<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Serverless</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Serverless feed</description>
    <item>
      <title>AWS Lambda Now Runs GPU Inference with 48 Concurrent Invocations Sharing One Model per GPU</title>
      <link>https://www.infoq.com/news/2026/11/aws-lambda-gpu-managed-instances/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Serverless</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/11/aws-lambda-gpu-managed-instances/en/headerimage/generatedHeaderImage-1795178998128.jpg"/&gt;&lt;p&gt;AWS Lambda now runs Event Functions on EC2 G-series GPU instances through Lambda Managed Instances, with up to 48 concurrent invocations sharing one model per GPU, vLLM and SGLang base images that need no handler code, and 90-minute asynchronous timeouts. Billing is the instance price plus a 9.75 percent fee; first hands-on tests report an eight-minute publish and no response streaming.&lt;/p&gt; &lt;i&gt;By Steef-Jan Wiggers&lt;/i&gt;</description>
      <category>Amazon Web Services</category>
      <category>EC2</category>
      <category>AWS</category>
      <category>Serverless</category>
      <category>Cloud</category>
      <category>AWS Lambda</category>
      <category>GPU</category>
      <category>DevOps</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>Development</category>
      <category>Architecture &amp; Design</category>
      <category>news</category>
      <pubDate>Sun, 22 Nov 2026 06:27:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/11/aws-lambda-gpu-managed-instances/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Serverless</guid>
      <dc:creator>Steef-Jan Wiggers</dc:creator>
      <dc:date>2026-11-22T06:27:00Z</dc:date>
      <dc:identifier>/news/2026/11/aws-lambda-gpu-managed-instances/en</dc:identifier>
    </item>
  </channel>
</rss>
