BEGIN:VCALENDAR VERSION:2.0 PRODID:-//CFP.DEV//CFP.DEV shortcodes//EN CALSCALE:GREGORIAN METHOD:PUBLISH X-WR-CALNAME:Voxxed Days Zurich X-WR-RELCALID:c426493a-54d4-472b-b975-6f3aaa7163fa X-WR-TIMEZONE:Europe/Zurich BEGIN:VEVENT UID:cfp-1151-14330@cfp.dev DTSTAMP:20260920T140328Z SEQUENCE:0 STATUS:CONFIRMED DTSTART:20250325T155000Z DTEND:20250325T163500Z SUMMARY:Practical LLM Inference in Modern Java DESCRIPTION:Large Language Models (LLMs) have become essential in many appl ications\, but integrating them effectively into Java environments can sti ll be challenging. This session will explore practical approaches to imple menting local LLM inference using modern Java.We'\;ll demonstrate how t o leverage the latest Java features to implement local inference for a var iety of open-source LLMs\, starting with Llama 3 (Meta). Importantly\, we& #39\;ll show how the same approach can easily be extended to run other pop ular open-source models on standard CPUs without the need for specialized hardware.Key topics we'\;ll cover:- Implementing efficient LLM inferenc e engines in modern Java for local execution- Utilizing Java 21+ features for optimized CPU-based performance- Creating a flexible framework adaptab le to multiple LLM architectures- Maximizing standard CPU utilization for inference without GPU dependencies- Integrating with LangChain4j for strea mlined local inference execution- Optimizing performance with Java Vector API for accelerated matrix operations and leveraging GraalVM to reduce lat ency and memory consumption.Join us to learn about implementing and optimi zing local LLM inference for open-source models in your Java projects and creating fast and efficient AI applications using the latest Java technolo gies.\nSpeakers: Alina Yurenko\, Alfonso² Peterssen\nTrack: Java URL:https://vdz25.voxxeddays.ch/talk/practical-llm-inference-in-modern-java / LOCATION:Room 4\nARENA Cinemas\, Sihlcity\nZürich\, Switzerland CATEGORIES:Java END:VEVENT END:VCALENDAR