The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for KubeCon + CloudNativeCon North America 2023 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.
Please note: This schedule is automatically displayed in Central Standard Time (UTC -6). To see the schedule in your preferred timezone, please select from the drop-down menu to the right, above "Filter by Date." The schedule is subject to change.
Recently, generative artificial intelligence (GenAI) has become mainstream with everyone exploring how to integrate it into their applications and workflows to increase productivity and enhance user experience. In game development, the applications of GenAI are boundless: creating art assets, auto-generating game code, life-like conversations with bots, and generating levels from player input. While most users are willing to wait seconds for inference, game developers need sub-second latency to ensure a good player experience. GenAI during gameplay brings demanding requirements - low latency, high performance, fast scalability, and low cost. Therefore, solving this use case will benefit the entire Kubernetes ecosystem. In this talk, we will present an in-depth analysis of deployment options for GenAI inference alongside applications running on Kubernetes. We will also demonstrate real-time GenAI inference integrated with distributed game servers running on Kubernetes using OSS Agones.
Ishan Sharma is a Senior Product Manager in Google Kubernetes Engine (GKE) at Google Cloud. He is focused on building GKE features for games workloads. He has years of product management and engineering leadership experience at large and small companies in the fields of cloud, AI... Read More →