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

I renewed my pod on a saving plan but it has not been applied.

I also got a notice Maintenance is scheduled for Fri, 03 Oct 2025 07:15:32 GMT. ...

Docker / template for existing environment on the network volume

Hi, Is it possible to implement working with A1111 on newly created pods without completely reinstalling the entire environment? I have a network volume and would like to: 1) for the first time - create an environment on the network volume using a good template, for example, "ULTIMATE Stable Diffusion Kohya ComfyUI InvokeAI"; 2) terminate pod when I do not work and create a new one again when needed;...

My PROD GPU Pod keeps on going off during traffic time. How to keep it awake 24/7 ?

Hi, I'm running FastAPI with some models with GPU. But there will be 0 traffic some-times, POD is going off and port gets changed. so when API Request comes it was unable to serve it back since FastAPI Port is killed & I've to reinstall packages + start server. How to keep the server up 24/7. Since POD runs on docker, I was not able to utilize systemctl to start/stop the App. any advice please ??...
No description

Monitor Pod individual monthly usage / billing

Hi, I would like to be able to track each Pod individual usage using your API . I see how to get usage for GPU classes but not individual pod. Is it possible to fetch this data? Thanks you!...

Speed up text-generation-interface startup time

I'm running HuggingFace's TGI with LLM models on pods. The startup time can be significant because the first thing the image does is download the entire model I'm running. For example, it often takes 10-15 minutes from the time I start a Pod until it is available. When we are autoscaling due to load, that is a long time! Is there any way to speed up how quickly pods start up in this scenario?...

upload very slow

I’m trying to upload a 17GB model to ComfyUI. What’s the best way to upload it, because it seems to take forever? I tried using scp, rsync, and wget, but it says it will take 4 days....

lock pod vs. crone job

hi @everyone, I've got into a problem. I want to create a cronejob on my processes in runpod for cost optimization. my users come only for max 9 hours per day. So, can I use lock and unlock pod each day for this.? and will this affect any other thing in the processes. thank you....

Hello everyone guys! I need your experience please...I can’t understand why when I try to install w

Hello everyone guys! I need your experience please... I can’t understand why when I try to install wav2vec either in the audio_encoders folder or in a folder I created called wav2vec2, the file is not saved to the folder. Has anyone ever had this problem?...

Why is there a 3–4s delay in API responses due to RunPod’s reverse proxy?

Hi, We deployed a GPU cloud service on RunPod that exposes an API endpoint. The API generates image results, and while the model inference on the server side is quite fast, we’ve noticed that the actual response time observed from the frontend is significantly longer. Specifically, the time difference between when the server finishes computing the image and when the frontend actually receives the result is around 3–4 seconds slower. After investigating, we confirmed that the extra latency is not caused by our code or model, but rather seems to come from RunPod’s reverse proxy service. ...

Unable to connect to pod - Web Terminal, SSH, and Jupyter Lab all failing

Hello RunPod support, I'm experiencing connectivity issues with my pod and cannot access it through any available method. ...

CloudSync to AWS S3 fails with cryptic error message "One of the commands was not successful!"

- IAM permissions for S3 has been provisioned - S3 bucket and folder have been created and exist - s3 path is {bucket}/{folder} formatted - path on pod is /workspace/checkpoints...

Network Volume Upload: 502 Bad Gateway Left and Right

Hi chat, Anyone experience this when interacting network volume via aws s3: ``` An error occurred (502) when calling the UploadPart operation (reached max retries: 2): Bad Gateway...

I cant open pods.

when i try to open a pod, it starts to open but it doesnt go pass that point to jupiter notebook

chat am i cooked

3 of my pods omggggggggggggggggggggggggggggg
No description

error creating container: Error response from daemon: unauthorized: authentication required

Basically title. I have not been able to start my pod due to this error. I'm using the official image runpod/pytorch:2.8.0-py3.11-cuda12.8.1-cudnn-devel-ubuntu22.04 I have stopped and started it for multiple times. Deploying a new pod has the same problem....
Solution:
According to this message this is a problem on Dockerhub's side: https://discord.com/channels/912829806415085598/1420555672268836955/1420558621728833578
No description

I am encountering a permission error when launching Runpod.

error pulling image: Error response from daemon: unauthorized: authentication required error creating container: unauthorized to use image vllm/vllm-openai:latest...

Request to enable Provider Mode

I would like to join as a node provider. I have 4× NVIDIA H200 GPUs available in my facility with stable internet, power and cooling. Please enable provider mode for my account: dagkorma@gmail.com Thanks in advance!...

Add ports to a existing pod

how do i add ports to a existing pod. The Edit pod UI just shows the existing ports and has no option to add a new port...
No description