<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Systalyze blog</title><description>Engineering notes, benchmarks and open-source releases from the Systalyze team.</description><link>https://www.systalyze.com/</link><language>en-us</language><item><title>Systalyze Pushes the LLM Inference Frontier: Up to 10× Faster Serving</title><link>https://www.systalyze.com/blog/systalyze-achieves-10x-faster-serving/</link><guid isPermaLink="true">https://www.systalyze.com/blog/systalyze-achieves-10x-faster-serving/</guid><description>How Systalyze composes serving optimizations across Gemma 4, Nemotron and Qwen3-32B, achieving up to 10× faster serving and cutting cost per output token by up to 73%.</description><pubDate>Fri, 25 Sep 2026 00:00:00 GMT</pubDate><category>Benchmarks</category><category>Inference</category></item><item><title>Your GPU dashboard is lying to you</title><link>https://www.systalyze.com/blog/your-gpu-dashboard-is-lying-to-you/</link><guid isPermaLink="true">https://www.systalyze.com/blog/your-gpu-dashboard-is-lying-to-you/</guid><description>The standard GPU utilization metric doesn’t measure what it claims to. Here’s what accurate measurement looks like, and an open-source tool to bring it to every AI deployment.</description><pubDate>Mon, 20 Apr 2026 00:00:00 GMT</pubDate><category>Open source</category><category>GPU efficiency</category></item></channel></rss>