Imagine building AI models like LLMs, image classifiers, or speech recognizers, directly in Java, and running them fast on your GPU.

Project Babylon introduces the experimental Code Reflection technology that lets you define machine learning logic in plain Java code, without needing Python or external model files. It then uses Foreign Function and Memory (FFM) API to connect your code to native runtimes like ONNX Runtime for fast inference, including GPU acceleration. On top of this, Heterogeneous Accelerator Toolkit (HAT) allows developers to write and compose compute kernels, in order to offload high-performance computing tasks to the GPU power in a more general way.

In this session, we’ll introduce you to Babylon’s upcoming features, and how they bridge the worlds of Java and modern AI workloads. For those curious about new Java features or looking for practical ways to bring AI into your Java stack, join us for a first look at Babylon’s vision for Java and machine learning.