This session explores patterns for productionizing AI applications on Google Kubernetes Engine (GKE). Learn to leverage open source frameworks, cloud AI services, and readily available models to train, deploy, and scale with GKE. We’ll share real-world customer stories and best practices for productionizing AI solutions on GKE.

This technical deep dive explores how small IT teams can leverage Google Kubernetes Engine (GKE) and AI Hypercomputer to build, refine, and optimize a cutting-edge, scalable, and secure container platform for AI workloads.

Google Kubernetes Engine (GKE) provides cost efficiency and high performance to run AI inference on Google tensor processing units (TPUs) and NVIDIA graphics processing units. Join us to learn how Anthropic runs its inference workload for Claude on GKE, and how Anthropic achieved better price-perf on TPU v5e on GKE. We’ll also learn how GKE advanced management capabilities simplify Day-2 maintenance, and how Google Cloud Customer Support makes the entire experience a blast.

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.

Text-to-image generative AI models such as the Stable Diffusion family of models are rapidly growing in popularity. In this session, we explain how to optimize every layer of your serving architecture – including TPU accelerators, orchestration, model server, and ML framework – to gain significant improvements in performance and cost effectiveness. We introduce many new innovations in Google Kubernetes Engine that improve the cost effectiveness of AI inference, and we provide a deep dive into MaxDiffusion, a brand new library for deploying scalable stable diffusion workloads on TPUs.

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.

Learn how the patent search engine company IPRally created a custom compute platform to enable higher scale data processing and deep learning. The solution relies on Ray Core and Google Kubernetes Engine, and harvests the cheapest resources from all around the world. In addition to the efficiency, the goal was to build the best environment for machine learning R&D. This has been achieved with integration to Weights&Biases as the experiment tracking system. In this session, we’ll go through on a high level the solution. Please note: seating is limited and on a first-come, first served basis; standing areas are available

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.

This technical deep dive explores how small IT teams can leverage Google Kubernetes Engine (GKE) and AI Hypercomputer to build, refine, and optimize a cutting-edge, scalable, and secure container platform for AI workloads.