<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>SageMaker on GPT资讯  --  知识铺</title>
    <link>https://index.zshipu.com/gpt/tags/SageMaker/</link>
    <description>Recent content in SageMaker on GPT资讯  --  知识铺</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-CN</language>
    <lastBuildDate>Wed, 09 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://index.zshipu.com/gpt/tags/SageMaker/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Qwen3.8-2.4T-A95B 在 Amazon SageMaker HyperPod 上通过 vLLM 完成部署</title>
      <link>https://index.zshipu.com/gpt/post/20260909/Qwen3.8-2.4T-A95B-%E5%9C%A8-Amazon-SageMaker-HyperPod-%E4%B8%8A%E9%80%9A%E8%BF%87-vLLM-%E5%AE%8C%E6%88%90%E9%83%A8%E7%BD%B2/</link>
      <pubDate>Wed, 09 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://index.zshipu.com/gpt/post/20260909/Qwen3.8-2.4T-A95B-%E5%9C%A8-Amazon-SageMaker-HyperPod-%E4%B8%8A%E9%80%9A%E8%BF%87-vLLM-%E5%AE%8C%E6%88%90%E9%83%A8%E7%BD%B2/</guid>
      <description>Qwen3.8-2.4T-A95B 在 Amazon SageMaker HyperPod 上通过 vLLM 完成部署 Qwen3.8-2.4T-A95B 是一款 2.4 万亿参数的开源权重模型，现可在 Amazon SageMaker HyperPod 上通过 vLLM 部署。该指南涵盖集群配置、NVFP4 量化，以及构建兼容 OpenAI 的端点，该端点支持内置推理、工具调用和原生 MTP 规范。 AWS 提供的部署流程让开发者能够在大规模算力集群上高效运行这一超大模型。整个过程聚焦于实际操作步骤</description>
    </item>
  </channel>
</rss>
