Overview
@zerogpu/worker is the ZeroGPU edge worker for servers. Each running worker joins the network as one device: it registers with your SDK key, downloads its assigned models, and serves inference tasks. Its connection to ZeroGPU is outbound only.
It ships two ways:
Requirements
Install and run
- Docker
- npm
Store the key as a secret and mount it, then run the image with a volume for models and one for the device’s identity:On an NVIDIA host, use
zerogpu/worker:cuda and add --gpus all.Configuration
The inference a worker serves is attributed to the app your SDK key belongs to.
Check a worker
The worker serves a health endpoint on its local port (default8080):
ready turns true once a model is loaded and warmed up. network.completedTasks counts tasks ZeroGPU sent to this worker. Keep the local port inside your own network; never expose it to the internet.
Stop
SendSIGTERM (docker stop does this). The worker leaves the network, unloads its models, and exits within about 5 seconds.
Once workers are online, verify they’re connected and track earnings.

