Official #TornadoVM - JIT Compiler & Runtime system for running JVM applications on heterogeneous hardware. https://www.tornadovm.org/https://bsky.app/profile/tornadovm.orghttps://bsky.app/profile/tornadovm.org/post/3mujuvot3vc2jTornadoVM 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: https://www.tornadovm.org/blogs/tornadovm-6-0-0-zero-jni-faster-runtime #Java #GPU #CUDA #TornadoVM #OpenSource #HPC #AI02 Sep 2026 11:55 +0000at://did:plc:zdlf7f5vb2wu3vucqn67f262/app.bsky.feed.post/3mujuvot3vc2jhttps://bsky.app/profile/tornadovm.org/post/3mszsuofkzk2n3 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 #opensource14 Aug 2026 09:11 +0000at://did:plc:zdlf7f5vb2wu3vucqn67f262/app.bsky.feed.post/3mszsuofkzk2nhttps://bsky.app/profile/tornadovm.org/post/3mrpaj2qecc2sGPULlama3 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 #GPU28 Jul 2026 10:51 +0000at://did:plc:zdlf7f5vb2wu3vucqn67f262/app.bsky.feed.post/3mrpaj2qecc2shttps://bsky.app/profile/tornadovm.org/post/3mqcensebcc2aTornadoVM 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 #GPU10 Jul 2026 14:35 +0000at://did:plc:zdlf7f5vb2wu3vucqn67f262/app.bsky.feed.post/3mqcensebcc2ahttps://bsky.app/profile/tornadovm.org/post/3mokjovlowc2aNew 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. 🔗 https://youtu.be/9YCRUwr7pO8?si=WaMitojbwXIIzDBW #Java #GPU #LLM #AI #opensource18 Jun 2026 09:36 +0000at://did:plc:zdlf7f5vb2wu3vucqn67f262/app.bsky.feed.post/3mokjovlowc2ahttps://bsky.app/profile/tornadovm.org/post/3mkrynztq2c2dLast 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 #GPUs01 May 2026 11:12 +0000at://did:plc:zdlf7f5vb2wu3vucqn67f262/app.bsky.feed.post/3mkrynztq2c2dhttps://bsky.app/profile/tornadovm.org/post/3mkk454usic2bTornadoVM is featured in the April 2026 issue of Java Pro Magazine - “Java in the Age of AI”! 👉 https://javapro.io/wp-content/uploads/2026/04/JAVAPRO_04-2026.pdf#page=42 In this article, @mikepapadim.bsky.social shared our experiences on building #GPU accelerated #LLM inference libraries with #TornadoVM. #Java #community #AI28 Apr 2026 07:53 +0000at://did:plc:zdlf7f5vb2wu3vucqn67f262/app.bsky.feed.post/3mkk454usic2bhttps://bsky.app/profile/tornadovm.org/post/3mjh6czswcc27Great 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! [contains quote post or other embedded content]14 Apr 2026 10:29 +0000at://did:plc:zdlf7f5vb2wu3vucqn67f262/app.bsky.feed.post/3mjh6czswcc27