the development of infrastructure for text document processing. The paper discusses related technologies, the CLARIN-PL infrastructure architecture, and implementations of small and large language models. The emphasis is on model formats, data precision, and runtime environments (GPU and CPU). It identifies optimal solutions through extensive experimentation. In addition, the paper advocates for a more comprehensive performance evaluation approach. Instead of reporting only average token throughput, it suggests considering the curve’s shape, which can vary from constant to monotonically increasing or decreasing functions. Evaluating token throughput at various curve points, especially for different output token counts, provides a more informative perspective.

implementation of modern deep learning algorithms. Hence, the concept of intelligent agent is introduced. A case study with a set of intelligent agents designed to handle real-world events related to environmental data monitoring is presented. The results of the case study discussion indicate a reasonable scale for tuning the Event Processing Element (EPA) topology with correct responses and the required output performance level. These results have important implications for the practical implementation of the EPA structure, i.e., the use of GPUs in CEP systems. Finally, the results of performance analysis of different implementations of intelligent agents are presented and discussed.