YoVDO

Practical LLM Inference in Modern Java

Offered By: Devoxx via YouTube

Tags

Java Courses GraalVM Courses Vector API Courses LangChain4j Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore practical approaches to implementing local Large Language Model (LLM) inference using modern Java in this 51-minute Devoxx conference talk. Learn how to leverage the latest Java features to implement local inference for various open-source LLMs, starting with Llama 2 and 3 (Meta). Discover how to extend this approach to run other popular open-source models on standard CPUs without specialized hardware. Delve into key topics such as implementing efficient LLM inference engines for local execution, utilizing Java 21+ features for optimized CPU-based performance, creating a flexible framework adaptable to multiple LLM architectures, and maximizing standard CPU utilization without GPU dependencies. Gain insights on integrating with LangChain4j for streamlined local inference execution and optimizing performance using the Java Vector API for accelerated matrix operations. Learn how to leverage GraalVM to reduce latency and memory consumption. Acquire the knowledge to implement and optimize local LLM inference for open-source models in Java projects, enabling the creation of fast and efficient AI applications using cutting-edge Java technologies.

Syllabus

Practical LLM Inference in Modern Java by Alfonso² Peterssen, Alina Yurenko


Taught by

Devoxx

Related Courses

Algorithms, Part I
Princeton University via Coursera
Introduction à la programmation orientée objet (en Java)
École Polytechnique Fédérale de Lausanne via Coursera
MongoDB for Java Developers
MongoDB University
Initiation à la programmation (en Java)
École Polytechnique Fédérale de Lausanne via Coursera
Intro to Java Programming
San Jose State University via Udacity