On this page
Introduction
Block Diagram
Benefits
Latest News
Community
Get the Qualcomm® newsletter straight to your inbox.
Built for GenAI workloads. Made simple.
The ExecuTorch delegate for Hexagon NPU is integrated within the ExecuTorch repository and lets you offload AI/ML and Gen AI inference directly to the Hexagon NPU. ExecuTorch is an end-to-end solution for on-device inference across mobile and edge devices including wearables, embedded devices, and microcontrollers. It is part of the PyTorch Edge ecosystem and supports efficient deployment of PyTorch models to edge devices.
It can help to improve performance, reduce latency, support power efficiency, and provide users with personalized, offline experiences for consumer and industrial use case on devices powered by Qualcomm® technology.
ExecuTorch delegate for Qualcomm Hexagon NPU runs models on Qualcomm devices for better performance, lower latency, on-device access, and reduced costs.
