
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>马致良&#39;s Blog</title>
      <link>https://mpxy.cc/blog</link>
      <description>这里记录我的想法和见解 (Here, I record my thoughts and insights.)</description>
      <language>en-us</language>
      <managingEditor>mapinxue@qq.com (mapinxue)</managingEditor>
      <webMaster>mapinxue@qq.com (mapinxue)</webMaster>
      <lastBuildDate>Mon, 01 Jun 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://mpxy.cc/tags/本地部署/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://mpxy.cc/blog/local-llm-deployment</guid>
    <title>本地部署 LLM</title>
    <link>https://mpxy.cc/blog/local-llm-deployment</link>
    <description>从成本、数据安全、个人主机和算力集群几个角度，讨论为什么以及如何本地部署大语言模型。</description>
    <pubDate>Mon, 01 Jun 2026 00:00:00 GMT</pubDate>
    <author>mapinxue@qq.com (mapinxue)</author>
    <category>LLM</category><category>AI</category><category>本地部署</category><category>Ollama</category><category>算力集群</category>
  </item>

    </channel>
  </rss>
