Wasm as the Runtime for LLMs - Advantages and Applications
CNCF [Cloud Native Computing Foundation] via YouTube
Overview
Explore how WebAssembly (Wasm) is emerging as the preferred runtime for Large Language Models (LLMs) in this 27-minute conference talk by Michael Yuan from Second State. Learn why Python-based LLM applications are facing challenges due to speed, bloat, and installation complexities, and discover how compiled languages like C, C++, and Rust are gaining traction in LLM frameworks. Delve into the advantages of using Rust and Wasm for developing and running LLM applications, including improved efficiency, safety, and performance with a smaller footprint. Witness demonstrations of running Llama 2 models in Wasm and developing LLM agents in Rust. Gain insights into real-world applications, such as LLM-based code review and book-based learning assistants, through practical examples and demos presented by the speaker.
Syllabus
Wasm Is Becoming the Runtime for LLMs - Michael Yuan, Second State
Taught by
CNCF [Cloud Native Computing Foundation]