We're very excited to announce ISMM'25, co-located with PLDI in Seoul, South Korea. ISMM is the top venue dedicated to all things memory management. If you're working with memory, consider submitting! The submission link and CFP are here: conf.researchr.org/home/ismm-2025

Blazing fast #Java matrix multiply👇

TornadoVM leads the way for AI in the Java ecosystem. Matrix-multiply is critical for LLM performance. Just like Truffle this is powered by the Graal compiler. #java4ai

🚀 Blog Part 2 is available! A deep dive into accelerating the Period Search algorithm for the ESA Gaia mission. Discover how we optimized its performance with #GPUs and #TornadoVM on EU processor. 👉 Read Part 2: aero-project.eu/posts/aero-pil… Horizon Europe 🇪🇺 HaDEA @UKRO SBFI SEFRI SERI

Don’t miss this opportunity to interact with us and our sister projects at HiPEAC! #HIPEAC25 👉hipeac.net/2025/barcelona… HaDEA

Glad to participate in this workshop, to present the work that we do in AERO to optimize #TornadoVM for the EU processor ecosystem. We will highlight the results through the collaboration between Computer Science @ The University of Manchester, Codeplay Software and RedHatJava!

Moving to bsky.app/profile/kotsel… See you there!

We are proud to release the first fully JITed, open-source GPU-accelerated Llama3 inference in pure Java powered by #TornadoVM  🚀 🎯 NVIDIA GPUs using PTX and OpenCL backend 👉 github.com/beehive-lab/GP… We are looking forward to your feedback!  #opensource #Java #AI #LLM #GPUs

GPULlama3.java Brings GPU-Accelerated LLM Inference to Pure Java bit.ly/44vmLmQ by A N M Bazlur Rahman 🇧🇩🇨🇦

The University of Manchester team extended Alfonso² Peterssen☕'s Llama3.java (github.com/mukel/llama3.j…) with GPU support via the GraalVM JIT and TornadoVM: infoq.com/news/2025/06/g… Nicely done!👏

First integration of GPULlama3.java with LangChain4j. Now, you can compile and run pure-Java inference on GPUs with TornadoVM for Llama3, Mistral, Qwen2.5/3 and Phi-3 github.com/langchain4j/la… github.com/langchain4j/la…

#Java + #GPUs + #AI = #TornadoVM We’re speaking at #Devoxx 2025! I will be there along with Michalis Papadimitriou Mary Xekalaki Christos Kotselidis for a deep dive on TornadoVM! 📅 Oct 6 | 13:30–16:30 | Rm 4 HiPEAC EUCloudEdgeIoT AERO P2CODE TANGO EU #opensource

Good morning from #Devoxx Belgium and the #TornadoVM team! Our #TornadoVM deep dive talk is today at 13.30 in Room 4. #opensource #Java #AI #GPU

My colleague Michalis Papadimitriou gives live #code demo with #TornadoVM at Devoxx Belgium! #opensource #software #Java #AI

Mary Xekalaki presenting how to write modern Java like a GPU expert with TornadoVM in Devoxx Belgium #java #ai #gpus

In today's Devoxx we presented how we use GraalVM to generate efficient GPU code with TornadoVM and GPULlama3.java #java #ai #llms

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 P2CODE, and coming to #MPLR25 next week! #Devoxx youtu.be/WNQ5ylMs4Ok?si…

Behind the cameras! Christos Kotselidis and Michalis Papadimitriou discussing with Frank Delporte #JavaOnRaspberryPi about our technology at Devoxx and how it can be used for fast #AI in #Java! The video is coming soon…

The #TornadoVM team at #Devoxx! Credits to dimitrisDoutsiopoulos for the amazing capture!

Yesterday I had the chance to present in Devoxx Belgium our work on building #GPULlama.java with TornadoVM . The first GPU-ready inference library in pure #Java that has no extra dependencies and it's fully integrated with LangChain4j . youtu.be/PO6wOtzUb3w