Skip to content

Gensyn RL-Swarm on QuickPod

Notifications You must be signed in to change notification settings

quickpod/gensyn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

70 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🐝 Quick Start: Gensyn RL-Swarm on QuickPod

Last updated: July 12, 2025


1. Create Your Pod

  1. Go to QuickPod Templates

  2. Find Jupyter Lab CUDA 12.9, click Clone, and name it (e.g., Gensyn 12.9)

    image
  3. In the Docker settings, add:

    -p 3000:3000 --shm-size=16g
    

    Then click Save.

    msedge_uOQO96e36Z

    Set Disk Space to at least 50

    image

  4. Choose a machine:

    • CPU: 16GB+ RAM
    • GPU: 16GB+ RAM (VRAM can be less or more than 24GB)

    Select the template you just created.

    image

  5. Click the orange Connect to JupyterLab button.

    image


2. Open a Terminal

Inside JupyterLab, click the Terminal icon on the left.

image


3. Upload Your swarm.pem (Optional)

Warning

Skip this if you don’t already have a swarm.pem file. If you do, drag and drop it into the file panel.

image
image


4. Install Gensyn Node

Paste and run the following.

git clone https://github.com/gensyn-ai/rl-swarm && apt update && apt install -y sudo

If you are prompted to overwrite the sudoers file, keep the current one by simply pressing ENTER. Keep the existing sudeors file

Then, run these commands to update npm and node to the latest version.

sudo apt-get install -y curl
curl -fsSL https://deb.nodesource.com/setup_24.x | sudo -E bash -
sudo apt-get install -y nsolid
nsolid -v
npm install --force -g node@latest

5. Start the Node

In the terminal, run:

python3 -m venv .venv
source .venv/bin/activate
cd /workspace/rl-swarm && ./run_rl_swarm.sh

If it gets stuck before the login page prompt loads, press CTRL+C, then run ./run_rl_swarm.sh again.

image


6. Open the Login Page

Click your port 3000 link. It will open a new browser tab.

image


7. Authenticate

Note

It may take 1–3 minutes. Just wait until you see this.

  1. Click on Login image

  2. Enter your email address
    image

  3. Enter the token sent to your inbox
    image
    image

    If you are not receiving OTP email:

    • OTP emails may be mistakenly filtered as spam. Look in your spam or junk folder for the OTP message
    • Sometimes, there may be a delay in OTP delivery due to network or server issues. Wait a few minutes before requesting another OTP
    • Double-check that the email address entered is correct and free of typos. An incorrect email will prevent delivery of the OTP
  4. You should see Login Success

    image

  5. Back in the terminal, it will ask if you would like to upload your results to Huggingface. If you would, type "y", hit enter and then paste your Access Token and enter. alt text

  6. When prompted with which model to use, just click enter. alt text

  7. It will also ask if you would like to participate in the AI Prediction Market (Judge) functionality. If so, type "y" and press enter. alt text


8. Check Your Node

Warning

Note you may need to do step #5 multiple times until you don't get error. of Daemon failed to start in 15.0 seconds , Gensyn is quite unstable right now. I usually need to try 5 to 10 times on a bad day

image

If running is succesful you will see these, locate your ORG ID and Peer ID and remember it.

image

Go to: https://quickpod.github.io/gensyn

Note

Gensyn now uses a new swarm system called reasoning-gym instead of math problems. Old swarms are deprecated. New swarms will show 0 score at start.

image


9. Backup Your Identity

Warning

Save swarm.pem locally to reconnect later with the same identity.

  1. Right-click swarm.pem
  2. Click Download

image


Note

Your node will stay running even if you close the browser. To check on it later, just reconnect to JupyterLab.

About

Gensyn RL-Swarm on QuickPod

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •