We held our next tinyML Talks webcast. Chris Hoge from OctoML has presented An Introduction to Optimizing ML Models with TVMC on February 18, 2021.
Currently, deep learning systems rely on vendor-provided kernel libraries or various search strategies to get performant tensor programs. This talk will give an introduction to TVMC, a front-end to the Apache TVM deep learning compiler stack that can build optimized models for a variety of different platforms. It will cover how TVM works at a high level, then give a practical introduction on how to use TVMC in practice.
Chris Hoge has more than 10 years of experience in helping build open source communities, including strategic program management for the OpenStack Foundation and as a SIG co-founder in the Kubernetes community. He has a background in Applied Mathematics, and lives in the PNW.
Watch on YouTube:
Download presentation slide:
Feel free to ask your questions on this thread and keep the conversation going!