Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore how to build AI models like LLMs, image classifiers, and speech recognizers directly in Java and run them efficiently on GPUs through this 59-minute conference talk from Devoxx. Discover Project Babylon's experimental Code Reflection technology that enables you to define machine learning logic in plain Java code without requiring Python or external model files. Learn how the Foreign Function and Memory (FFM) API connects your Java code to native runtimes like ONNX Runtime for fast inference with GPU acceleration. Understand the Heterogeneous Accelerator Toolkit (HAT) and its developer-facing programming model for writing and composing compute kernels that allow Java libraries to harness GPU power for high-performance computing tasks. Gain insights into Babylon's upcoming features and how they bridge Java with modern AI workloads, whether you're interested in new Java capabilities or seeking practical approaches to integrate AI into your Java technology stack.
