jitLLM (@jitllm) header
jitLLM (@jitllm) profile picture

Java Inference Tornado toolkit | Powered by @TornadoVM | https://nitter.cf/t.co/24V0XxmPMD

Joined September 2026
Photo by jitLLM (@jitllm)Photo by jitLLM (@jitllm)
jitLLM retweeted
Our inference engine is getting better! @jitllm 3.0 brings: ⚡ AOT startup: 1.43× faster with @GraalVM Native Image, plus a Leyden AOT cache 🧩 Combined with native #GPU libraries from Java: #cuBLAS, #cuDNN and #MLX via the #TornadoVM API. #Java #LLM #GPU👇
jitLLM 3.0 is out! #Java #LLM inference on CUDA, Metal and OpenCL GPUs via #TornadoVM. • 1.43× faster startup with @graalvm Native Image • Up to 9.3× faster prefill • Zero-copy weights on @Apple silicon Soon in @langchain4j @QuarkusIO @springcentral github.com/beehive-lab/jitll…
2
11
1
36
1,023
jitLLM 3.0 is out! #Java #LLM inference on CUDA, Metal and OpenCL GPUs via #TornadoVM. • 1.43× faster startup with @graalvm Native Image • Up to 9.3× faster prefill • Zero-copy weights on @Apple silicon Soon in @langchain4j @QuarkusIO @springcentral github.com/beehive-lab/jitll…
8
3
13
1,088
Next Tuesday (17 Nov) I'm at @parisjug for a TornadoVM evening! ☕ GPU-ready Java, no GPU code needed 🤖 LLM inference in pure Java with jitLLM 🟩 CUDA + NVIDIA libs from Java, no JNI 19:00 at Criteo. Register 👇 parisjug.org/events/2026/11-… #Java #TornadoVM #GPU #LLM
8
17
376
jitLLM retweeted
Our next #YouTube video shows 4 ways to install #TornadoVM. SDKMAN! with 1 command, prebuilt archives for Linux, macOS and Windows, building from source, & #JBang with no SDK at all. 👉 youtu.be/_ipmOKOYj_s Subscribe: youtube.com/@TornadoVM-Dev #Java #GPU #TornadoVM #tutorial
9
7
330
Replying to @tornadovm
@tornadovm now can automatically convert plain Java to GPU-compatible Java through the TornadoInsight plugin.
The @TornadoVM team dropped me a message about TornadoInsight, their free plugin for @IntelliJIDEA for working with Java on GPUs. A nice find to pass along if you’ve been curious about GPU programming in Java 👇 plugins.jetbrains.com/plugin… Have you folks already worked with GPUs?
4
6
132
jitLLM retweeted
TornadoInsight 2.1.0 is out 🌪️ New (experimental): #AI turns a plain #Java method into a #TornadoVM kernel, then runs it on your #GPU and checks it against the original. Black-Scholes on an Apple M4 Pro: 25× faster than Java. #IntelliJ @intellijidea plugins.jetbrains.com/plugin…
8
2
25
1,787
🥃 Clustering Scotch whiskies with @ApacheFlink and @ApacheGroovy: Flink ML, hand-written K-means on Flink 2.3, then the hot loop as a Groovy GPU kernel with @tornadovm. Plus a caching trap and why Amdahl's law decides whether the GPU helps. @TheASF groovy.apache.org/blog/groov…
7
15
457
New @TornadoVM release, v8.0.0 is coming with support for ahead-of-time compilation via @graalvm Native Image and Project Leyden. tornadovm.org/blogs/fast-sta… Huge leap for the project! Kudos to all contributors! 🙌 #opensource #Java #GPUs #TornadoVM
TornadoVM 8.0.0 is out 🌪️ After 10 years: thank you, Graal. Java kernels are now compiled by TC, our own pure-Java compiler to CUDA, OpenCL and Metal. • AOT ready • No JVMCI • Now Apache 2.0 • Your code doesn't change 👉 tornadovm.org/blogs/tornadov… #OpenSource #Java #AI #GPU
6
13
384
After 10 years of lessons learned,@tornadovm introduces its own lean, modern Java-to-GPU compiler written in pure Java, no Graal or JVMCI dependencies. With AOT support, Leyden and @graalvm Native Image readiness, and improved compiler tooling. Apache 2.0 licenced.
TornadoVM 8.0.0 is out 🌪️ After 10 years: thank you, Graal. Java kernels are now compiled by TC, our own pure-Java compiler to CUDA, OpenCL and Metal. • AOT ready • No JVMCI • Now Apache 2.0 • Your code doesn't change 👉 tornadovm.org/blogs/tornadov… #OpenSource #Java #AI #GPU
3
9
21
757
jitLLM retweeted
TornadoVM 8.0.0 is out 🌪️ After 10 years: thank you, Graal. Java kernels are now compiled by TC, our own pure-Java compiler to CUDA, OpenCL and Metal. • AOT ready • No JVMCI • Now Apache 2.0 • Your code doesn't change 👉 tornadovm.org/blogs/tornadov… #OpenSource #Java #AI #GPU
8
26
8
120
8,383
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!
1
5
12
470
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
7
1
12
260
The Devoxx Greece 2027 Call for Papers is OPEN! Join us in Athens (Apr 15-17). Propose a session across 8 tracks—from 15m bytes to 3h deep dives. First-time speakers welcome! Submit by end of Nov: dvgr27.cfp.dev/ #devoxxgr #dvgr27
5
2
14
1,776
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…
2
7
12
310
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
1
8
1
12
367
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
6
6
112