<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>OneNexus Blog</title><description>Technical reports on model serving, AI infrastructure, platform architecture, and the work behind production systems.</description><link>https://onenexus-do.cloud/</link><item><title>GLM-5.2 on AMD GPUs: Solving 5 of 6 IMO 2026 Problems</title><link>https://onenexus-do.cloud/blog/glm-52-imo-2026/</link><guid isPermaLink="true">https://onenexus-do.cloud/blog/glm-52-imo-2026/</guid><description>How OneNexus used GLM-5.2 on AMD MI355X to score 37/42 in our documented internal evaluation of the IMO 2026 problems — not an official IMO result.</description><pubDate>Fri, 31 Jul 2026 00:00:00 GMT</pubDate><category>GLM-5.2</category><category>AMD</category><category>Inference</category><category>IMO</category></item></channel></rss>