<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>VMware on raimes.ai</title>
    <link>https://raimes.ai/categories/vmware/</link>
    <description>Recent content in VMware on raimes.ai</description>
    <image>
      <title>raimes.ai</title>
      <url>https://raimes.ai/images/og-default.jpg</url>
      <link>https://raimes.ai/images/og-default.jpg</link>
    </image>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 16 Oct 2026 09:00:04 +0200</lastBuildDate>
    <atom:link href="https://raimes.ai/categories/vmware/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>GPU architecture for model serving on VMware Cloud Foundation: whatever you pass through pins the VM</title>
      <link>https://raimes.ai/posts/gpu-architecture-for-model-serving-on-vcf/</link>
      <pubDate>Fri, 16 Oct 2026 09:00:04 +0200</pubDate>
      <guid>https://raimes.ai/posts/gpu-architecture-for-model-serving-on-vcf/</guid>
      <description>The second half of my Explore on Tour session, written down. Three ways to give a VM a GPU, how GPUs talk inside a server, and a two-letter grid for connecting GPU hosts.</description>
    </item>
    <item>
      <title>Private AI Services 3.0 on VMware Cloud Foundation 9.1.1: the five changes that matter</title>
      <link>https://raimes.ai/posts/private-ai-services-3-on-vcf-9-1-1/</link>
      <pubDate>Thu, 15 Oct 2026 09:00:00 +0200</pubDate>
      <guid>https://raimes.ai/posts/private-ai-services-3-on-vcf-9-1-1/</guid>
      <description>Notes from preparing a VMware Explore on Tour session. Model sharing, public models behind a private gateway, tenants without GPUs, three ways to log in, and the one rule that still decides your GPU design.</description>
    </item>
  </channel>
</rss>
