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

🔧｜api-opensource

📡｜instant-clusters

🗂｜hub

peanut_

5/1/2025

Problems Setting Up ComfyUI

I've tried a few of the ComfyUI templates and they seem to have various issues. For the moment I'll focus on the default runpod template for it. When I upload my own workflow I am unable to install missing nodes. I get the usual error that nodes are missing but when I try to install them the node results come back empty. I've also tried updating and restarting the interface but the problem persists. The other problem is that it won't load my custom LoRA or the checkpoint that I downloaded. I've tried adding the LoRA to workspace/comfyui as well as comfyui and I refreshed the interface after each move but the problem is still there....

ArtOfficial

5/1/2025

failed to create shim task: OCI runtime create failed:

I only see this issue when using the 5090 pods, and not all of them either. the base docker image is nvidia/cuda:12.8.0-cudnn-devel-ubuntu22.04 error starting container: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error setting cgroup config for procHooks process: openat2 /sys/fs/cgroup/memory/docker/52fd6559d48734b8cef57a73bd60c7e11468d50c7f3d34265f3c1ccadd5a6e88/memory.limit_in_bytes: no such file or directory: unknown...

Gaze

5/1/2025

Custom arguments for Better Launcher template

Hi @Madiator2011 for your madiator2011/better-launcher:dev is editing /app/utils/app_configs.py directly the only way to add custom arguments to ComfyUI? Is there a newer setup you recommend?

KamKam

4/29/2025

Unable to SSH into Pod + Error

This is the second pod back to back that has resulted in this error. I am now unable to SSH into the pod. I tried restarting the pod but that didn't resolve the issue. Can someone please take a look?...

4/29/2025

(Beginner Question) Hosting Quantized model

Hi, I'm new to runpod can anyone point me towards how I can host a quantized model like this? I want to try the 2.71bit version first. https://huggingface.co/unsloth/DeepSeek-V3-0324-GGUF-UD

JJJ999

4/28/2025

using RTX 4090 Pod want to create API from civitai diffuser models - is cog best way?

Would love to avoid Docker.. and want to stick to my own server instead of serverless. input would be one of several safetensor models and some parameters, and then the generated image is the output of the API.

ozzie

4/28/2025

trl vllm-serve not binding to port

I have a pod with two A6000 and I am trying to run vLLM on one of them via:

VLLM_LOGGING_LEVEL=DEBUG NCCL_DEBUG=TRACE trl vllm-serve --model meta-llama/Meta-Llama-3-8B-Instruct --gpu_memory_utilization=0.75 --max_model_len 2048 --host 0.0.0.0 --port 8000

VLLM_LOGGING_LEVEL=DEBUG NCCL_DEBUG=TRACE trl vllm-serve --model meta-llama/Meta-Llama-3-8B-Instruct --gpu_memory_utilization=0.75 --max_model_len 2048 --host 0.0.0.0 --port 8000

...

txh

4/28/2025

Any easy pipeline to migrate from GCP Cloud Compute VM Instance to Runpod Cluster?

Whats the easiest route? Looking to migrate within the next 24hrs.

cocodev

4/27/2025

Do A6000 pods have NVLink support?

Cynder - birthday kitsune (25th)

4/27/2025

how do i do this?

hay, how do i do this? im trying to rent a GPU so i can run my anaconda stuff and i have no idea how to make this work, can i get a hand setting this up? please?

Osama Akhtar

4/26/2025

Bug in Runpod ComfyUI Network Volume Setup

The /workspace/comfyui folder is not the actual one. The actual one is in /ComfyUI which is outside of the network volume mount. This means that if you terminate the pod, your progress is lost. I think that the folder should be inside the volume mount so the state persists between pod reinitialisations

nick

4/26/2025

web ui was demanding i pay just to start a pod, but i have plenty of credits

I have $69 in credits but the web ui was prompting me to put more money in before starting a pod. this is probably because i had a very old tab open, i had to log out and log back in. so this issue has been fixed for me, but i could see it happening to other people. thanks

Seungduk Kim

4/25/2025

GPU Suddenly Stopped Working

I cannot restart the pod because all the files are in the container storage now. Can you fix it, please?

message.txt

jacksonp

4/25/2025

custom docker which uses streamlit and postgresql

how do i solve a issue that i have to host using streamlit and postgresql

Cathy

4/24/2025

Unable to start kernel

Hi I’m Cathy, I’m trying to run a Flask + JupyterLab project (with Whisper, Gemini API, etc.) on a RunPod GPU pod. I set up a virtual environment and installed all my dependencies, but I keep running into issues: Jupyter kernels don’t use my venv by default, and when I try to switch, I get port conflicts or 502 errors. Sometimes, even after installing packages like Flask or Whisper, my notebook still says “ModuleNotFoundError.” The RunPod dashboard often shows “Not Ready” for JupyterLab and my HTTP service, even when I think they’re running....

Jannes

4/24/2025

Assistance with SSH Access to My Pod

I am trying to connect to my pod via SSH using the following configuration: Host: 69.30.85.33 Port: 22045 User: root...

Joostan

4/23/2025

Global Networking

Hi, I have a volume on IL-1. I thought that was a Global Networking server when I created the volume. Whenever I go to make a pod on any other server, it won't let me choose my volume and a different server. Also, there are no options for Global Networking under any instance price. Any clarification would be helpful.

jang

4/23/2025

[GPU not assigned to Pod – Need help]

[GPU not assigned to Pod – Need help] Hi, I have an issue with my Pod where the GPU is not assigned even though I selected RTX 4090 (on-demand). - Pod ID: ul6dffsrkkbnvl...

바보가 된 나

4/23/2025

Network Issue

Hello, I'm currently using a rented GPU, but I received the message: "This server has recently suffered a network outage and may have spotty network connectivity. We aim to restore connectivity soon, but you may have connection issues until it is resolved. You will not be charged during any network downtime." ...

Mr Mat AI_0001

4/23/2025

Unable to back up volume data to Google Cloud storage bucket

Hi, I've been trying for a while now to sync my Google Cloud storage bucket to Runpod so that I can back up my volume data. I followed the instructions provided by the documentation, but I just can't seem to initiate the transfer; it just keeps refreshing, and then I open up the options tab to select whether to upload or download from Google Cloud storage. I created my service account key JSON key. I provide the bucket name and directory path, but it doesn't seem to work. I ensured that the buck...

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!