Designed to ease the development of ML/AI applications in the Cloud-Edge-IoT Continuum, COMPSs is a task-based programming model that orchestrates the execution of such tasks in a serverless manner on top of any distributed platform. PyCOMPSs is an enhanced version of the programming model exploiting the benefits of the Python programming language. DisLib provides application developers with a set of built-in AI algorithms that uses PyCOMPSs to distribute computation.

The AI-SPRINT framework and PyCOMPSs are more flexible than existing programming solutions as they address most of the challenges related to the composition of AI applications and their deployment and execution on the edge with transparent offloading to cloud platforms depending on load and constraints requirements. Specific highlights are also put on security and QoS in the definition of the AI-SPRINT framework. In particular, dislib, a library which includes ML algorithms implemented in COMPSs able to run on distributed computing platforms, provides ready-to-use parallel models.

From the runtime point of view, AI-SPRINT manages the distribution, parallelism and heterogeneity across edge/cloud resources transparently to the application developer.