<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>SGLang on AI内参</title>
    <link>https://www.neican.ai/tags/sglang/</link>
    <description>Recent content in SGLang on AI内参</description>
    <generator>Hugo</generator>
    <language>zh-cn</language>
    <lastBuildDate>Wed, 10 Jun 2026 14:10:07 +0800</lastBuildDate>
    <atom:link href="https://www.neican.ai/tags/sglang/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>分布式推理的“云原生觉醒”：DeepSeek-V4 与 SGLang RBG 如何重塑国产 AI 基础设施架构</title>
      <link>https://www.neican.ai/insights/deepseek-v4-sglang-rbg-ai--20260610141007125-0/</link>
      <pubDate>Wed, 10 Jun 2026 14:10:07 +0800</pubDate>
      <guid>https://www.neican.ai/insights/deepseek-v4-sglang-rbg-ai--20260610141007125-0/</guid>
      <description>本文深度剖析了招商银行在国产 AI 芯片上部署 DeepSeek-V4 的技术创新，重点阐述了基于 SGLang RBG 实现分布式推理编排的路径，并预测了推理基础设施向高度自治、异构兼容演进的产业趋势。</description>
    </item>
  </channel>
</rss>
