Listen now (52 mins) | Compilers are all you need. How XGBoost and TVM were created, and the future of universal model deployments with MLC!
Fascinating! I wonder if these can be made to run on the AI coprocessors in so many SoCs these days
LLMs Everywhere: Running 70B models in browsers and iPhones using MLC — with Tianqi Chen of CMU / OctoML
Fascinating! I wonder if these can be made to run on the AI coprocessors in so many SoCs these days