<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>On-Device on SoloSoft</title><link>https://www.solosoft.dev/tags/on-device/</link><description>Recent content in On-Device on SoloSoft</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 01 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.solosoft.dev/tags/on-device/index.xml" rel="self" type="application/rss+xml"/><item><title>MNN: Alibaba's Blazing-Fast Lightweight Inference Engine for Mobile and Edge AI</title><link>https://www.solosoft.dev/post/mnn-mobile-inference-2026/</link><pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate><guid>https://www.solosoft.dev/post/mnn-mobile-inference-2026/</guid><description>&lt;p&gt;Running deep learning models on mobile and edge devices presents unique challenges: limited compute power, constrained memory, battery sensitivity, and diverse hardware architectures. &lt;strong&gt;MNN&lt;/strong&gt; (Mobile Neural Network) is Alibaba&amp;rsquo;s answer to these challenges, a lightweight inference engine that brings AI to the edge with minimal overhead and maximum performance.&lt;/p&gt;
&lt;p&gt;MNN powers over 30 of Alibaba&amp;rsquo;s applications, including Taobao (e-commerce), Youku (video streaming), and various enterprise tools. It has been battle-tested at billion-user scale, handling everything from real-time computer vision to on-device large language models. The engine&amp;rsquo;s small binary size (under 500 KB for the core runtime) and minimal runtime memory footprint make it suitable even for low-end devices.&lt;/p&gt;</description></item></channel></rss>