In this demo, Sam Charrington (TWIML) is joined by Abhijit Khobare, the Director of Software Engineering at Qualcomm Technologies. In this video, we explore Qualcomm Innovation Center’s AI Model Efficiency Toolkit (AIMET), a library that provides users with advanced quantization and compression techniques from Qualcomm AI Research for trained neural network models. We discuss why AIMET is an important tool for developers working with edge devices, the benefits of quantization, the capabilities of the toolkit, and the ease of applying the quantization techniques in AIMET.
AIMET: github.com/quic/aimet
AIMET Model Zoo: github.com/quic/aimet-model-zoo
Qualcomm AI Research: www.qualcomm.com/research/art...