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

Chauban

4/22/2024

Is it all pods based on Docker?

I want to work on the original Ubuntu system or KVM, also get the public IP of the machine. Is it possible? It seems that the container image all are dockers.

Ramp

4/21/2024

Comfyui runpod don’t save workflow

Hi, I’m having a problem, when I stop the pod with comfyui and I run it again my workflow disappears

Haussar

4/21/2024

HTTP service [PORT 7860] Not ready

Like the title says, the http service isn't ready for me to connect when I'm trying to run TheBloke Local LLMs One-Click UI template. I'm using the A100 GPU with 100GB Disk and 100GB pod volume. its usually lets me connect after a few minutes and its been more than this.

Catid

4/20/2024

I'd like to run a job that takes 8x GPUs.. any way I can increase the spend limit?

tonnu

4/20/2024

Suddenly cannot boot SD Pod having trouble with "Could not load settings"

full error message: 2024-04-20T12:41:36.193868880Z *** Could not load settings 2024-04-20T12:41:36.194453815Z Traceback (most recent call last): 2024-04-20T12:41:36.194479595Z File "/workspace/stable-diffusion-webui/modules/launch_utils.py", line 244, in list_extensions 2024-04-20T12:41:36.194485685Z settings = json.load(file)...

DreamGen

4/20/2024

4xH100 pod is stuck -- can't restart or stop

I am still connected with SSH, but the pod can't be used due to some network issues. RunPod UI also can't reach it (it shows waiting for logs). Over night the pod failed with: ```...

basphi

4/19/2024

Can't open folder in Jupyter Lab

I've been generating some video in ComfyUI and now want to open the output folder in JupyterLab to download them. The problem is I just can't open it, nothing happens when I click it. Is there another way to display the files or open the folder? Downloading the whole folder doesn't make sense since there's a lot of files in there.

HugoA

4/19/2024

CPU seems extremely slow

Hello, I created a pod with an A40 and 16vCPU. I'm trying to train a deep learning model, however, I'm stuck at data preprocessing as the CPU seems to be very slow, this step takes 10 times longer than on my computer with an i5 13th gen which seems very surprising to me. The CPU usage is 100% on the dashboard when I run this step, which is as well surprising....

Ian Upright

4/18/2024

getting a pod's port mapping..

Is there any way to use an API to find out the port mappings of the externally exposed ports for a particular pod?

Unggi Lee

4/18/2024

Megatron Container Image Setting

Hi. I want to use 'nvcr.io/nvidia/pytorch:24.03-py3' image for using the megatron. My start command is 'docker run --gpus all -it --rm -v /:/workspace/megatron -v /:/workspace/dataset -v /:/workspace/checkpoints nvcr.io/nvidia/pytorch:24.03-py3' However, I have trouble with starting the pod....

nace

4/18/2024

Network Volume and copying data between pods.

Hey folks, I've had a pod with 3 GPUs and 1TB under /workspace mounted (not a network volume). All my GPUs are gone without me stopping the pod (ID: jlqfqkgo7sd8h5). 1) It wasn't a spot instance, it was an on-demand one. Why would that happen? 2) I can't allocate more GPU to the existing pod, so I'm forced to create a new one....

Dennis K

4/18/2024

How does runpod work with custom docker images? Multiple questions.

I have some questions: 1. If I use my own dockerhub image, does it have to pull the image from dockerhub everytime? 2. I tried to use a community template (ComfyUI - AI-Dock) and the pull from ghcr is very slow. This is related to the first question. Is there something that affects the pull speed? This sucks because I still get charged as I wait for my image to be downloaded. This image takes about 40mins to download ~5Gb while other take couple of mins for 5GB. So its not a problem on my end. 3. Are there any workarounds for pulling an image everytime? or bumping the pull speed? Can I request an add to cache for this image? I will be using it for now on. 4. How to use credentials registry? What do I set for password? My docker account pass or I generate a token with docker?...

Wolfsauge

4/17/2024

My first template

I am trying to create my first template: https://runpod.io/console/deploy?template=i6ipm7ovin&ref=jndc8ozi It's based on a docker image here: https://hub.docker.com/r/nschle/tabbyapi/tags When filling the template like so, ......

Solution:

docker pull nschle/tabbyapi:v0.0.1

docker pull nschle/tabbyapi:v0.0.1

works and reveals the error, a typo in the tag (missing character "v")...

Volko

4/17/2024

is AWQ faster than GGUF ?

In which order is the fastest inference speed between AWQ, GGUF, GPTQ, QAT, EXL2 ?

Entropy

4/17/2024

Tensorflow Runpod Container

Given this container template : https://github.com/runpod/containers/blob/main/official-templates/tensorflow/Dockerfile and the command flow in https://hub.docker.com/layers/runpod/tensorflow/1.0.3/images/sha256-5b5f23a1e7e81eeb26a85c6e95a9f7f1b664936244d9d8047c23c93c3eb1d7c6?context=explore. Is the template up to date? I want to make some modification to the template and I am curious if I will get the same tensorflow functionality as in the container version 1.0.3. Small feedback would be appre...

TWTom

4/17/2024

What would happen when my spot is interrupted and then the spot is back?

will it: 1. re-run my interrupted script and cost money 2. it would not re-run and still cost money 3. it just stops and won't do anything and won't cost money for the gpu...

Solution:

3. - you have to start it again

DreamGen

4/17/2024

A6000 price change based on # GPUS?

Steps to reproduce: 1. Go to community cloud 2. Select A6000 (price 0.69/hr) 3. Change count to 2 (price 1.58/hr -- which is 0.79/hr per gpu!)...

KiIshikawa

4/17/2024

Conditions under invoice emails are sent

I get these emails frequently, and I'm not sure under what conditions I'm supposed to get these emails. So can you tell me

Fish | Datura [τ, σ/χ)

4/17/2024

Who can I contact to get a runpod invoice for more runpod credits? (5k+)

I have tried contacting [email protected]. 7 days and no reply. Are there any other contacts I can try? Thanks.

AugļuZaglis

4/14/2024

How to add python or API bindings for an vLLM?

I want my vLLM to be able to execute some Python code or call an API. How do I get it to do this?

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!