
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>The Herd Mentality</title>
      <link>https://www.herdmentality.xyz/blog</link>
      <description>The Herd Mentality is a technical blog on data science, statistics, machine learning, R, and software engineering, with hands-on tutorials and write-ups.</description>
      <language>en-us</language>
      <managingEditor> (Herd Mentality)</managingEditor>
      <webMaster> (Herd Mentality)</webMaster>
      <lastBuildDate>Mon, 07 Sep 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://www.herdmentality.xyz/tags/gpu/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://www.herdmentality.xyz/blog/llm-inference-vocabulary</guid>
    <title>Running your own LLMs (for beginners)</title>
    <link>https://www.herdmentality.xyz/blog/llm-inference-vocabulary</link>
    <description>A working glossary of LLM inference workloads running on GPUs</description>
    <pubDate>Mon, 07 Sep 2026 00:00:00 GMT</pubDate>
    <author> (Herd Mentality)</author>
    <category>llm</category><category>gpu</category><category>inference</category><category>vllm</category><category>machine-learning</category>
  </item>

    </channel>
  </rss>
