Deploying LLM Workloads on Kubernetes with WasmEdge and Kuasar

Explore the deployment of Large Language Model (LLM) workloads on Kubernetes using WasmEdge and Kuasar in this keynote presentation. Discover how these innovative solutions address challenges in running LLMs, including complex package installations, GPU compatibility issues, scaling limitations, and security vulnerabilities. Learn how WasmEdge enables the development of fast, agile, resource-efficient, and secure LLM applications, while Kuasar facilitates running applications on Kubernetes with faster container startup and reduced management overhead. Witness a demonstration of running Llama3-8B on a Kubernetes cluster using WasmEdge and Kuasar as container runtimes. Gain insights into how Kubernetes enhances efficiency, scalability, and stability in LLM deployment and operations, making this 14-minute presentation essential for those interested in advanced cloud-native AI solutions.