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

Abe
Abe
View on Discord
10/21/2025

Blank COmfyui

[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json Context impl SQLiteImpl. Will assume non-transactional DDL. No target revision found....
No description
unturned3payload
unturned3payload
View on Discord
10/21/2025

Shell Initialization Harms VSCode Remote SSH Integration

Hi, I noticed many of the conveniences offered by VSCode Remote SSH (e.g. git credentials forwarding, the code command, etc.) isn't available when connected to a RunPod instance. After some investigation, it seems that the shell initialization scripts are the culprit. The provided ~/.bashrc runs source /etc/rp_environment at the very end. Inside this file, among other things, is a hard-coded instruction that sets the PATH:...
osayamen
osayamen
View on Discord
10/20/2025

Enable access for NVIDIA GPU profiling

Hey! TL;DR: Can we enable access to GPU performance counters by default as described here? ...
Cristobal Burgos
Cristobal Burgos
View on Discord
10/20/2025

Pods dissapeared

Hi RunPod team, We're aware of the ongoing AWS issues, and it seems to have impacted our pods. They were returning errors earlier and have now completely disappeared from our console. Is there a way to check they were deleted, or if they are just temporarily not visible due to the outage?...
Freke
Freke
View on Discord
10/20/2025

Turn off Pod without using https://console.runpod.io (which is currently down)

I don't have an API. Is there any other way to turn off my pod? Or am I doomed to either run out of money and risk losing my pod or wait and also lose money? I already sent an email to support.
Solution:
Seems to be fixed, fwew
Simon
Simon
View on Discord
10/20/2025

https://rest.runpod.io/v1/pods returns 500 INTERNAL ERROR

It started at 7:45 PDT (14:45 UTC). I don't have any other details.
VieraLimon
VieraLimon
View on Discord
10/20/2025

ComfyUI

Have my two pods launched (3060 and 5090) ncant stopped it( may i have refund or help?...
The Coding Kev
The Coding Kev
View on Discord
10/20/2025

I was training a LoRa and I can't close my pod.

I'm paying 10$ per hour for the training and I can't close my pod. What is going on with this application?? Issues left and right? Am I gonna get refunded for the time this keeps on wasting my money and has locked me out of the account so I can't even close it.
Shahnawaz
Shahnawaz
View on Discord
10/20/2025

using Image AI models with fastapi

I’m planning to run an image generation app using Python and Hugging Face diffusers (like SDXL + ControlNet). I don’t want to use ComfyUI I just want to run my own Python scripts or FastAPI server. Which template or setup should I choose for that? ...
Abe
Abe
View on Discord
10/20/2025

error creating container: Error response from daemon: Head "https://registry-1.docker.io/v2/nextdiff

error creating container: Error response from daemon: Head "https://registry-1.docker.io/v2/nextdiffusionai/comfyui-sageattention/manifests/cuda12.8": received unexpected HTTP status: 503 Service Unavailable can you help me...
CatBunny
CatBunny
View on Discord
10/20/2025

pods are not connecting terminals are not working

Pods terminals are not connecting i tried everything restart as well fix it asap
Kubilay Yazoglu
Kubilay Yazoglu
View on Discord
10/20/2025

How to automate redeployment of pods with network storage?

Hi, I'm using a network volume for my pod to serve an LLM. Since I only need the model to run for a few hours each day, I want to be able to stop and start it easily. However, whenever I stop the pod, all the configuration seems to disappear from the pod page, as if it was never created. The ai-chatbot in discord told me to use automation(scripts etc.). Is there any documentation about how to achieve that?
bghira
bghira
View on Discord
10/19/2025

pod shut down on its own

pod ilmcztyo6x9wuk i didn't want it to be shut down, it wasn't interruptable and had no maintenance alert.....
Smiffy
Smiffy
View on Discord
10/19/2025

CUDA error

I keep getting this message: torch.AcceleratorError: CUDA error: uncorrectable ECC error encountered Search for `cudaErrorECCUncorrectable' in https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__TYPES.html for more information. CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect....
Esorlandoh
Esorlandoh
View on Discord
10/19/2025

jupiter

🐛 Bug Report: JupyterLab port 8888 disappears after pod restart Template: Official ComfyUI (latest version) Pod ID: wgenifr3985iv5 Region: EU-RO-1...
No description
bghira
bghira
View on Discord
10/19/2025

pod not running

why does this happen so much? ``` -- RUNPOD.IO -- Enjoy your Pod #2hcudh6igw3bgb ^_^...
Joe
Joe
View on Discord
10/18/2025

performance issue 5090

The 5090 is being very inconsistant right now. normal generation time for what i do is 100 seconds. Now its jumping up to 250 seconds? What is going on? North america network....
YoYo
YoYo
View on Discord
10/18/2025

Not able to start docker on CPU pods

I used to be able to run docker on CPU pods last year without needing to do anything else than just installing docker, but now I am not able to start docker after installing it. I get this error: ``` Cannot connect to the Docker daemon at unix:///var/run/docker.sock. Is the docker daemon running?...

message.txt

zerozerozeroone
zerozerozeroone
View on Discord
10/18/2025

What GPU is used for wan 2.5 public endpoint

I'm looking to rent a pod to generate videos at similar speed as the public endpoint. I don't need it to be faster as I'm trying to pick the lowest costing one for identical performance.
Milad
Milad
View on Discord
10/17/2025

RTX 5090 model loading extremely slow compared to other GPUs

We have been experimenting with RTX 5090 for some of our workflows and we are finding these machines are extremly slow at loading the model. In a ComfyUI workflow for example, the identical checkpoint loading take 2 seconds on other machines but takes 60 seconds on any of the RTX 5090 machines we have tested.
PreviousNext