<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Model Performance on AI VOID</title><link>https://ai-blog.noorshomelab.dev/tags/model-performance/</link><description>Recent content in Model Performance on AI VOID</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 20 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://ai-blog.noorshomelab.dev/tags/model-performance/index.xml" rel="self" type="application/rss+xml"/><item><title>Data Validation &amp;amp; Quality Checks</title><link>https://ai-blog.noorshomelab.dev/metadataflow-guide-2026/07-data-validation-quality/</link><pubDate>Wed, 28 Jan 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/metadataflow-guide-2026/07-data-validation-quality/</guid><description>&lt;h2 id="introduction-to-data-validation--quality-checks"&gt;Introduction to Data Validation &amp;amp; Quality Checks&lt;/h2&gt;
&lt;p&gt;Welcome back, data explorer! In our previous chapters, we&amp;rsquo;ve learned how to load, inspect, and perform basic transformations on our datasets using Meta&amp;rsquo;s powerful open-source library. But what good is a beautifully processed dataset if the underlying data itself is flawed? This is where &lt;strong&gt;Data Validation and Quality Checks&lt;/strong&gt; come into play, and it&amp;rsquo;s the heart of what we&amp;rsquo;ll master in this chapter.&lt;/p&gt;</description></item><item><title>Monitoring and Observability for Production LLMs</title><link>https://ai-blog.noorshomelab.dev/llmops-ai-infra-guide-2026/monitoring-observability-production-llms/</link><pubDate>Fri, 20 Mar 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/llmops-ai-infra-guide-2026/monitoring-observability-production-llms/</guid><description>&lt;h2 id="monitoring-and-observability-for-production-llms"&gt;Monitoring and Observability for Production LLMs&lt;/h2&gt;
&lt;p&gt;Welcome back, fellow MLOps engineers and data scientists! In our previous chapters, we&amp;rsquo;ve explored the exciting world of building robust LLM inference pipelines, optimizing them for GPU usage, implementing smart caching strategies, and designing for scalability. We&amp;rsquo;ve laid a strong foundation, but there&amp;rsquo;s a crucial piece missing: How do we &lt;em&gt;know&lt;/em&gt; if our systems are actually performing as expected in the wild? How do we catch issues before our users do?&lt;/p&gt;</description></item></channel></rss>