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

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?...

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

The Devoxx Belgium presentations from the first Deep Dive day are now available on each talk’s detail page and on our YouTube channel. Enjoy! 🍿👀 m.devoxx.com/events/dvbe25

My colleague @mikepapadim.bsky.social gives live #code demo with #TornadoVM at @devoxx.com ! #opensource #software #Java #AI

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

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!

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

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...

Good morning from Madrid! Ready for the second day of the Open Source Community Day workshop! Looking forward to connecting with other EU-funded #research projects working on #opensource! @eucloudedgeiot.bsky.social

Excited to present the AERO Project today at Open Source Community Day, Madrid 🇪🇸✨ Let’s talk about open collaboration, innovation, and the future of OSS. #AERO #OpenSource #CommunityDay

Open collaboration drives progress - excited to share how AERO is helping shape the future of OSS. #opensource #software

Check out what’s new in the world of #Java 👉 bit.ly/3VcJkYb JEP 517 proposed to target for JDK 26; TornadoVM; the September 2025 edition of the Payara Platform; point releases of Quarkus, Micronaut, Apache Kafka and Apache Tomcat; Grails 7.0 & Gradle 9.1; and more. #InfoQ #JavaUpdates

#GPULlama3.java keeps improving with larger model coverage, cross platform support, performance improvements and soon #LangChain4J integration! Stay tuned!

"Java, LangChain4J and Enterprise LLMs"--an airhacks.fm podcast conversation with @agoncal.bsky.social is ready to listen 👉 adambien.blog/roller/java_... #java #podcast #langchain #ai

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

#Devoxx Belgium 2025 : Java + AI + Agents I'm convinced this is the biggest European AI conference using Java 🔥 #Devoxx #AI #Java #Agents

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!

Huge congratulations to the Sednai team for their groundbreaking work on GPU-accelerated vector search with pgvector, showcased at Swiss PGDay! 👏 Slides: 👉https://www.pgday.ch/common/slides/2025_KREFL_SwissPGday2025_final.pdf #PostgreSQL #GPU #OpenSource @eucloudedgeiot.bsky.social

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

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

☕️🎙️"TornadoVM: The Need for GPU Speed"--an airhacks.fm podcast conversation with Michalis Papadimitriou is ready to listen 👉 adambien.blog/roller/torna... #podcast #java #tornadovm

📈 ACM Open: Fast Facts Did you know #OpenAccess articles published in the Digital Library receive 2-3x more downloads? Help your researchers achieve the reach they deserve. Learn more about #ACMOpen: bit.ly/46pctGj #Computing

The University of Manchester team extended @mukel.bsky.social's Llama3.java (github.com/mukel/llama3...) with GPU support via the GraalVM JIT and TornadoVM: www.infoq.com/news/2025/06... Nicely done!👏

Powered by TornadoVM🚀🚀🚀 www.infoq.com/news/2025/06... GPULlama3.java Brings GPU-Accelerated LLM Inference to Pure Java - InfoQ

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

GPU-accelerated Llama3.java inference in pure Java using TornadoVM Discussion

What a night that was! 🔥 Our 10 Years Anniversary went above and beyond our expectations! 🎉 A huge thank you to everyone who showed up, contributed, spoke, or simply joined us to be part of the moment. DevStaff is all about the people — and last night proved that once again!

The 2025 Managed Programming Languages & Runtimes Conference (MPLR) CFP is out and extended - June 24! Regardless of which managed language you use, if you come from industry or academia, or if you develop tools or compiler optimizations, MPLR has a track for you! conf.researchr.org/home/icfp-sp...

The Devoxx Belgium 2025 CFP is now OPEN! ➡️https://dvbe25.cfp.dev This year we’re zooming in on Java 25 & AI Agents🤖 Got insights, hacks, or bold ideas? Share them with the dev community at #Devoxx 🔥

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!

#SecOPERA #Chania

Really fun and interesting podcast with @adambien.blog. In this one we talk about the status of TornadoVM and all new changes, API design and optimisations we had to do to run LLMs more efficiently on integrated and discrete GPUs. 🎧https://airhacks.fm/#episode_346

"Accelerating LLMs with TornadoVM: From GPU Kernels to Model Inference" an airhacks.fm podcast conversation with Juan Fumero about TornadoVM and new meaning of "Write Once, Run Anywhere" is ready to download: adambien.blog/roller/accel... #java #podcast #tornadovm

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!

The #TornadoVM team in Paris! Attending the #RISCVSummitEurope and @encrypt_project to discuss our progress in accelerating FHE! #opensource #acceleration

Nice to be in Mallorca for our plenary meeting at the EU TANGO project! Looking forward for the discussions that will take place! We are working on expanding #TornadoVM to accelerate analytics with focus on energy efficiency! #opensource #green #computing #horizoneurope #ukri

TornadoInsight v1.2.5 is out! Now fully compatible with #IntelliJ 2024.3.5! Ready to supercharge #Java development on #GPUs with #TornadoVM. 🔗 JetBrains Marketplace: plugins.jetbrains.com/plugin/23309... 🔗 GitHub: github.com/beehive-lab/... This work has been developed in the P2Code project.

🌟 Big things are happening in the world of #Java! bit.ly/4clB9jQ The formal release of the Jakarta EE 11 Web Profile; the eleventh milestone release of GlassFish 8.0.0; point releases TornadoVM 1.1.0, Micronaut 4.8.0 and JHipster 8.10.0; and a new JEP candidate to remove the Applet API. #InfoQ

🚀 Learn how to accelerate performance on RISC-V CPUs using TornadoVM & vector instructions with OCK in my latest article. #Java #RISCV #Performance #OpenSource 🔗 jjfumero.github.io/posts/2025/0...

New release #TornadoVM v1.1.0 is out! Key highlights: ✅ Mixed precision computations (FP16 to FP32) ✅ New memory and buffer management features (persist & reuse data) 🔗https://github.com/beehive-lab/TornadoVM/releases/tag/v1.1.0 Thanks to all contributors! #opensource #Java #AI

We just released a new version of #TornadoVM: v1.1.0 Highlights: - New API calls to share and optimise device buffers - Multi-task graphs fine-grained executions - Support for FP16 and mixed precision computations - Memory management improvements - Extended Math library and much more!

Preprint is now available: 🔗 research.manchester.ac.uk/en/publicati... #riscv #java #acceleration #vectorization #tornadovm

The second day of our plenary started at Observatory premises of the University of Geneva! #opensource #software for #EU #hardware

We conclude our plenary meeting in Geneva with a photo of our consortium! Safe travels to everyone and thanks to the University of Geneva and Sednai for hosting us! Stay tuned!

Next week, all our partners will gather together in Geneva for our 4th physical plenary meeting! 🌍🇨🇭 Big thanks to the University of Geneva that will host our meeting. We can't wait to see everyone in person, exchange insights, and make meaningful progress together. Safe travels to everyone!

Excellent outcome of the #research collaboration between the University of Manchester and Codeplay Software! Exploring #vectorization on #RISCV architectures for #Java parallel workloads! The work has been accepted to be presented at #RISCVSummitEurope! #opensource #TornadoVM #OCK #acceleration

Our last paper is accepted at the #RISCV Summit Europe 2025! We evaluated Java parallel workloads expressed with #TornadoVM on real RISC-V CPUs using vector instructions generated by the oneAPI Construction Kit. How cool is this? Pre-print coming soon!

🚀 DARE SGA1 has launched! 🚀 A €240M and 38 partners initiative, to build #Europe’s first fully European #HPC & #AI stack—from #RISCV #processors to an optimized #software ecosystem. 🔗https://dare-riscv.eu/launch-of-dare-sga1-project/

Last week @kotselidis.net and myself presented the work we are doing to run and optimise Java/ #TornadoVM applications for RISC-V hardware accelerators in the #RISCV J-Group. See the slides: github.com/jjfumero/jjf... If you are interested in the topic, stay tune!