With the rise of containerization and edge computing, the demand for portable, efficient, and low-latency solutions is growing. WebAssembly (WASM), known for its small size and fast loading, is expanding beyond the browser into containerized and edge environments. When combined with CNCF projects like Kraken, WasmEdge Runtime, and containerd, WASM can unlock hardware accelerators (GPU, TPU, FPGA) to revolutionize AI/ML workloads across both containerized and edge deployments.

In this talk, we’ll explore:

1. How Kraken and WasmEdge Runtime enable seamless integration of WASM into containerized environments for enhanced performance.
2. Live demos showcasing WASM-powered containers running AI workloads across various hardware platforms.

By the end of this talk, you'll know how to take your containerized and edge AI/ML workloads to the next level with speed, portability, and hardware acceleration.