RT @Stephan007: Looking forward to speaking tomorrow at @VoxxedCERN together with @TheMukel followed by delivering both a keynote and a reg…

RT @fniephaus: We just merged the current status of the upcoming JDWP support for @GraalVM Native Image! 🥳 This will soon provide develope…

Graal compiler: +10% faster inference with the latest early access build. New features: batched prompt processing & AVX512 support.

RT @Stephan007: As a result I can now use @DevoxxGenie with a pure Java Arm Inference engine running locally on my mac using Llama 3.2 🍏🔥 h…

RT @Stephan007: Modern @Java Project : a Spring Boot wrapper for from @TheMukel supporting OpenAI Chat Completion…

RT @JohanHutting: Earlier today was asked if Java AI integration improved yet, or that we'd still need to rely on Python or C bindings. Was…

RT @FilterPunk: @tjake For me your #Devoxx talk about and the one from @TheMukel about wer…

RT @Stephan007: Just made the first-ever @DevoxxGenie LLM inference using ONLY @Java, powered by the awesome #Jlama project! ☕🔥 Huge thanks…

@christzolov @vitalethomas @alina_yurenko I have a working prototype with function calling via LangChain4j. Vision is just a matter of implementing an additional component, the rest of the inference remains the same. I'll do my best to implement the missing encoder for vision soon-ish, starting with Llama, then Qwen.

@diegoasua @bate5a55 @julien_c Why not? It runs Llama 3.2 1B at 40+ tokens/s on my laptop. It also supports GraalVM's Native Image with instant time-to-first-token.

All details were presented at Devoxx Belgium! PS: I'm the original author.

RT @alina_yurenko: Developing and optimizing an LLM inference engine in pure Java: with @TheMukel #Devoxx #Java #L…

RT @Stephan007: Here's the #Devoxx Belgium recording, enjoy!

RT @Stephan007: Contribute! 👇

RT @AdamBien: jlama (by @tjake ) and (by @TheMukel ) examples are working. See you at: "Pure Java Enterprise AI/LLM…

RT @fniephaus: .@TheMukel and @alina_yurenko talking about practical LLM inference in modern Java with and @GraalVM…

RT @maxandersen: Loving @TheMukel and @alina_yurenko 's talk explaining the various working parts of inference engines - then make it work…

RT @Stephan007: Must see #Devoxx talk : Practical LLM Inference in Modern Java with @TheMukel and @alina_yurenko Btw I see also DevoxxGeni…

RT @alina_yurenko: Fast LLM inference in pure Java? How about ✨instant✨ LLM inference in pure Java?:) Join me and @TheMukel on Thursday at…

@maxandersen 🙌 Big #JBang fan here! Really looking forward to your session. See you Monday!