Skip to main content

Burn Testing

Machines should be thoroughly tested before they are listed on the RunPod platform. Here is a simple guide to running a burn test for a few days.

Stop the RunPod agent by running:

sudo systemctl stop runpod

Then you can kick off a gpu-burn run by typing:

docker run --gpus all --rm jorghi21/gpu-burn-test 172800

You should also verify that your memory, CPU, and disk are up to the task. You can use the ngstress library to accomplish this.

When everything is verified okay, start the RunPod agent again by running

sudo systemctl start runpod

Then, on your machine dashboard, self rent your machine to ensure it's working well with most popular templates.