Sign in

TornadoVM

@tornadovm.org
50 followers 16 following 32 posts

Official #TornadoVM - JIT Compiler & Runtime system for running JVM applications on heterogeneous hardware. www.tornadovm.org

PostsRepliesMedia
Reposted by TornadoVM
Christos Kotselidis @kotselidis.net · 4h
Our latest addition to the TornadoVM family. Blazing fast AI inference at native speed!
053
Reposted by TornadoVM
jitLLM @jitllm.io · 5h
Can Java compete with llama.cpp/ollama? YES! With @jitllm.io! jitLLM uses NVIDIA CUDA features and libraries (cuBLAS, cuDNN) and reaches 0.90× to 1.12× of llama.cpp's throughput! jitLLM is empowered by @tornadovm.org and will be soon in @langchain4j.dev and @quarkus.io. github.com/beehive-lab/...
094
TornadoVM @tornadovm.org · 6h
Next week we will be in @devoxx.com and speak about @tornadovm.org, @jitllm.io and how we accelerate Java on GPUs, using #NVIDIA native libraries! Come and talk to us, to learn more! #opensource #Java #AI #TornadoVM #jitLLM #GPU
075
TornadoVM @tornadovm.org · 22/09/2026
TornadoVM 7.0.0 is out! New TileContext API: Write #GPU kernels from #Java in tiles, not threads, via #NVIDIA #cuTile model. Now, cuTile methods can be mixed with cuBLAS functions in one TaskGraph, optimizing data transfers. 👉 github.com/beehive-lab/TornadoVM/releases/tag/v7.0.0 #opensource #AI
052
TornadoVM @tornadovm.org · 16/09/2026
Java 27 arrived yesterday! And we are compatible since Day-0! #opensource #Java #TornadoVM #GPU
042
Reposted by TornadoVM
Thanos Stratikopoulos @stratika.bsky.social · 04/09/2026
New #TornadoVM release, and it's JVMCI-free. 📌No more separate jdk25 branch, no back-syncing every PR from develop - one build for JDK 21–27. 📌Native code also migrated from JNI to Panama's FFM API - 7.5k lines of C++ gone. Kudos to all contributors! 👏 #opensource #Java #GPU #AI
053
Reposted by TornadoVM
Christos Kotselidis @kotselidis.net · 03/09/2026
TornadoVM is now modernized and forwards compatible with any JDK > 21 while receiving significant performance boosts! Can't wait to see those benefits translating to our AI inference engine in our next release!
022
TornadoVM @tornadovm.org · 02/09/2026
TornadoVM 6.0.0 is here - JVMCI-free and JNI-free. ✅ Compatible with any JDK 21-27 distribution. ✅ Cold start down 37%. ✅ 4.1× faster GEMM with Tensor-Core MMA. ✅ ~7,400 lines of C/C++ glue deleted. 📖 New blog: www.tornadovm.org/blogs/tornad... #Java #GPU #CUDA #TornadoVM #OpenSource #HPC #AI
075
Reposted by TornadoVM
Christos Kotselidis @kotselidis.net · 13/08/2026
The next TornadoVM release 6.0 will remove completely the dependency to JVMCI and will be onwards compatible. Babylon/HAT are complementary and we may integrate some parts when they are stable. Also we will soon land a PR to integrate with SpringAI! Your feedback is greatly appreciated!
187
Reposted by TornadoVM
Christos Kotselidis @kotselidis.net · 14/08/2026
Great news! Three talks accepted at @devoxx.com 2026! Hope to see you all and discuss the future of #Java and #AI!
042
TornadoVM @tornadovm.org · 14/08/2026
3 sessions accepted at @devoxx.com Belgium! 🛠️ Tools in Action: NVIDIA ecosystem from Java via #TornadoVM's Hybrid API 🎤 Talk: Building LLM inference engines in Java with TornadoVM 🧑‍💻 Hands-on Lab: From install to insight — a GPU lab for Java devs Stay tuned #Java #CUDA #LLM #AI #GPU #opensource
073
Reposted by TornadoVM
Christos Kotselidis @kotselidis.net · 28/07/2026
Our #Java #AI inference engine just got another major update with a huge performance leap and native #CUDA integration!
043
Reposted by TornadoVM
Thanos Stratikopoulos @stratika.bsky.social · 28/07/2026
Great effort and what an achievement! #LLM inference implemented in #Java, automatically accelerated on #GPUs with #TornadoVM & CUDA native support! #opensource #AI #Java #GPU
064
TornadoVM @tornadovm.org · 28/07/2026
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
073
Reposted by TornadoVM
AERO Project @aero-project.eu · 28/07/2026
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-project.eu
AERO v2.0 – June 2026 - AERO at a glance
AERO-Software-Stack-Leaflet-v2.0Download AERO-Software-Stack-Leaflet-v2.0 Presentation PPTXDownload
044
Reposted by TornadoVM
Thanos Stratikopoulos @stratika.bsky.social · 16/07/2026
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
linkedin.com
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...
084
Reposted by TornadoVM
InfoQ @infoq.com · 15/07/2026
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
066
Reposted by TornadoVM
Christos Kotselidis @kotselidis.net · 10/07/2026
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 👇
075
TornadoVM @tornadovm.org · 10/07/2026
TornadoVM 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
0134
Reposted by TornadoVM
AERO Project @aero-project.eu · 18/06/2026
The talk is now online! GPU-accelerated, local LLM inference in pure Java, from a #Quarkus #LangChain4j app. No Python. No CUDA. #TornadoVM 🔗 youtu.be/9YCRUwr7pO8 #horizoneurope @hipeac.bsky.social @eucloudedgeiot.bsky.social @quarkus.io @langchain4j.dev
youtu.be
Building GPU-Accelerated AI Libraries in Java with TornadoVM, Thanos Stratikopoulos
YouTube video by Bulgarian Java User Group
051
TornadoVM @tornadovm.org · 18/06/2026
New talk recording from @jprimeconf.bsky.social! Run GPU-accelerated, local LLM inference in Java - from a @quarkus.io @langchain4j.dev app. No Python. No CUDA. Just Java. All inside the JVM - powered by #TornadoVM + GPULlama3. 🔗 youtu.be/9YCRUwr7pO8?... #Java #GPU #LLM #AI #opensource
youtu.be
Building GPU-Accelerated AI Libraries in Java with TornadoVM, Thanos Stratikopoulos
YouTube video by Bulgarian Java User Group
092
Reposted by TornadoVM
AERO Project @aero-project.eu · 17/06/2026
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
185
Reposted by TornadoVM
Thanos Stratikopoulos @stratika.bsky.social · 12/06/2026
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
073
Reposted by TornadoVM
Thanos Stratikopoulos @stratika.bsky.social · 02/06/2026
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
064
Reposted by TornadoVM
AERO Project @aero-project.eu · 04/05/2026
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.com
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.
084
Reposted by TornadoVM
Thanos Stratikopoulos @stratika.bsky.social · 01/05/2026
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
055
Reposted by TornadoVM
AERO Project @aero-project.eu · 01/05/2026
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
054
TornadoVM @tornadovm.org · 01/05/2026
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
085
Reposted by TornadoVM
LangChain4j @langchain4j.dev · 30/04/2026
#LangChain4j 1.14.0 is out! 🎉 github.com/langchain4j/...
github.com
Release 1.14.0 and 1.14.0-beta24 · langchain4j/langchain4j
Notable Changes AI Services: Support polymorphic return types and tool parameters by @dliubarskyi in #5060 Add ReturnBehavior.IMMEDIATE_IF_LAST by @dliubarskyi in #4998 OpenAI Responses API: R...
192
Reposted by TornadoVM
AERO Project @aero-project.eu · 28/04/2026
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
043
TornadoVM @tornadovm.org · 28/04/2026
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
064
Reposted by TornadoVM
AERO Project @aero-project.eu · 22/04/2026
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
064
Reposted by TornadoVM
Thanos Stratikopoulos @stratika.bsky.social · 20/04/2026
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
074
TornadoVM @tornadovm.org · 14/04/2026
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!
075
Reposted by TornadoVM
Adam Bien @adambien.blog · 12/04/2026
I have just migrated a Python launch/configuration script to Java 25, and I have asked an LLM to review it 👇
1132
Reposted by TornadoVM
Devoxx Belgium @devoxx.com · 09/04/2026
🚀 Gemma4 Java runner: • Single file, no deps • E2B→31B + MoE • GGUF + quant (F16→Q8) • Vector API ⚡ • CLI + thinking modes • GraalVM native + instant TTFT Pure Java 😏 by @mukel.bsky.social github.com/mukel/gemma4...
github.com
173
TornadoVM @tornadovm.org · 09/04/2026
Our @cern.voxxeddays.ch 2026 talk is now live! We introduce TornadoVM, and show how it’s already used in the ESA #GAIA mission. Highlight: #GPULlama3, a #GPU accelerated #LLM inference in #Java, integrated with @langchain4j.dev + #Quarkus 👉 www.tornadovm.org/gpullama3 📽️ youtu.be/oRVtTEbtt_Y?...
youtu.be
TornadoVM: Supercharge your Java with GPU acceleration - Christos Kotselidis, Mary Xekalaki
YouTube video by Devoxx
0106
TornadoVM @tornadovm.org · 07/04/2026
TornadoVM v4.0.0 is out! ✔ Apple Metal backend → native Apple Silicon ✔ SIMD intrinsics for PTX → more performance ✔ CUDA Graphs → reduced overhead ✅ Downloads at TornadoVM → www.tornadovm.org/downloads Big thanks to our contributors! 👏 #Java #JDK25 #JDK21 #TornadoVM #opensource #AI #GPUs
0103
Reposted by TornadoVM
Christos Kotselidis @kotselidis.net · 30/03/2026
ICYMI our @cern.voxxeddays.ch 2026 talk with @maryxek.bsky.social on @tornadovm.org #Java #GPUs #AI and all👇 youtu.be/oRVtTEbtt_Y?...
youtu.be
TornadoVM: Supercharge your Java with GPU acceleration - Christos Kotselidis, Mary Xekalaki
YouTube video by Devoxx
054
TornadoVM @tornadovm.org · 30/03/2026
We’re excited to see TornadoVM featured at OCX 2026. Thanos Stratikopoulos will share how TornadoVM evolved from academic research into an open source success story. 🕓 16:00-16:45 📍 Studio 4 www.ocxconf.org/event/2026/a... #OCX2026 #TornadoVM #opensource #Java #HPC #research
063
TornadoVM @tornadovm.org · 13/03/2026
New 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...
063
Reposted by TornadoVM
Christos Kotselidis @kotselidis.net · 06/03/2026
The latest version of #LangChain4J supports our latest #GPULlama3 version 0.4.0 for native GPU acceleration of #Java 25 AI Inference!
0116
Reposted by TornadoVM
Christos Kotselidis @kotselidis.net · 06/03/2026
Join Mary and Michalis at #NVIDIA #GTC to discover how to achieve GPU accelerated Inference for #Java enterprise!
052
TornadoVM @tornadovm.org · 06/03/2026
TornadoVM at NVIDIA GTC (Mar 16–19, San Jose) Session: “Build AI Libraries for NVIDIA GPUs in Pure Modern Java With TornadoVM” [P81211] 👉 www.nvidia.com/gtc/session-... See how Java runs AI inference on NVIDIA GPUs. Come meet us and discover more! #opensource #Java #GPU #AI #TornadoVM
051
Reposted by TornadoVM
Thanos Stratikopoulos @stratika.bsky.social · 03/03/2026
Great to see the collaboration moving forward in the @aero-project.eu - and proud to represent the University of Manchester and the @tornadovm.org team. Looking forward to productive discussions over the coming days.
022
Reposted by TornadoVM
Christos Kotselidis @kotselidis.net · 25/02/2026
🚀 🚀 Another major release for TornadoVM now with both JDK21 and 25 support! You can start running your GPU accelerated AI inference workloads in Java today on all major JDK distros!
022
Reposted by TornadoVM
Thanos Stratikopoulos @stratika.bsky.social · 25/02/2026
TornadoVM v3.0.0 is out! What a milestone! This release brings: ✅ JDK 25 (25.0.2) compatibility ✅ Continued JDK 21 (LTS) support New SDKs are now available via SDKMAN! & the #TornadoVM downloads page. Great teamwork from the community 👏 #Java #JDK25 #opensource #Java #AI
054
TornadoVM @tornadovm.org · 25/02/2026
TornadoVM v3.0.0 is out 🎉 ✅ JDK 25 (25.0.2) compatible ✅ JDK 21 (LTS) fully supported • Available via SDKMAN! & TornadoVM downloads page • Docker images coming soon 👉 github.com/beehive-lab/... 👉 www.tornadovm.org/downloads Thanks to all contributors! 👏 #Java #JDK25 #JDK21 #TornadoVM
052
TornadoVM @tornadovm.org · 13/02/2026
Our #TornadoVM talk from Thanos Stratikopoulos (@stratika.bsky.social) at #VoxxedDaysTicino #VDT26 is now live on YouTube! 👉 youtu.be/2peFTUktkuY?... 1. From #Java to #GPUs without writing GPU code. 2. TornadoVM SDK installation via SDKMAN! 3. Featuring #GPULlama3.java + live #IntelliJ IDE demo.
youtu.be
Write Once, Accelerate Everywhere: GPU-Ready Java with TornadoVM by Thanos Stratikopoulos
YouTube video by Devoxx
054
Reposted by TornadoVM
Thanos Stratikopoulos @stratika.bsky.social · 09/02/2026
Last week at #VoxxedDaysTicino, I presented our work on @tornadovm.org. Great conversations, inspiring people - and the chance to admire Lugano🇨🇭 Big thanks to the organizers, and a special shout-out for the tour of the #Alps Supercomputer @cscsch.bsky.social 🙌 #opensource #Java #GPU #AI
064