Live, expert-led sessions where you’ll build real agentic systems step-by-step.

Speaker: Sanyam Bhutani, Partner Engineer, Generative AI Engineer at Meta

Publishing to Maven Central sounds simple… until it isn’t. In this talk, I’ll share a decade’s worth of lessons learned from publishing open source libraries to Maven Central and other repositories. From GPG key nightmares and Gradle plugin magic to simplify your publishing workflow: those are the tips wish you knew earlier. If you’ve ever fought with .pom files, staging repositories, or just want to understand how to go from a gradlew publish to GitHub download badge, this talk is for you. Expect incident stories, practical tips, and a series of do’s and don’ts to don’t be miserable when publishing to Central and making your next release smooth and drama-free!

Always wanted to get started with open source LLMs? Meta's Llama models are among the most popular and best performing in the world – and you can find them in Vertex Model Garden. In this session, we'll cover everything you need to know about working with Llama models on Vertex, from prompting best practices to choosing the best deployment method for your use case. With practical demos and real-world examples, discover how Llama can power your startup.

**Please bring your laptop to get the most out of this hands-on session**

In this presentation, we delve into the cutting-edge realm of large-scale AI training and inference, focusing on the open models and their deployment on Google Cloud Accelerators. Open models such as the Llama family of LLMs and Gemma are state-of-the-art language models that demand robust computational resources and efficient strategies for training and inference at scale. This session aims to provide a comprehensive guide on harnessing the power of PyTorch on Google Cloud Accelerators, specifically designed to meet the high-performance requirements of such models.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.