Research Fellow @OfficialUoM, @TornadoVM Team.
Manchester, United Kingdom
Joined July 2011
- Tweets2K
- Following491
- Followers321
- Likes3.9K
Pinned Tweet
Interested in reading about #programming hardware accelerators via managed runtimes? Our new #book analyses the challenges of utilising heterogeneous hardware from a managed runtime environment along with several information about #heterogeneous programming models!
We are happy to announce the release of our latest book titled “Programming Heterogeneous Hardware via Managed Runtime Systems” published by @SpringerNature together Juan Fumero (@snatverk) and Thanos Stratikopoulos (@thanos_str )!
link.springer.com/book/10.10…
Thanos Stratikopoulos retweeted
Great to see @tornadovm on the top of the @ycombinator today! The article has all of the latest work on accessing @nvidia libraries from Java!
Had so much fun at @JDD_Krakow 2026 in Kraków yesterday.
I presented “Java Goes CUDA-Native”: new @tornadovm features that let @jitLLM run LLM inference at GPU-native speed, from Java.
tornadovm.org
jitllm.io
#opensource #Java #TornadoVM #GPU #AI
Thanos Stratikopoulos retweeted
Last chance to submit to @VoxxedZurich!🇨🇭
— 9 tracks across development practices, AI, architecture, and more 🎙️
— 700 participants 👩💻
— cinema screens 🔭
— all you can eat gelato and chocolate 😄
Let's go!💃 vdz27.voxxeddays.ch/
Thanos Stratikopoulos retweeted
LLM Inference on GPU in Java?
@tornadovm and @jitllm at @Devoxx Belgium!
* Java writing Java that runs on the GPU. Java for the GPU, on the GPU!.
* A @QuarkusIO @langchain4j application reviewing it's future port to Quarkus 4 locally, all in Java on GPU!
youtu.be/HO5CpETzywk?is=_ws2…
Thanos Stratikopoulos retweeted
96.65 tokens/sec for #Llama 3.2 1B – running through a pure-#Java GPU inference engine. @mikepapadim explores GPULlama3.java & #TornadoVM and how they bring GPU-accelerated #LLM inference to the #JVM.
See the code: javapro.io/2026/10/13/buildi…
#AI @langchain4j @QuarkusIO
Thanos Stratikopoulos retweeted
@mariofusco and @kevindubois rocking Devoxx with Agentic Patterns using @langchain4j & @QuarkusIO !!!
Yesterday my colleagues @MXekalaki and @mikepapadim showed live demos about using @nvidia cuFFT and cuBLAS with @tornadovm for signal filtering and @jitllm!
NVIDIA performance is a jar away from Java.
#Java #CUDA #TornadoVM
Optimized GPU libraries (e.g. cuBLAS, cuDNN, etc.) by @nvidia, now one jar away for your Java - without caring about JNI.
We also show demos with @ApacheFlink and @jitllm.
Watch our talk in @Devoxx 👇
youtu.be/6SPnBmQrYEk?si=3DI_…
#opensource #AI #TornadoVM #Java #GPU
Thanos Stratikopoulos retweeted
TornadoVM has a new family member! #jitLLM provides blazing fast AI inference at native speed⚡️👇
Can Java compete with llama.cpp/@ollama? YES! With @jitLLM!
jitLLM uses @nvidia CUDA libraries (cuBLAS, cuDNN) and reaches 0.90× to 1.12× of llama.cpp's throughput!
jitLLM is empowered by @tornadovm and will be soon in @langchain4j and @QuarkusIO.
github.com/beehive-lab/jitll…
Thanos Stratikopoulos retweeted
Optimized GPU libraries (e.g. cuBLAS, cuDNN, etc.) by @nvidia, now one jar away for your Java - without caring about JNI.
We also show demos with @ApacheFlink and @jitllm.
Watch our talk in @Devoxx 👇
youtu.be/6SPnBmQrYEk?si=3DI_…
#opensource #AI #TornadoVM #Java #GPU
We are @Devoxx, getting ready for our first hands-on #GPU lab for #Java!
We will be in BOF2 room at 16:50, with live demos!
@tornadovm @jitllm
Thanos Stratikopoulos retweeted
jitLLM is part of the @langchain4j 1.21.0 release! 🚀
Read more here: docs.langchain4j.dev/integra…
#opensource #LLM #GPU #Java #LangChain4j #Inference
#LangChain4j 1.21.0 is out! 🚀
Meet Decision Models: instant yes/no, choice and scale answers with probabilities.
Decision Services turn any Java interface into a classifier.
Plus model routing, re-ranking, tool selection, guardrails and agentic routing!
github.com/langchain4j/langc…
Thanos Stratikopoulos retweeted
Excited to see our work reaching this point. ⚡
Pure Java LLM inference, seriously fast. Approaching - and in some cases exceeding - llama.cpp performance.
Can Java compete with llama.cpp/@ollama? YES! With @jitLLM!
jitLLM uses @nvidia CUDA libraries (cuBLAS, cuDNN) and reaches 0.90× to 1.12× of llama.cpp's throughput!
jitLLM is empowered by @tornadovm and will be soon in @langchain4j and @QuarkusIO.
github.com/beehive-lab/jitll…
Thanos Stratikopoulos retweeted
Next week we will be in @Devoxx and speak about @tornadovm, @jitllm 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
Thanos Stratikopoulos retweeted
TornadoVM adds initial support for cuTile from @kotlin
Thanos Stratikopoulos retweeted
Thanos Stratikopoulos retweeted
📣 New Press Release: AXHEL, an open-source C++ library from @DII_Pisa accelerating the arithmetic behind Homomorphic Encryption on AArch64.
👉 aero-project.eu/wp-content/u…
Repo: github.com/AERO-Project-EU/A…
@EU_HaDEA
@HorizonEU
@hipeac
@EU_CloudEdgeIoT
#opensource #he #encryption
Thanos Stratikopoulos retweeted
TornadoVM 7.0.0 introduces the new TileContext API, bringing @nvidia CUDA cuTile programming to Java.
Now, you can combine TileContext , JIT and cuBLAS tasks in a single TaskGraph and capture them as one CUDA Graph and more all from Java.
TornadoVM 7.0.0 is out!
New TileContext API: Write #GPU kernels from #Java in tiles, not threads, via @nvidia cuTile model. The compiler picks threads, shared memory and Tensor Cores.
Mixes with Parallel API, KernelContext & cuBLAS in one TaskGraph.
👉 github.com/beehive-lab/Torna…
