"TVM: An End to End Deep Learning Compiler Stack" by Thiery Moreau (OctoML)

Talk given on Oct 21, 2020 for the internal Harvard offering of the Intro to TinyML course.
Dr. Thierry Moreau is the co-founder of OctoML Inc., a Seattle-based startup that applies state of the art ML-based techniques to make deep learning models faster and easier to put into production. Thierry has been a key contributor to Apache TVM, the open source machine learning compiler that started at University of Washington, where Thierry got his Ph.D. TVM aims to make deep learning optimization and deployment easier across a wide range of hardware backends. Today, Thierry leads a team of engineers at OctoML that leverages TVM in order to seamlessly deploy ML models on various novel hardware platforms ranging from data-center GPUs down to accelerator-rich smartphone SoCs and low-power microcontrollers.
See more: sites.google.c...

[@vil9386]

wow, wonderful content on TVM.

[@ta0x1c]

This is a really awesome introduction of TVM

[@middleclassprogrammer7202]

well explained!

[@prizmaweb]

Brilliant

[@prathameshkhadse8329]

29:00