In October, the TornadoVM team from UNIMAN gave two talks at Devoxx Belgium!
The first talk was a deep dive on TornadoVM, explaining the programming model, the API and the TornadoVM tool ecosystem! The video of the deep dive is available on YouTube.
The second talk included a live coding demo by Michalis Papadimitriou, showing Java-native GPU acceleration for an open-source LLM inference engine, GPULlama3.java. The video of this talk is available on YouTube.
