This paper covers a study on the performance of various machine learning model inference runtimes including Tenserflow Serving and PyTorch Serve as well as NVIDIA Triton with either of these as the backend.
The paper was written by Egi Brako based on his bachelor’s thesis, which he had wr...
An important aspect of working as a scientist is writing things down.
In order to later on understand one’s notes and to reproduce one’s work, these notes should have a system.
Moreover, when working in science for years, one might need to go back to look at past notes as some problems keep showin...
PykeBot2 is a Discord bot that I had developed in order to easily determine how skilled opponents in a given League of Legends tournament would be.
When I was playing League of Legends in an amateur team in the German university league we would often participate in tournaments hosted via Toorname...
About Me
Dr. Jonathan Decker
Jonathan Decker takes the role of a system architect with a focus on designing systems that enable new and novel ways of utilizing Cloud and HPC resources, while also being efficient, secure and scalable.
Most notably, he strives to combine HPC with Kubernetes to get the best of both worlds.
Jonathan completed his PhD in 2025 via his work on Chat AI and its underlying AI inference platform, which now enables secure and sensitive access to AI services for students and researchers across Germany.
Moreover, in 2025, he served as the speaker of the PhD student representatives of the Georg-August-University of Göttingen.
Now he heads a team in the High-Performance Storage research group of Prof Kunkel while being in close collaboration with the GWDG.
There he handles research, supervision of PhD students and university teaching activities.