Technical
Inference (Inferenz)
The runtime process of executing AI models to produce outputs.
Definition
The technical processes and infrastructure required to run pretrained AI models (notably large language models) to generate outputs; the strategy discusses providing inference capacity on state‑owned servers and integrating inference services into university applications and administration.
Related Terms
Inference
Technical processes and infrastructure for running AI models....
Infrastructure
Compute and storage resources like HPC and cloud services....
Infrastructure (AI layered model)
Compute, data centers and national platforms supporting AI....
High-performance computing (HPC)
Advanced computational infrastructure supporting AI research and deployment....
Foundational infrastructure
Core physical and virtual resources for data and AI....