Software Engineering Radio - the podcast for professional software developers cover image

Episode 479: Luis Ceze on the Apache TVM Machine Learning Compiler

Software Engineering Radio - the podcast for professional software developers

00:00

How to Deploy a Model on Multiple Architectures?

You can run this on multiple talk at architectures. One is, like we've discussed, about performance in order to get best out of your model. But are there other reasons why you would want to run it on different archit architecture? And that doing up positions like what anbis is an enabler, right? So theng. Some usegats we've had here was employed in a pretty unique but popular architecture, dat is deployed in cameras. And we offered at 30 acts better performance. It's likely to be true for its for self driving cars and in altomos vehicles in generaere as you deploy a fleet of those. The second one is, when you

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app