Deeplite platform accelerates AI on Arm CPUs through quantisation

Deeplite platform accelerates AI on Arm CPUs through quantisation
Fin is an experienced editor with a focus on the frontlines of global business news and cutting-edge technological trends. He has published engaging interviews with leading industry figures from the likes of CBS, Rakuten, Spotify, and more. When not tapping away behind a laptop, he can be found researching and exploring the cryptocurrency and NFT markets. You can follow his Twitter @FinStrathern or connect with him at

Deeplite, a Canadian AI software company, has unveiled its Deeplite Runtime (DeepliteRT) platform that makes AI models smaller and faster without compromising accuracy.

Thanks to quantisation, customers will benefit from reduced power consumption and the ability to use existing Arm CPUs to run AI models with GPU-level performance.

AI optimisation’s importance is growing in an industry where edge devices are increasingly being turned to. Making AI models run on small edge devices with limited power budgets, such as security cameras, drones, and mobile phones, is becoming a central challenge for developers.

DeepliteRT solves this challenge by running ultra-compact quantised models on commodity Arm processors whilst maintaining model accuracy.

Nick Romano, CEO and co-founder at Deeplite, said: “Multiple industries continue to look for new ways to do more on the edge. It is where users interact with devices and applications and businesses connect with customers.

“However, the resource limitations of edge devices are holding them back. DeepliteRT helps enterprises to roll out AI quickly on existing edge hardware, which can save time and reduce costs by avoiding the need to replace current edge devices with more expensive hardware.”

Deeplite has partnered with Arm to run DeepliteRT on its Cortex-A Series CPUs in everyday devices such as home security cameras.

Businesses can run complex AI tasks on these low-power CPUs, eliminating the need for expensive and power-hungry GPU-based hardware solutions that limit AI adoption.

Bradley Shimmin, chief analyst for AI platforms, analytics, and data management at Omdia, added: “To make AI more accessible and human-centered, it needs to function closer to where people live and work.

“By making AI smaller and faster, Deeplite is helping to bring AI to new edge applications and new products, services and places where it can benefit more people and organisations.”

Looking to revamp your digital transformation strategy? Learn more about the in-person Digital Transformation Week North America taking place in Santa Clara, CA on 11-12 May and discover key strategies for making your digital efforts a success.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

Tags: , , , , , ,

View Comments
Leave a comment

Leave a Reply