Leveraging Wasm for Portable AI Inference Across GPUs, CPUs, OS and Cloud-Native Environments

Explore the advantages of using WebAssembly (Wasm) for AI inference tasks in cloud-native ecosystems through this 25-minute conference talk. Discover how Wasm enables developers to create AI applications on their personal computers that can be uniformly executed across various hardware platforms, including GPUs, CPUs, operating systems, and edge cloud environments. Learn about Wasm's seamless integration with cloud-native frameworks, enhancing the deployment and scalability of AI applications. Gain insights into how Wasm provides a flexible and efficient solution for diverse cloud-native architectures, including Kubernetes, allowing developers to fully harness the potential of large language models (LLMs), particularly open-source ones. Tailored for cloud-native practitioners and AI developers, this talk offers valuable knowledge on maximizing AI application potential by leveraging Wasm's cross-platform capabilities, ensuring consistency, cost-effectiveness, and efficiency in AI inference across various computing environments.