<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Edge-Devices on Phil Wheat</title><link>https://philwheat.net/tags/edge-devices/</link><description>Recent content in Edge-Devices on Phil Wheat</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 13 Oct 2026 08:41:00 -0500</lastBuildDate><atom:link href="https://philwheat.net/tags/edge-devices/index.xml" rel="self" type="application/rss+xml"/><item><title>SiMa.ai Palette</title><link>https://philwheat.net/links/sima-palette/</link><pubDate>Tue, 13 Oct 2026 08:41:00 -0500</pubDate><guid>https://philwheat.net/links/sima-palette/</guid><description>&lt;p&gt;SiMa.ai is an edge-AI chip company (Modalix MLSoC, ~50 TOPS at sub-10W, targeting drones, robotics, automotive, industrial vision). Palette is their software environment: &amp;ldquo;Palette Neat&amp;rdquo;, an agentic, containerized build environment where human+agent developers go from ONNX models to a running binary on the MLSoC in hours instead of months — model compiler toolchain, purpose-built physical-AI libraries, runtime orchestration on host and chip, plus a Model Browser and devkits. &amp;ldquo;Physical AI&amp;rdquo; here means on-device/embedded inference, not robotics research.&lt;/p&gt;</description></item></channel></rss>