JavaConference50min
Now and Next Java for AI
The session demonstrates how Java developers can directly run AI models using JDK 25’s Foreign Function and Memory API, integrating with native runtimes like ONNX for CPU/GPU inference. It also previews Project Babylon’s code reflection, enabling pure Java, accelerator-ready AI models without external files or glue code.
Ana-Maria MihalceanuOracle
Tired of treating AI like a black-box REST endpoint? What if you could own the stack: shape the tensors, steer memory, pick execution providers?
In this session, we make that shift. Today, with JDK 25, you can wire real models - LLMs, image classifiers, or object detection algorithms - straight from Java via the Foreign Function and Memory API to call native runtimes like ONNX for fast CPU/GPU inference. You will learn how to map tensor buffers to Java MemorySegment, how to flip execution providers, and have a self-contained Java application. Around the corner, developments in Project Babylon and others will continue to push the boundaries and offer even greater interactions of the JVM with the outside world. We touch on what such a future might mean to Java developers with Project Babylon’s code reflection: express model logic as Java code that Babylon can analyze and lower to accelerator backends, skipping external model files or the need for a glue language.
Build expressive and testable FFM-based inference today and author pure Java AI-ready models with code reflection tomorrow!
In this session, we make that shift. Today, with JDK 25, you can wire real models - LLMs, image classifiers, or object detection algorithms - straight from Java via the Foreign Function and Memory API to call native runtimes like ONNX for fast CPU/GPU inference. You will learn how to map tensor buffers to Java MemorySegment, how to flip execution providers, and have a self-contained Java application. Around the corner, developments in Project Babylon and others will continue to push the boundaries and offer even greater interactions of the JVM with the outside world. We touch on what such a future might mean to Java developers with Project Babylon’s code reflection: express model logic as Java code that Babylon can analyze and lower to accelerator backends, skipping external model files or the need for a glue language.
Build expressive and testable FFM-based inference today and author pure Java AI-ready models with code reflection tomorrow!
Ana-Maria Mihalceanu
Ana is a Java Champion Alumni, Developer Advocate for the Java Platform Group at Oracle, guest author of the book "DevOps tools for Java Developers", and a constant adopter of challenging technical scenarios involving Java-based frameworks and multiple cloud providers. She actively supports technical communities' growth through knowledge sharing and enjoys curating content for conferences as a program committee member. To learn more about/from her, follow her on Twitter @ammbra1508.
comments.speakerNotEnabledComments