<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Deep Learning Container on 知识铺的博客</title>
    <link>https://index.zshipu.com/ai002/tags/Deep-Learning-Container/</link>
    <description>Recent content in Deep Learning Container on 知识铺的博客</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-CN</language>
    <lastBuildDate>Thu, 10 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://index.zshipu.com/ai002/tags/Deep-Learning-Container/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>TorchServe 停止维护后，AWS Ray Serve Deep Learning Container 如何简化工作负载</title>
      <link>https://index.zshipu.com/ai002/post/20260910/TorchServe-%E5%81%9C%E6%AD%A2%E7%BB%B4%E6%8A%A4%E5%90%8EAWS-Ray-Serve-Deep-Learning-Container-%E5%A6%82%E4%BD%95%E7%AE%80%E5%8C%96%E5%B7%A5%E4%BD%9C%E8%B4%9F%E8%BD%BD/</link>
      <pubDate>Thu, 10 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://index.zshipu.com/ai002/post/20260910/TorchServe-%E5%81%9C%E6%AD%A2%E7%BB%B4%E6%8A%A4%E5%90%8EAWS-Ray-Serve-Deep-Learning-Container-%E5%A6%82%E4%BD%95%E7%AE%80%E5%8C%96%E5%B7%A5%E4%BD%9C%E8%B4%9F%E8%BD%BD/</guid>
      <description>TorchServe 停止维护后的推理栈负担 TorchServe 不再维护，这直接让团队不得不自己承担整个 GPU 推理栈。过去依赖 TorchServe 的团队现在面临维护框架、驱动和 serving 组件的全部责任。每个环节都需要单独验证和更新，增加了运维复杂度和潜在风险。 这种变化迫使开发者和运维人员重新评估现有推理管道。原本集成的 TorchServe 工作负载现在需要寻找替代方</description>
    </item>
  </channel>
</rss>
