RunPod

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

Join

RunPod

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

Join

⚡｜serverless

⛅｜pods-clusters

Stephen

3/14/2025

How do I ssh tunnel into my runpod instance?

I have tried just testing connectivity. I start up a normal connection using ssh [email protected] -i ~/.ssh/id_ed25519 I then start a python server to emulate ollama...

SuperSynapse

3/14/2025

Is there any way to apt install screen to resume on the webterminal if the connection closes?

I'm doing some longer runs for ai training, but one issue I keep running into in the webterminal is the "Connection Closed" notification which leaves me unable to resume where I left off after the pod has run for an hour. Is there any way to setup a webterminal to resume so that in the event the connection is closed I don't lose all of my work?...

olve

3/14/2025

failed to pull image: failed to register layer: Container ID 1258672 cannot be mapped to a host ID

I get this error when I build my containers either based on nvidia/cuda:11.8.0-runtime-ubuntu20.04 or node:22.11.0. I build my image in github actions on runs-on: ubuntu-latest for platforms: linux/amd64. Is this a common problem?...

Kevin "Literally Who?" Abanto

3/13/2025

VERY LOW SPEED FOR DOWNLOAD

Sometimes the same files download at 120 mb/s and sometimes at 15mb/s it is too slow, and worse if I need to load several models and I use a very expensive GPU Considering that they are the same files that I download every day that I use the platform...

julius

3/13/2025

Websocket Runpod proxy problems

When uploading a 1.8 MiB file over a websocket connection to the pod via the runpod proxy, the websocket is force-disconnected. It's not an error related to the software, the disconnect appears to come from the proxy. It might be a case where the server autoterminate the connection if it's inactive for X many seconds. So the limit on filesize is however much data I can manage to upload before it treats the connection as inactive? Anything that can be done to fix this?...

locusai_admin

3/13/2025

🛠 /etc/hosts Not Resolving DNS

Hi All, I’m facing an issue where I’ve added an IP and hostname mapping to /etc/hosts, but the hostname is not resolving as expected. Here’s what I’ve done: Added the following entry to /etc/hosts:...

bhattronak14

3/13/2025

Connect pods to GKE cluster

Our current inference operations are conducted on Google Kubernetes Engine (GKE). We are interested in leveraging RunPod's GPU offerings for inference tasks. Could you provide information on how to set up and utilize RunPod GPUs for inference purposes?

Johnny

3/13/2025

File Transfer

Is it possible to just download and zip files to my computer from current pod uasing jupiter and then upload to new pod using jupiter

3/13/2025

how to connect to Network Volume after ssh-ing into a Pod?

i deployed the pod with my network volume attached. I ssh-ed into the pod. but I am in root and the storage is only 20gb. i can't seem to find documentation on how to connect to my persistent network volume.

Cap'n Trips

3/13/2025

Connect to jupyter lab?

I'm using the official Stable Distribution template and it says I need to connect to jupyter lab? How do I do that? The web terminal starts and then stops again. Am I supposed to be using a 3rd party app to connect to the server?

danb

3/12/2025

How to have a pod terminate after running a script?

I'm deploying pods using the python sdk. It allows you to set the arguemnt dockerArgs, which will "override the container start command". I'd like to use this to run a custom script and then have the pod terminate automatically after the script finishes. However, I can't get the pod to actually finish. I tried setting dockerArgs="/bin/bash /my_persistent_volume/start.sh" where start.sh is taken from here but with the "sleep infinity" line removed at the end of the file. When checking the logs, it appears that the start.sh script is actually running every 15 seconds rather than running once and then terminating the pod....

R1ckyH

3/12/2025

How to use python api to filter the machine not available to start with network volume?

```json { "maxGpuCount": 8, "id": "NVIDIA L40", "displayName": "L40",...

riverfog7

3/12/2025

Abnormal GPU Temperature in community cloud

GPU No 0 reaches almost 90 degrees which can cause throttling pod id: bg9ctqtv74f459 region: CA type: A6000 x 4...

Borges

3/12/2025

Dropbox cloud sync is very very slow

Hi guys. Everything works with dropbox, i can see its an interface to rclone but uploads to dropbox are getting throttled a lot. Im trying with a CPU instance (thank you btw on the work of getting network drives going on cpus), but its deadly slow. I tried the smallest but then a 16gb one and we are still talking Kibs on the rclone meter so... this is pretty bad. Now, i dont mind any other option as long as it works, but i would like to know which one is known to have decent speed so i dont go t...

hagen

3/11/2025

How to talk to OLLAMA on the same pod? Network error communicating with Ollama: Request URL is missi

After rebooting my pod i see the following error message when talking to ollama: Network error communicating with Ollama: Request URL is missing an 'http://' or 'https://' protocol. According to the docs, I use the following ENV-.Var: ...

Rob1

3/11/2025

Issue HTTP service not ready

I need access to my pod, but it's not ready. I waited for 35 minutes now, but still not accessible Any advices ?...

Technology Genius

3/11/2025

Need Pods ASAP

Hi, I need access to 8 Nvidia GPU (H200), I specifically need 3TB of vCPU memory. Currently only 1.5Tb is showing. Also, I went to demo simulations for a client but in the end the cpu memory was not sufficient so had to wait in front of the client for a couple of hours and finally ended up leaving. Is there a way to reserve the pods beforehand?...

c2h

3/11/2025

Newbie creating a pod : pb with network storage and stop a pod

Hi there, I've made a on-demand pod which is running fine. The problem is that I need to reinstall all every time I need to use it. So I've setup a network storage, and then created a new pod based on it. It runs fine....

Johnny

3/11/2025

automatic not showing models

I have installed embeddings and lora models but for some reason every template for atuomatic 1111 will not show the models in lora tab or textual inversion tab. Everything has been working fine all month but now this is happening! anyone having the same issue

NeuralMuse

3/10/2025

Output in ComfyUI

Dear all, I have a very basic question: I’m using Runpod for ComfyUI and I don’t understand where to download all my images … Is there a way to download them in one shot as well? Thank you very much in advance and sorry for the newbie question...

Previous Next

Gaming

Programming

RunPod

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

RunPod

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