Don't miss out! Join us at our next Flagship Conference: KubeCon + CloudNativeCon Europe in Paris from March 19-22, 2024. Connect with our current graduated, incubating, and sandbox projects as the community gathers to further the education and advancement of cloud native computing. Learn more at [ Ссылка ]

WebAssembly for AI Infra : A Lightweight, Fast, and Secure Alternative Approach - Miley Fu, Second State Inc

WASM is lightweight, fast, and safe for the cloud, making them a good choice for a variety of applications, including AI inference. Rust+Wasm can be orders of magnitude faster and smaller than Python for AI inference apps. Wasm is an ideal sandbox to run Rust applications in the cloud. In this presentation, I will discuss the benefits of using WASM+Rust for AI infra. 1. Problems with the current Python+Docker combination in building large model infrastructure 2. Why the Rust + WebAssembly combination is better for building large model infrastructure 3. Rust + WebAssembly combination case sharing
What you will learn

Understand the motivations, advantages and disadvantages of using wasm in building large-scale model infrastructure
Understand WebAssembly's role in large model infrastructure, its strengths and weaknesses
Learn how to quickly deploy a serverless Rust+Wasm AI app in a serverless way

свернуть