Lightnews — Scholar-powered news

Reposted by TornadoVM

AERO Project @aero-project.eu · 17h

🧩 #MPLR2025: #TornadoInsight - #IntelliJ plugin for #TornadoVM.
Detects incompatible #Java constructs & offers instant feedback for accelerator programming.
📄 zenodo.org/records/1695...
Repository: github.com/beehive-lab/...
JetBrains Marketplace: plugins.jetbrains.com/plugin/23309...

Dynamic and Static Code Analysis for Java Programs on Heterogeneous Hardware

The increasing prevalence of heterogeneous computing systems, incorporating accelerators like GPUs, has spurred the development of advanced frameworks to bring high performance capabilities to managed...

zenodo.org

1 5 6

Reposted by TornadoVM

AERO Project @aero-project.eu · 17h

📊 #MPLR2025: #TornadoViz - visual analytics for #TornadoVM.
Explore task dependencies, memory ops & #performance across CPUs/#GPUs interactively.
📄 zenodo.org/records/1695...
Repository: github.com/beehive-lab/...

TornadoViz: Visualizing Heterogeneous Execution Patterns in Modern Managed Runtime Systems

With the increasing prevalence of machine learning and large language model (LLM) inference, heterogeneous computing has become essential. Modern JVMs are embracing this transition through projects su...

zenodo.org

1 2 3

Reposted by TornadoVM

AERO Project @aero-project.eu · 17h

Next week at #MPLR2025 & #VMIL2025 in Singapore!
We are excited to share that our partners from @manchester.ac.uk University of Crete and #RedHat are presenting 4 #research outcomes on #Java, #TornadoVM, #GC and #tools.

#horizoneurope

@hipeac.bsky.social
@eucloudedgeiot.bsky.social

👇

1 5 9

Reposted by TornadoVM

Christos Kotselidis @kotselidis.net · 1d

In less than two hours @mikepapadim.bsky.social will demo state-of-the-art native #Java #AI inference on GPUs at @devoxx.com
Based on @tornadovm.org and the @graalvm.org compiler, 𝗚𝗣𝗨𝗟𝗹𝗮𝗺𝗮𝟯.𝗷𝗮𝘃𝗮 enables GPU inference of LLM models with high performance and integration with @langchain4j.dev!

5 7

Reposted by TornadoVM

Thanos Stratikopoulos @stratika.bsky.social · 2d

The #TornadoVM team at #Devoxx!

Credits to Dimitris Doutsiopoulos for this amazing capture!

5 6

TornadoVM @tornadovm.org · 2d

The #TornadoVM deep dive session is live on YouTube!
👉 youtu.be/WNQ5ylMs4Ok?...

Next up: GPULlama3.java at #Devoxx with live coding demo showing Java-native GPU acceleration! -

🗓 Tomorrow (Oct 9) | 🕔 17:40–18:30 | 📍 Room 6
Don’t miss it!

#opensource #Java #AI #GPU

TornadoVM Deep Dive: Empowering Java Developers with GPU Acceleration by Thanos Stratikopoulos, Ch

YouTube video by Devoxx

youtu.be

4 9

Reposted by TornadoVM

Christos Kotselidis @kotselidis.net · 2d

Project Panama is a key component for transitioning #Java into the #AI era! @tornadovm.org has been among the early adopters of Panama. Thanks @nipafx.dev for the excellent talk @devoxx.com and the shoutout!

8 14

TornadoVM @tornadovm.org · 3d

Behind the cameras! @kotselidis.net and @mikepapadim.bsky.social discussing with @frankdelporte.be about our technology at #Devoxx and how it can be used for fast #AI in #Java! The video is coming soon…

@devoxx.com

8 12

Reposted by TornadoVM

AERO Project @aero-project.eu · 3d

The #TornadoVM team from the University of Manchester is at @devoxx.com Belgium! Don’t miss it, join them to learn more about #Java #GPU acceleration and the work done in the context of our project for the #EU hardware ecosystem!

#opensource

5 7

Reposted by TornadoVM

Thanos Stratikopoulos @stratika.bsky.social · 3d

Yesterday at the #TornadoVM deep dive, we presented #TornadoInsight - an #opensource IntelliJ plugin that helps devs learn the TornadoVM API via static analysis & dynamic inspection.

Extended in the P2Code project and coming to #MPLR2025 next week!

#Devoxx

youtu.be/WNQ5ylMs4Ok?...

TornadoVM Deep Dive: Empowering Java Developers with GPU Acceleration by Thanos Stratikopoulos, Ch

YouTube video by Devoxx

youtu.be

5 5

Reposted by TornadoVM

Thanos Stratikopoulos @stratika.bsky.social · 4d

Good morning from #Devoxx Belgium and the @tornadovm.org team!

Our #TornadoVM deep dive talk is today at 13.30 in Room 4.

#opensource #Java #AI #GPU

7 11

Reposted by TornadoVM

Christos Kotselidis @kotselidis.net · 8d

GPULlama3.java our first GPU-accelerated Java-native LLM inference engine with #TornadoVM has officially been integrated to LangChain4J! Congratulations to the whole team for this achievement!
Next week @devoxx.com we will showcase our demos as well as provide a deep dive on @tornadovm.org!

1 10 22

Reposted by TornadoVM

Thanos Stratikopoulos @stratika.bsky.social · 8d

Java + GPUs + AI = TornadoVM

We’re speaking at #Devoxx 2025! I will be there along with @mikepapadim.bsky.social @maryxek.bsky.social and @kotselidis.net for a deep dive on #TornadoVM!

📅 Oct 6 | 13:30–16:30 | Rm 4

@eucloudedgeiot.bsky.social
@aero-project.eu

#Java #AI #GPU #opensource

5 9

Reposted by TornadoVM

GraalVM @graalvm.org · 16d

TornadoVM Deep Dive

This session will explore how @tornadovm.org extends GraalVM to unlock GPU acceleration, covering parallelism, integration with existing tooling, and a live demo optimizing an LLM pipeline.

m.devoxx.com/events/dvbe2...

3 4

Reposted by TornadoVM

Thanos Stratikopoulos @stratika.bsky.social · Sep 5

Docker images of GPULlama3.java v0.2.0 for NVIDIA #GPUs are now ready in DockerHub!

OpenCL image: hub.docker.com/r/beehivelab...

PTX image:
hub.docker.com/r/beehivelab...

2 4

Reposted by TornadoVM

Christos Kotselidis @kotselidis.net · Aug 17

Checkout the latest podcast from @mikepapadim.bsky.social on GPULlama3.java; our latest #Java #AI inference framework accelerated with @tornadovm.org!

5 5

Reposted by TornadoVM

Thanos Stratikopoulos @stratika.bsky.social · Sep 5

New #GPULlama3.java release, bringing expanded model support, cross-platform GPU inference, and upcoming #LangChain4j integration.

Demo is preparing for @devoxx.com: lnkd.in/dfbV_tSU

Checkout the release 👉 github.com/beehive-lab/...

#opensource #Java #AI #TornadoVM

@aero-project.eu

Release v0.2.0 · beehive-lab/GPULlama3.java

Model Support Mistral – support for GGUF-format Mistral models with optimized GPU execution. Qwen2.5 – GGUF-format Qwen2.5 models supported, including performance improvements for attention layers...

github.com

6 10

Reposted by TornadoVM

Hackernews Top Stories @news.facts.dev · Jun 15

⚡ Hackernews Top story: GPU-accelerated Llama3.java inference in pure Java using TornadoVM

GitHub - beehive-lab/GPULlama3.java: GPU-accelerated Llama3.java inference in pure Java using TornadoVM.

GPU-accelerated Llama3.java inference in pure Java using TornadoVM. - GitHub - beehive-lab/GPULlama3.java: GPU-accelerated Llama3.java inference in pure Java using TornadoVM.

github.com

8 12

Reposted by TornadoVM

Thanos Stratikopoulos @stratika.bsky.social · Aug 6

A deep dive talk about #TornadoVM, an #opensource #Java technology for hardware acceleration will be part of the @devoxx.com program! #DevoxxBE

Join us to learn more about the technology!

And do not miss, a 2nd talk on how TornadoVM can offer GPU-accelerated inference in Java! 🚀

Christos Kotselidis @kotselidis.net · Aug 6

Super excited to give a deep dive talk on @devoxx.com 2025!

We will give a deep dive presentation on the internals of @tornadovm.org and explain how #Java developers can harness the power of #GPUs!

See you all in Belgium at fall!

3 9

Reposted by TornadoVM

Christos Kotselidis @kotselidis.net · Aug 6

Super excited to give a deep dive talk on @devoxx.com 2025!

We will give a deep dive presentation on the internals of @tornadovm.org and explain how #Java developers can harness the power of #GPUs!

See you all in Belgium at fall!

3 8

TornadoVM @tornadovm.org · Jul 10

Docker images now available for TornadoVM v1.1.1!

See here how to run:
👉https://github.com/beehive-lab/docker-tornadovm

These images support #NVIDIA #GPUs or #Intel #GPUs, making it easier than ever to get started with heterogeneous computing using #TornadoVM.

#containers #Java #acceleration

5 4

TornadoVM @tornadovm.org · Jul 7

New TornadoVM release v1.1.1!

Packed with new features and optimizations that unlock GPU acceleration for Llama3 in pure Java!

🧬JIT-compiled kernels for high performance.
👏 Thanks to our amazing contributors.

👉 github.com/beehive-lab/...

#opensource #AI #LLM #Java #TornadoVM

3 8

Reposted by TornadoVM

Thanos Stratikopoulos @stratika.bsky.social · May 30

A great milestone achieved by our team. Just released #GPULlama3.java, the first Java implementation of Llama3 inference accelerated on GPUs via #TornadoVM.

GitHub v0.1.0-beta: github.com/beehive-lab/...

Looking forward to your feedback.
#opensource #Java #AI #LLM #GPUs

1 7 14

Reposted by TornadoVM

Christos Kotselidis @kotselidis.net · May 30

Very proud of this work! At the 30th anniversary of our beloved #Java we release the first Llama 3 inference engine written in pure Java and accelerated on GPUs with TornadoVM!

Super excited to be part of Java’s transition into the #AI world!

Thanos Stratikopoulos @stratika.bsky.social · May 30

A great milestone achieved by our team. Just released #GPULlama3.java, the first Java implementation of Llama3 inference accelerated on GPUs via #TornadoVM.

GitHub v0.1.0-beta: github.com/beehive-lab/...

Looking forward to your feedback.
#opensource #Java #AI #LLM #GPUs

5 8

Reposted by TornadoVM

AERO Project @aero-project.eu · May 15

We are in the #RISCVSummitEurope hosted in Paris, presenting the work fostered in our project from the University of Manchester and @codeplaysoftware.bsky.social for accelerating #Java workloads on #RISCV with autovectorization. 🚀

#TornadoVM and #oneAPIConstructionKit are #opensource!

4 5