10 Aug 2023

LLMs Everywhere: Running 70B models in browsers and iPhones using MLC — with Tianqi Chen of CMU / OctoML

Latent Space: The AI Engineer Podcast — Practitioners talking LLMs, CodeGen, Agents, Multimodality, AI UX, GPU Infra and all things Software 3.0

This podcast episode features Tianqi Chen, an assistant professor at CMU and chief technologist of AutoML. He shares his passion for coding, detailing how he uses sketchbooks to design and develop open-source projects. The conversation moves to XGBoost, a gradient boosting library, and its surprising success in machine learning competitions. The experts discuss the potential for merging tree-based and deep learning models and the journey of an engineer from working on XGBoost to building TVM, a popular compiler framework. They delve into topics such as Machine Learning Compilation (MLC), optimization techniques, and the importance of optimizing models for different hardware platforms.

Takeaways

Outlines

Q & A

Preview

How to Get Rich: Every EpisodeNaval