Skip to content


The DeGirum AI Inference Software Development Kit, PySDK, is a Python package which provides APIs to perform inference on ML models.

PySDK consists of the following components:

  1. PySDK library, which includes the following essential modules:

  2. The CoreClient extension module implementing APIs to work with DeGirum AI accelerator cards installed locally

  3. The aiclient extension module implementing APIs to work with DeGirium AI servers running on remote systems
  4. The degirum.server module - helper module that allows launching AI server on a local AI hardware to be used by remote clients.
  5. The degirum console script implementing command-line interface to various PySDK management facilities.

The PySDK package provides the necessary tools to support the following use cases:

  • Local Inference: perform AI inferences on the local system using DeGirum AI accelerator hardware installed on the same system
  • AI Server Hosting: deploy the system with installed DeGirum AI accelerator hardware as AI server
  • AI Server Inference: connect to one or several AI servers and perform AI inferences on those servers remotely
  • Cloud Inference: connect to DeGirum Cloud Platform and perform AI inferences in the cloud

Documentation References

For the list of supported operating systems, CPU architectures, and Python versions please refer to PySDK Supported Configurations table.

For PySDK installation instructions please refer to PySDK Installation Guide

For AI Server installation and configuration instructions please refer to AI Server Configuration Guide