Quarkus Insights #197: Understanding Jlama in Quarkus
Mar 12, 2025•1 hr 1 min
Listen to this episode in Metacast mobile app
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more
Episode description
Jake Luciani and Mario Fusco join us to explain the benefits of performing LLM-inference directly in the same JVM as your Java application. They will discuss Jlama's technical aspects, its pros and cons, ongoing work, and future improvements. They will provide a practical example of how Quarkus, LangChain4j, and Jlama simplify creating a pure Java LLM-infused application.
For the best experience, listen in Metacast app for iOS or Android