AI Server

Learn how to use the DeGirum AI Server to efficiently host your hardware with local or cloud models.

Estimated read time: 4 minutes

You should use the DeGirum AI server when you want to:

• Use models from the DeGirum AI Hub while running inference on local Hailo accelerators.

• Serve models from on-device storage for fully offline or LAN-hosted operation.

If you want to set HAILO_MONITOR=1 and you plan to use an AI Server started as a service, add Environment="HAILO_MONITOR=1" under [Service] in /etc/systemd/system/degirum.service, then reload the daemon.

Continue to Inference with cloud models or Inference with local models to learn more about using a DeGirum AI server.