<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>JAX on KAD</title>
    <link>https://www.kad8.com/tags/jax/</link>
    <description>Recent content in JAX on KAD</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <copyright>© 2026 </copyright>
    <lastBuildDate>Fri, 17 Jul 2026 17:24:57 +0800</lastBuildDate><atom:link href="https://www.kad8.com/tags/jax/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>AMD ROCm 7.14 Adds Early Support for Ryzen AI MAX PRO 400</title>
      <link>https://www.kad8.com/software/amd-rocm-7.14-adds-early-support-for-ryzen-ai-max-pro-400/</link>
      <pubDate>Fri, 17 Jul 2026 17:24:57 +0800</pubDate>
      
      <guid>https://www.kad8.com/software/amd-rocm-7.14-adds-early-support-for-ryzen-ai-max-pro-400/</guid>
      <description>&lt;blockquote&gt;
&lt;p&gt;AMD ROCm 7.14 Adds Early Support for Ryzen AI MAX PRO 400&lt;/p&gt;&lt;/blockquote&gt;
&lt;p&gt;AMD has added early support for its upcoming Ryzen AI MAX PRO 400 series to the ROCm 7.14 open-source software stack. The processors, codenamed Gorgon Halo, are expected to launch in the coming weeks, giving developers an opportunity to prepare AI and high-performance computing workloads before the hardware reaches the market.&lt;/p&gt;</description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/software/amd-rocm-7.14-adds-early-support-for-ryzen-ai-max-pro-400/featured-Processor_rendering_with_command.jpeg" />
    </item>
    
    <item>
      <title>Google TPU Evolution: From TPU v2 to Ironwood in 8 Years</title>
      <link>https://www.kad8.com/ai/google-tpu-evolution-from-tpu-v2-to-ironwood-in-8-years/</link>
      <pubDate>Thu, 25 Jun 2026 23:51:38 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/google-tpu-evolution-from-tpu-v2-to-ironwood-in-8-years/</guid>
      <description>&lt;blockquote&gt;
&lt;p&gt;Google TPU Evolution: From TPU v2 to Ironwood in 8 Years&lt;/p&gt;&lt;/blockquote&gt;
&lt;p&gt;When discussing advanced chip design, companies such as Intel, AMD, and NVIDIA traditionally dominate the conversation. However, in 2016, Google fundamentally altered the landscape by introducing a custom AI accelerator known as the Tensor Processing Unit (TPU).&lt;/p&gt;</description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/google-tpu-evolution-from-tpu-v2-to-ironwood-in-8-years/featured-Google_TPU_generations_AI_infrastructure.jpeg" />
    </item>
    
    <item>
      <title>Google TPU v4: The Fastest AI Supercomputer at MLPerf 0.7</title>
      <link>https://www.kad8.com/ai/google-tpu-v4-the-fastest-ai-supercomputer-at-mlperf-0.7/</link>
      <pubDate>Wed, 29 Jul 2020 23:11:42 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/google-tpu-v4-the-fastest-ai-supercomputer-at-mlperf-0.7/</guid>
      <description>&lt;blockquote&gt;
&lt;p&gt;Google TPU v4: The Fastest AI Supercomputer at MLPerf 0.7&lt;/p&gt;&lt;/blockquote&gt;
&lt;p&gt;Google&amp;rsquo;s fourth-generation Tensor Processing Unit (TPU v4) demonstrated how aggressively optimized AI accelerators can exploit massive system-level scale.&lt;/p&gt;</description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/google-tpu-v4-the-fastest-ai-supercomputer-at-mlperf-0.7/featured-Google-TPU-V4-supercomputer_datacenter.jpeg" />
    </item>
    
  </channel>
</rss>
