# TornadoVM

TornadoVM is a GPU programming framework for Java that JIT-compiles Java bytecode into CUDA, OpenCL C, and Apple Metal for heterogeneous hardware.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## A Glance at GPU Goodness in Java: LLM Inference with TornadoVM

DevFeed: [A Glance at GPU Goodness in Java: LLM Inference with TornadoVM](<https://devfeed.tech/articles/a-glance-at-gpu-goodness-in-java-llm-inference-with-tornadovm-23010.md>)

Original publisher: [Read original article](<https://www.javaadvent.com/2025/12/a-glance-at-gpu-goodness-in-java-llm-inference-with-tornadovm.html>)

Author: Edoardo Vacchi

Published: 2025-12-11T03:03:21Z

Content type: tutorial

Language: en

Sources: [Java Advent Calendar](<https://devfeed.tech/sources/java-advent-calendar.md>)

Topics: [TornadoVM](<https://devfeed.tech/topics/tornadovm.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Java](<https://devfeed.tech/topics/java.md>), [openjdk](<https://devfeed.tech/topics/openjdk.md>), [Programming](<https://devfeed.tech/topics/programming.md>)

Tags: [2025](<https://devfeed.tech/tags/2025.md>), [c-c-plus-plus](<https://devfeed.tech/tags/c-c-plus-plus.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [java](<https://devfeed.tech/tags/java.md>), [jdk](<https://devfeed.tech/tags/jdk.md>), [linux](<https://devfeed.tech/tags/linux.md>), [llama3](<https://devfeed.tech/tags/llama3.md>), [llm](<https://devfeed.tech/tags/llm.md>), [openjdk](<https://devfeed.tech/tags/openjdk.md>), [tornadovm](<https://devfeed.tech/tags/tornadovm.md>)

### AI overview

This tutorial introduces TornadoVM, an OpenJDK plugin that compiles annotated Java code for heterogeneous hardware, and explains how it can run LLM inference on GPUs. It covers installation, a basic GPU kernel, and the GPULlama3 project, which demonstrates running a Llama 3 model in Java with GPU acceleration.

### Source excerpt

It seems like it's become a tradition that I announce I have joined a new company for the Java Advent of Code. At least this time it's actually an old friend: I am excited to be back at Red Hat, in the llm-d team! Does that mean I forgot about Java? Of course not. If [...] The post A Glance at GPU Goodness in Java: LLM Inference with TornadoVM appeared first on JVM Advent.