The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) cover image

Open Source at Qualcomm AI Research with Jeff Gehlhaar and Zahra Koochak - #414

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

00:00

Enhancing AI Efficiency on Edge Devices

This chapter explores advancements in running machine learning models on edge devices using the AI Model Efficiency Toolkit Library (AMET). The speakers discuss techniques for model compression and quantization, highlighting both manual and automatic modes for optimal performance. Additionally, they delve into the integration of AMET with frameworks like TensorFlow and PyTorch, as well as the role of the TVM compiler in optimizing model efficiency for various hardware.

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