Thanos Stratikopoulos
@stratika.bsky.social
Research Fellow at The University of Manchester, #TornadoVM Team.
Our #Java #AI inference engine just got another major update with a huge performance leap and native #CUDA integration!
TornadoVM@tornadovm.org · last wk.GPULlama3 v1.0.0 is out - now #CUDA-native ⚡ ✅ TornadoVM CUDA backend w/ tensor-core (MMA) batch prefill ✅ FP16 & Q8_0 · Llama, Qwen, Devstral & more models ✅ An OpenAI-compatible server (llama-tornado --server) Pure #Java. No JNI. github.com/beehive-lab/GPULlama3.java #opensource #AI #LLM #GPU
Great effort and what an achievement! #LLM inference implemented in #Java, automatically accelerated on #GPUs with #TornadoVM & CUDA native support! #opensource #AI #Java #GPU
TornadoVM@tornadovm.org · last wk.GPULlama3 v1.0.0 is out - now #CUDA-native ⚡ ✅ TornadoVM CUDA backend w/ tensor-core (MMA) batch prefill ✅ FP16 & Q8_0 · Llama, Qwen, Devstral & more models ✅ An OpenAI-compatible server (llama-tornado --server) Pure #Java. No JNI. github.com/beehive-lab/GPULlama3.java #opensource #AI #LLM #GPU
The final release of the AERO software stack is here! Our new v2.0 leaflet showcases how we've optimized cloud deployments on top of the EU processor designs & accelerators. 📄 Get the brochure: aero-project.eu/posts/aero-v... #OpenSource #cloud @hipeac.bsky.social @euprojectpulse.bsky.social
AERO v2.0 – June 2026 - AERO at a glance
AERO-Software-Stack-Leaflet-v2.0Download AERO-Software-Stack-Leaflet-v2.0 Presentation PPTXDownload
aero-project.eu
New results presented at #IOLTS2026 by the Dept. of Information Engineering, Università di Pisa! Our work shows how #ARM #SVE accelerates Microsoft SEAL, boosting CKKS #homomorphicencryption performance. 👉 aero-project.eu/posts/aero-i... #Cybersecurity #Research
JVM Weekly by @askowronski.bsky.social features @tornadovm.org 5.0.0 release that brings native CUDA support (cuBLAS, cuDNN, etc.) via the new Hybrid API. Same hardware-agnostic Java, can be extended for AMD & Apple Metal libraries. www.linkedin.com/pulse/java-g... #Java #GPU #TornadoVM #opensource
Java gets a Movie, Jakarta Gets an AI Rewrite, and CUDA catches the Tornado(VM) - JVM Weekly vol. 184
A documentary about who actually built Java, an AI agent that reimplemented Jakarta EE from the spec, and TornadoVM conceding that portability has limits. Before we jump in, a quick note: I was away l...
linkedin.com
It’s been a busy week in the #Java ecosystem ➤ The GA release of TornadoVM 5.0; point releases of JHipster, Keycloak and Google ADK; maintenance releases of GraalVM Native Build Tools and Micronaut; the OmniFish Build of Payara and introducing Vidocq, and more. 🔗 #InfoQ News Roundup: bit.ly/4pq19Bl
TornadoVM has officially transitioned into a new phase. One line of code, > 150x performance. Becoming #CUDA native unlocks new potentials for high performance #Java #AI inference with zero dependencies. Checkout our latest release, blogs, and new website 👇
TornadoVM@tornadovm.org · 4w agoTornadoVM 5.0.0 is CUDA-native. One line of #Java. 74× faster. TornadoVM's Hybrid API drops a native cuBLAS call straight into a TaskGraph - same buffers, same #CUDA stream, zero host round-trips. ⚡ Run with the Hybrid API: bit.ly/4vqL7sq 📖 Full engineering deep dive: bit.ly/44VecBf #AI #GPU
TornadoVM 5.0.0 beacons a very important milestone: Native CUDA support! JIT-compiled Java kernels and native cuBLAS/cuDNN/cuFFT calls now live in the same task graph - same GPU buffers, same CUDA stream, no round-trips between them. #opensource #Java #TornadoVM #GPU #AI 👇
TornadoVM@tornadovm.org · 4w agoTornadoVM 5.0.0 is CUDA-native. One line of #Java. 74× faster. TornadoVM's Hybrid API drops a native cuBLAS call straight into a TaskGraph - same buffers, same #CUDA stream, zero host round-trips. ⚡ Run with the Hybrid API: bit.ly/4vqL7sq 📖 Full engineering deep dive: bit.ly/44VecBf #AI #GPU
#LangChain4j 1.17.0 is out! 🎉 github.com/langchain4j/...
Release 1.17.0 and 1.17.0-beta27 · langchain4j/langchain4j
Notable Changes Introduce new Debate agentic pattern by @mariofusco in #5382 Allow a tool to declare its compensating action and invoke it when it fails by @mariofusco in #5171 Add Oracle Database...
github.com
Final month of #AERO - and we're not slowing down! Run GPU-accelerated LLMs in pure Java from a @quarkus.io #Langchain4j apps. No Python. No CUDA. Just #Java with @tornadovm.org. A collab between @manchester.ac.uk & Red Hat! 🔗 aero-project.eu/posts/runnin... #Java #LLM #AI #LLM #GPU #opensource
Last week I was in Sofia for @jprimeconf.bsky.social! I presented our latest work on @tornadovm.org and #GPULlama3 for seamless #GPU acceleration of local #AI inference with @quarkus.io and @langchain4j.dev. Thanks to organizers, speakers, attendees & photographers for a great event. #opensource
A well presented overview on getting faster startup, warmup, memory footprint in #Java along with a comparison of all existing solutions delivered by @hansolo.eu at #jprime2026
Really interesting talk at #jPrime2026 from @kevindubois.com on @quarkus.io @langchain4j.dev and how to create #AI infused applications. I have kept a special note on dynamic model selection and non-AI agents for more deterministic tasks. #Java #AI
Great start in #jPrime2026, featuring a playful way of learning modern #Java by @piotrprz.bsky.social and @maritvandijk.bsky.social!
Excited to attend #jPrime2026 in Sofia this week! Looking forward to sharing our work on #GPULlama3, @tornadovm.org and their integration with @quarkus.io @langchain4j.dev. Join me on Thursday (4/6) at 14:05, in Hall A: jprime.io/agenda/275 #jPrime26 #Java #GPUs #AI #TornadoVM
This week, Mary Xekalaki @maryxek.bsky.social presents the latest work at #ICPE2026! “Pulse: A Profiling & Visualization Infrastructure for Heterogeneous Managed Systems” 📅 Thu, May 7 🕒 14:40–15:00 🔗 github.com/beehive-lab/... 📄 zenodo.org/records/1895... #opensource #Java #GPU #TornadoVM
GitHub - beehive-lab/TornadoVMPulse: A quick analyzer for TornadoVM's profilling logs
A quick analyzer for TornadoVM's profilling logs. Contribute to beehive-lab/TornadoVMPulse development by creating an account on GitHub.
github.com
TornadoVM@tornadovm.org · 5mo agoNew paper accepted at #ICPE2026! We present TornadoVMPulse, a profiling & visualization tool for #TornadoVM to analyze and optimize #Java apps on #GPUs. Results for #GPULlama3: ⚡ 18.4% faster execution 📉 38% lower data-transfer cost 🇪🇺 @aero-project.eu 📍 Florence, May26 zenodo.org/records/1895...
TornadoVM team at @devoxxgreece.bsky.social Great discussions, insightful sessions, and a fantastic community pushing the boundaries of high-performance #Java and #GPUs. 📸 Photo credit: @ddoutsiopoulos.bsky.social
Last week we gave two presentations at #OCX26 and @devoxxgreece.bsky.social - and the recordings are now available, scan the QR code! From open-source evolution to running LLMs on GPUs directly from Java - there’s a lot to explore. Stay tuned for more! #opensource #Java #TornadoVM #AI #LLM #GPUs
Great to see this work from the TornadoVM team! As part of the AERO project, we’re excited to support open-source innovation that pushes the boundaries of running local LLMs on GPUs directly from #Java. @euprojectpulse.bsky.social @hipeac.bsky.social @eucloudedgeiot.bsky.social #opensource
TornadoVM@tornadovm.org · 3mo agoLast week we gave two presentations at #OCX26 and @devoxxgreece.bsky.social - and the recordings are now available, scan the QR code! From open-source evolution to running LLMs on GPUs directly from Java - there’s a lot to explore. Stay tuned for more! #opensource #Java #TornadoVM #AI #LLM #GPUs
TornadoVM is featured in the latest Java Pro Magazine special issue (“Java in the Age of AI”, April 2026). 📌https://javapro.io/wp-content/uploads/2026/04/JAVAPRO_04-2026.pdf#page=42 @hipeac.bsky.social @euprojectpulse.bsky.social @eucloudedgeiot.bsky.social #horizoneurope #opensource #community
TornadoVM@tornadovm.org · 3mo agoTornadoVM is featured in the April 2026 issue of Java Pro Magazine - “Java in the Age of AI”! 👉 javapro.io/wp-content/u... In this article, @mikepapadim.bsky.social shared our experiences on building #GPU accelerated #LLM inference libraries with #TornadoVM. #Java #community #AI
TornadoVM is featured in the April 2026 issue of Java Pro Magazine - “Java in the Age of AI”! 👉 javapro.io/wp-content/u... In this article, @mikepapadim.bsky.social shared our experiences on building #GPU accelerated #LLM inference libraries with #TornadoVM. #Java #community #AI
How did @azulsystems.bsky.social #Zulu become part of Docker's Official Images for Java? @frankdelporte.be writes about the journey and its meaning for developers. foojay.io/today/the-ro... #Java #Docker
The Road to Docker Official Images for Java: The Azul Zulu Story
foojay is the place for all OpenJDK Update Release Information. Learn More.
foojay.io
Happening now! Meeting with the Quarkus team at @devoxxgreece.bsky.social ! #opensource #Java #cloud #native
Java action movies are easily filling cinemas 😀 Thank you for attending my #jcon session, 'Livecoding: Creating Beautiful Java Code with LLM and Agents', as well as for your questions and conversations. 👇
We are at #OCX26 this week! Yesterday, Thanos Stratikopoulos from University of Manchester presented the #opensource practices used in @tornadovm.org project for resulting into a production ready software! Stay tuned for more! @euprojectpulse.bsky.social #opensource #cloud #GPU #Java #TornadoVM
On my way to Brussels 🇧🇪 for #OCX2026 “TornadoVM: From Academia to Open Source Success” 🕓 Tomorrow, 16:00–16:45 | 📍 Studio 4 👉 www.ocxconf.org/event/2026/a... Let’s connect if you’re there! @tornadovm.org #OpenSource #Java #TornadoVM
Use command completion (..) in @intellijidea.com to refactor and transform code. It offers all relevant actions to your context, so you can keep moving forward. www.youtube.com/watch?v=Hmpp...
Refactor and transform code with command completion
Join us: Website: https://jb.gg/website Blog: https://jb.gg/blog X: https://twitter.com/intellijidea Bluesky: https://bsky.app/profile/intellijidea.com LinkedIn:…
youtube.com
Great to see external contributions driving real progress! Native #GPU support on Apple Silicon with Metal unlocked by #TornadoVM has enabled running Devstral 2 models directly on-device — a big step forward for performance and accessibility. This is exactly what makes #opensource so powerful!
Adam Bien@adambien.blog · 4mo agoI have just migrated a Python launch/configuration script to Java 25, and I have asked an LLM to review it 👇
