TornadoVM
@tornadovm.org
Official #TornadoVM - JIT Compiler & Runtime system for running JVM applications on heterogeneous hardware.
https://www.tornadovm.org/
https://www.tornadovm.org/
Pinned
TornadoVM
@tornadovm.org
· Jul 7
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
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
Reposted by TornadoVM
At the @devoxx.com and #JFall conferences, I interviewed speakers and attendees for the @foojay.io #Podcast. In part 1, you'll learn more about ongoing #OpenJDK projects and #TornadoVM. Watch on YouTube or listen in your favorite podcast app: www.youtube.com/watch?v=Srxy...
OpenJDK Projects (Leyden, Babylon, Panama) and TornadoVM (#82)
YouTube video by Frank Delporte
www.youtube.com
November 15, 2025 at 10:45 AM
At the @devoxx.com and #JFall conferences, I interviewed speakers and attendees for the @foojay.io #Podcast. In part 1, you'll learn more about ongoing #OpenJDK projects and #TornadoVM. Watch on YouTube or listen in your favorite podcast app: www.youtube.com/watch?v=Srxy...
Reposted by TornadoVM
Thanks Frank Delporte for the wonderful interview and the opportunity to discuss @tornadovm.org and its #AI capabilities in accelerating #Java programs on #GPUs. If you are interested in GPU-accelerated AI inference in pure Java, check the interview below and www.tornadovm.org/gpullama3
November 15, 2025 at 12:50 PM
Thanks Frank Delporte for the wonderful interview and the opportunity to discuss @tornadovm.org and its #AI capabilities in accelerating #Java programs on #GPUs. If you are interested in GPU-accelerated AI inference in pure Java, check the interview below and www.tornadovm.org/gpullama3
Reposted by TornadoVM
Thrilled to announce I’ll be speaking at #VoxxedDays Ticino on Feb 6th, joining such a great speaker lineup! 🇨🇭
I’ll share what’s new in #TornadoVM and #GPULlama3.java!
🔗 vdt26.voxxeddays.ch/talk/?id=3794
#Java #GPUs #AI #opensource
@aero-project.eu
I’ll share what’s new in #TornadoVM and #GPULlama3.java!
🔗 vdt26.voxxeddays.ch/talk/?id=3794
#Java #GPUs #AI #opensource
@aero-project.eu
November 13, 2025 at 1:51 PM
Thrilled to announce I’ll be speaking at #VoxxedDays Ticino on Feb 6th, joining such a great speaker lineup! 🇨🇭
I’ll share what’s new in #TornadoVM and #GPULlama3.java!
🔗 vdt26.voxxeddays.ch/talk/?id=3794
#Java #GPUs #AI #opensource
@aero-project.eu
I’ll share what’s new in #TornadoVM and #GPULlama3.java!
🔗 vdt26.voxxeddays.ch/talk/?id=3794
#Java #GPUs #AI #opensource
@aero-project.eu
Reposted by TornadoVM
Last week I presented at #MPLR2025 our work on #TornadoInsight - an #opensource tool for static & dynamic analysis of #Java code using #TornadoVM on #GPUs.
The presentation is on YouTube:
🎥 Talk: youtube.com/live/sJZtDHw...
The tool is available on GitHub & JetBrains Marketplace!
The presentation is on YouTube:
🎥 Talk: youtube.com/live/sJZtDHw...
The tool is available on GitHub & JetBrains Marketplace!
[ICFP/SPLASH'25] Peony SE - MPLR (Oct 14th)
YouTube video by ACM SIGPLAN
youtube.com
October 21, 2025 at 11:44 AM
Last week I presented at #MPLR2025 our work on #TornadoInsight - an #opensource tool for static & dynamic analysis of #Java code using #TornadoVM on #GPUs.
The presentation is on YouTube:
🎥 Talk: youtube.com/live/sJZtDHw...
The tool is available on GitHub & JetBrains Marketplace!
The presentation is on YouTube:
🎥 Talk: youtube.com/live/sJZtDHw...
The tool is available on GitHub & JetBrains Marketplace!
Reposted by TornadoVM
Congratulations to @mikepapadim.bsky.social for presenting the #TornadoViz tool at #MPLR2025!
It is an #opensource visualisation tool for the #TornadoVM Bytecodes that orchestrate the data transfers, execution, etc. of complex workloads.
Paper: zenodo.org/records/1695...
#horizoneurope #ukri
It is an #opensource visualisation tool for the #TornadoVM Bytecodes that orchestrate the data transfers, execution, etc. of complex workloads.
Paper: zenodo.org/records/1695...
#horizoneurope #ukri
October 14, 2025 at 11:35 AM
Congratulations to @mikepapadim.bsky.social for presenting the #TornadoViz tool at #MPLR2025!
It is an #opensource visualisation tool for the #TornadoVM Bytecodes that orchestrate the data transfers, execution, etc. of complex workloads.
Paper: zenodo.org/records/1695...
#horizoneurope #ukri
It is an #opensource visualisation tool for the #TornadoVM Bytecodes that orchestrate the data transfers, execution, etc. of complex workloads.
Paper: zenodo.org/records/1695...
#horizoneurope #ukri
Reposted by TornadoVM
Our colleague from @manchester.ac.uk, @stratika.bsky.social presented their work on #TornadoInsight, a plugin for @intellijidea.com that provides static and dynamic of #Java classes that use the #TornadoVM API!
#horizoneurope #opensource
#horizoneurope #opensource
October 14, 2025 at 10:08 AM
Our colleague from @manchester.ac.uk, @stratika.bsky.social presented their work on #TornadoInsight, a plugin for @intellijidea.com that provides static and dynamic of #Java classes that use the #TornadoVM API!
#horizoneurope #opensource
#horizoneurope #opensource
Reposted by TornadoVM
🧩 #MPLR2025: #TornadoInsight - #IntelliJ plugin for #TornadoVM.
Detects incompatible #Java constructs & offers instant feedback for accelerator programming.
📄 zenodo.org/records/1695...
Repository: github.com/beehive-lab/...
JetBrains Marketplace: plugins.jetbrains.com/plugin/23309...
Detects incompatible #Java constructs & offers instant feedback for accelerator programming.
📄 zenodo.org/records/1695...
Repository: github.com/beehive-lab/...
JetBrains Marketplace: plugins.jetbrains.com/plugin/23309...
Dynamic and Static Code Analysis for Java Programs on Heterogeneous Hardware
The increasing prevalence of heterogeneous computing systems, incorporating accelerators like GPUs, has spurred the development of advanced frameworks to bring high performance capabilities to managed...
zenodo.org
October 10, 2025 at 11:24 AM
🧩 #MPLR2025: #TornadoInsight - #IntelliJ plugin for #TornadoVM.
Detects incompatible #Java constructs & offers instant feedback for accelerator programming.
📄 zenodo.org/records/1695...
Repository: github.com/beehive-lab/...
JetBrains Marketplace: plugins.jetbrains.com/plugin/23309...
Detects incompatible #Java constructs & offers instant feedback for accelerator programming.
📄 zenodo.org/records/1695...
Repository: github.com/beehive-lab/...
JetBrains Marketplace: plugins.jetbrains.com/plugin/23309...
Reposted by TornadoVM
📊 #MPLR2025: #TornadoViz - visual analytics for #TornadoVM.
Explore task dependencies, memory ops & #performance across CPUs/#GPUs interactively.
📄 zenodo.org/records/1695...
Repository: github.com/beehive-lab/...
Explore task dependencies, memory ops & #performance across CPUs/#GPUs interactively.
📄 zenodo.org/records/1695...
Repository: github.com/beehive-lab/...
TornadoViz: Visualizing Heterogeneous Execution Patterns in Modern Managed Runtime Systems
With the increasing prevalence of machine learning and large language model (LLM) inference, heterogeneous computing has become essential. Modern JVMs are embracing this transition through projects su...
zenodo.org
October 10, 2025 at 11:24 AM
📊 #MPLR2025: #TornadoViz - visual analytics for #TornadoVM.
Explore task dependencies, memory ops & #performance across CPUs/#GPUs interactively.
📄 zenodo.org/records/1695...
Repository: github.com/beehive-lab/...
Explore task dependencies, memory ops & #performance across CPUs/#GPUs interactively.
📄 zenodo.org/records/1695...
Repository: github.com/beehive-lab/...
Reposted by TornadoVM
Next week at #MPLR2025 & #VMIL2025 in Singapore!
We are excited to share that our partners from @manchester.ac.uk University of Crete and #RedHat are presenting 4 #research outcomes on #Java, #TornadoVM, #GC and #tools.
#horizoneurope
@hipeac.bsky.social
@eucloudedgeiot.bsky.social
👇
We are excited to share that our partners from @manchester.ac.uk University of Crete and #RedHat are presenting 4 #research outcomes on #Java, #TornadoVM, #GC and #tools.
#horizoneurope
@hipeac.bsky.social
@eucloudedgeiot.bsky.social
👇
October 10, 2025 at 11:24 AM
Next week at #MPLR2025 & #VMIL2025 in Singapore!
We are excited to share that our partners from @manchester.ac.uk University of Crete and #RedHat are presenting 4 #research outcomes on #Java, #TornadoVM, #GC and #tools.
#horizoneurope
@hipeac.bsky.social
@eucloudedgeiot.bsky.social
👇
We are excited to share that our partners from @manchester.ac.uk University of Crete and #RedHat are presenting 4 #research outcomes on #Java, #TornadoVM, #GC and #tools.
#horizoneurope
@hipeac.bsky.social
@eucloudedgeiot.bsky.social
👇
Reposted by TornadoVM
In less than two hours @mikepapadim.bsky.social will demo state-of-the-art native #Java #AI inference on GPUs at @devoxx.com
Based on @tornadovm.org and the @graalvm.org compiler, 𝗚𝗣𝗨𝗟𝗹𝗮𝗺𝗮𝟯.𝗷𝗮𝘃𝗮 enables GPU inference of LLM models with high performance and integration with @langchain4j.dev!
Based on @tornadovm.org and the @graalvm.org compiler, 𝗚𝗣𝗨𝗟𝗹𝗮𝗺𝗮𝟯.𝗷𝗮𝘃𝗮 enables GPU inference of LLM models with high performance and integration with @langchain4j.dev!
October 9, 2025 at 2:19 PM
In less than two hours @mikepapadim.bsky.social will demo state-of-the-art native #Java #AI inference on GPUs at @devoxx.com
Based on @tornadovm.org and the @graalvm.org compiler, 𝗚𝗣𝗨𝗟𝗹𝗮𝗺𝗮𝟯.𝗷𝗮𝘃𝗮 enables GPU inference of LLM models with high performance and integration with @langchain4j.dev!
Based on @tornadovm.org and the @graalvm.org compiler, 𝗚𝗣𝗨𝗟𝗹𝗮𝗺𝗮𝟯.𝗷𝗮𝘃𝗮 enables GPU inference of LLM models with high performance and integration with @langchain4j.dev!
Reposted by TornadoVM
October 8, 2025 at 1:04 PM
The #TornadoVM deep dive session is live on YouTube!
👉 youtu.be/WNQ5ylMs4Ok?...
Next up: GPULlama3.java at #Devoxx with live coding demo showing Java-native GPU acceleration! -
🗓 Tomorrow (Oct 9) | 🕔 17:40–18:30 | 📍 Room 6
Don’t miss it!
#opensource #Java #AI #GPU
👉 youtu.be/WNQ5ylMs4Ok?...
Next up: GPULlama3.java at #Devoxx with live coding demo showing Java-native GPU acceleration! -
🗓 Tomorrow (Oct 9) | 🕔 17:40–18:30 | 📍 Room 6
Don’t miss it!
#opensource #Java #AI #GPU
TornadoVM Deep Dive: Empowering Java Developers with GPU Acceleration by Thanos Stratikopoulos, Ch
YouTube video by Devoxx
youtu.be
October 8, 2025 at 12:49 PM
The #TornadoVM deep dive session is live on YouTube!
👉 youtu.be/WNQ5ylMs4Ok?...
Next up: GPULlama3.java at #Devoxx with live coding demo showing Java-native GPU acceleration! -
🗓 Tomorrow (Oct 9) | 🕔 17:40–18:30 | 📍 Room 6
Don’t miss it!
#opensource #Java #AI #GPU
👉 youtu.be/WNQ5ylMs4Ok?...
Next up: GPULlama3.java at #Devoxx with live coding demo showing Java-native GPU acceleration! -
🗓 Tomorrow (Oct 9) | 🕔 17:40–18:30 | 📍 Room 6
Don’t miss it!
#opensource #Java #AI #GPU
Reposted by TornadoVM
Project Panama is a key component for transitioning #Java into the #AI era! @tornadovm.org has been among the early adopters of Panama. Thanks @nipafx.dev for the excellent talk @devoxx.com and the shoutout!
October 8, 2025 at 9:07 AM
Project Panama is a key component for transitioning #Java into the #AI era! @tornadovm.org has been among the early adopters of Panama. Thanks @nipafx.dev for the excellent talk @devoxx.com and the shoutout!
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
@devoxx.com
October 7, 2025 at 11:05 AM
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
@devoxx.com
Reposted by TornadoVM
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
#opensource
October 7, 2025 at 8:18 AM
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
#opensource
Reposted by TornadoVM
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?...
Extended in the P2Code project and coming to #MPLR2025 next week!
#Devoxx
youtu.be/WNQ5ylMs4Ok?...
TornadoVM Deep Dive: Empowering Java Developers with GPU Acceleration by Thanos Stratikopoulos, Ch
YouTube video by Devoxx
youtu.be
October 7, 2025 at 9:07 AM
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?...
Extended in the P2Code project and coming to #MPLR2025 next week!
#Devoxx
youtu.be/WNQ5ylMs4Ok?...
Reposted by TornadoVM
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
Our #TornadoVM deep dive talk is today at 13.30 in Room 4.
#opensource #Java #AI #GPU
October 6, 2025 at 9:06 AM
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
Our #TornadoVM deep dive talk is today at 13.30 in Room 4.
#opensource #Java #AI #GPU
Reposted by TornadoVM
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!
Next week @devoxx.com we will showcase our demos as well as provide a deep dive on @tornadovm.org!
October 2, 2025 at 5:12 PM
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!
Next week @devoxx.com we will showcase our demos as well as provide a deep dive on @tornadovm.org!
Reposted by TornadoVM
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
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
October 2, 2025 at 2:27 PM
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
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
Reposted by TornadoVM
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...
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...
September 24, 2025 at 2:18 PM
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...
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...
Reposted by TornadoVM
Docker images of GPULlama3.java v0.2.0 for NVIDIA #GPUs are now ready in DockerHub!
OpenCL image: hub.docker.com/r/beehivelab...
PTX image:
hub.docker.com/r/beehivelab...
OpenCL image: hub.docker.com/r/beehivelab...
PTX image:
hub.docker.com/r/beehivelab...
September 5, 2025 at 2:56 PM
Docker images of GPULlama3.java v0.2.0 for NVIDIA #GPUs are now ready in DockerHub!
OpenCL image: hub.docker.com/r/beehivelab...
PTX image:
hub.docker.com/r/beehivelab...
OpenCL image: hub.docker.com/r/beehivelab...
PTX image:
hub.docker.com/r/beehivelab...
Reposted by TornadoVM
Checkout the latest podcast from @mikepapadim.bsky.social on GPULlama3.java; our latest #Java #AI inference framework accelerated with @tornadovm.org!
August 17, 2025 at 4:56 PM
Checkout the latest podcast from @mikepapadim.bsky.social on GPULlama3.java; our latest #Java #AI inference framework accelerated with @tornadovm.org!
Reposted by TornadoVM
New #GPULlama3.java release, bringing expanded model support, cross-platform GPU inference, and upcoming #LangChain4j integration.
Demo is preparing for @devoxx.com: lnkd.in/dfbV_tSU
Checkout the release 👉 github.com/beehive-lab/...
#opensource #Java #AI #TornadoVM
@aero-project.eu
Demo is preparing for @devoxx.com: lnkd.in/dfbV_tSU
Checkout the release 👉 github.com/beehive-lab/...
#opensource #Java #AI #TornadoVM
@aero-project.eu
Release v0.2.0 · beehive-lab/GPULlama3.java
Model Support
Mistral – support for GGUF-format Mistral models with optimized GPU execution.
Qwen2.5 – GGUF-format Qwen2.5 models supported, including performance improvements for attention layers...
github.com
September 5, 2025 at 1:59 PM
New #GPULlama3.java release, bringing expanded model support, cross-platform GPU inference, and upcoming #LangChain4j integration.
Demo is preparing for @devoxx.com: lnkd.in/dfbV_tSU
Checkout the release 👉 github.com/beehive-lab/...
#opensource #Java #AI #TornadoVM
@aero-project.eu
Demo is preparing for @devoxx.com: lnkd.in/dfbV_tSU
Checkout the release 👉 github.com/beehive-lab/...
#opensource #Java #AI #TornadoVM
@aero-project.eu
Reposted by TornadoVM
⚡ Hackernews Top story: GPU-accelerated Llama3.java inference in pure Java using TornadoVM
GitHub - beehive-lab/GPULlama3.java: GPU-accelerated Llama3.java inference in pure Java using TornadoVM.
GPU-accelerated Llama3.java inference in pure Java using TornadoVM. - GitHub - beehive-lab/GPULlama3.java: GPU-accelerated Llama3.java inference in pure Java using TornadoVM.
github.com
June 15, 2025 at 1:18 AM
⚡ Hackernews Top story: GPU-accelerated Llama3.java inference in pure Java using TornadoVM