -i ~/.ssh/id_runpod OpenSSH_9.9p1 Ubuntu-3ubuntu3.1, OpenSSL 3.4.1 11 Feb 2025...
Solution:
Poorly made template
The Dude
The Dude
View on Discord
6/1/2025

Unable to start templates

I'm trying to start up either of two templates by "hearmeman" (hearmeman/comfyui-wan-template:v2 and hearmeman/comfyui-wanvideo:v9) both get stuck starting cuda and give an error in the system log. I've tried different L40's and H100's in different locations and have tried both with and without network volumes. I'm in contact with the author of the template and he is able to start it on his end. What's my move here?
No description
Hugo1111
Hugo1111
View on Discord
6/1/2025

Use onedrive or Google drive as workspace

Is there a way to reduce the pod storage and directly use my existing onedrive storage for workspace? Then I can also directly access the files on my local system. Thanks
Only Flags
Only Flags
View on Discord
5/29/2025

Stable diffusion wont start with network storage.

I change SYNC environment variable to false. But i still get these errors or errors like it.
No description
Wormhammer
Wormhammer
View on Discord
5/29/2025

ubuntu archive 403

All day long I've been trying to deploy pods to 4090s in EU-RO-1 with ubuntu/latest and they have been failing with 403 forbidden errors trying to install just about anything with apt. Does someone need to add some firewall rules or something? How do I follow up on this?
Sam Mellors
Sam Mellors
View on Discord
5/29/2025

Network peering between VPC and run pod network

Hi, I would like to set up a peering connection so dagster (running in my VPC) can orchestrate pods in the run pod network privately. I would greatly appreciate any resources or help people can provide on this
selectedpixel
selectedpixel
View on Discord
5/29/2025

Whitelist IP for AWS RDS Connection

I'm attempting to connect to a secure RDS connection. I need to whitelist IP addresses in AWS RDS security so that the connection is allowed. Are there any specific IP addresses I can use?
Dave
Dave
View on Discord
5/29/2025

Is it just me or jupyterlab connect button are no longer passing token ?

Now when i click connect it prompts me for a token, instead of including it in the url how it was years prior. Please bring that logic back, as it would be super annoying to manually paste it on a dozens pods that i manage!
selectedpixel
selectedpixel
View on Discord
5/29/2025

Error loading ASGI app. Could not import module "main".

I'm trying to run a Fast API app on a Pod. I've followed this tutorial https://www.runpod.io/articles/guides/deploy-fastapi-applications-gpu-cloud My Docker Image runs locally fine. ...
a
a
View on Discord
5/29/2025

Ultimate stable diffusion webui pod weirdness

Hey everyone. I’m trying to deploy the ultimate stable diffusion pod on a an rtx a5000 in region IL-1 (pod ID: aak6hvhnsbx95i) and it seems to be looping at “create container: still fetching image runpod/stable-diffusion-webui:7.4.4”. Is there something wrong in my configuration?
👨💻 Aidan
👨💻 Aidan
View on Discord
5/28/2025

Multi-Instance GPU Support on RunPod

Hey, Last night, I was experimenting with RunPod for the first time, and tried to enable MIG via nvidia-smi - but it didn’t work. Instead, it threw an ‘insufficient permissions’ error. This appears to be due to how virtualisation is implemented, providing a lack of hardware-level control within a pod....
sirouk
sirouk
View on Discord
5/28/2025

B200

Please let me know if you can allocate 8 of the B200. There is 7 max but I know there is one more and I could use it.
zoob
zoob
View on Discord
5/26/2025

runpod api questions

- how can i get precise information about availability of some gpu type for pod creating on demand? - is stockStatus value from LowestPrice type of graphql api representing availability status of some specific gpu to create pod with? my workflow is: graphql gpuTypes query -> passing to POST https://rest.runpod.io/v1/pods request body gpu count from my local ui(not more than maxGpuCountCommunityCloud i parsed for specific gpu type) and gpu type id...
No description
PreviousNext