Deploy and Manage LLMs on Google Cloud Run GPUs with Pulumi

If you’ve ever wanted to inference with an LLM in under a minute while paying only for what you consume, then Google Cloud Run GPUs are for you! In this hands-on workshop, we will demonstrate how Pulumi can seamlessly stand up an environment for deploying your LLMs and custom models on Google Cloud Run GPUs. Participants will learn how to create scalable, cost-efficient infrastructure that allows for rapid LLM inference, leveraging the power of Pulumi to automate and manage their deployments. Whether you’re deploying pre-trained LLMs or custom models, this workshop will provide the tools and knowledge you need to optimize your AI workloads on the cloud.