<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>CUDA on Jiayun's Blog</title><link>https://xiejiayun.github.io/tags/cuda/</link><description>Recent content in CUDA on Jiayun's Blog</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Tue, 19 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://xiejiayun.github.io/tags/cuda/index.xml" rel="self" type="application/rss+xml"/><item><title>【好文共赏】把 2000 秒砍成 50 秒：Modal 五年工程账本，从 LP 求解器到 CUDA Checkpoint 的『真·无服务器 GPU』栈</title><link>https://xiejiayun.github.io/post/good-read-modal-serverless-gpu-cold-starts/</link><pubDate>Tue, 19 May 2026 00:00:00 +0000</pubDate><guid>https://xiejiayun.github.io/post/good-read-modal-serverless-gpu-cold-starts/</guid><description>&lt;h2 id="-编辑推荐框">📌 编辑推荐框&lt;/h2>
&lt;blockquote>
&lt;p>&lt;strong>好文共赏 | Editor&amp;rsquo;s Pick&lt;/strong>&lt;/p>
&lt;p>原文：&lt;a href="https://modal.com/blog/truly-serverless-gpus">Cutting inference cold starts by 40x with LP, FUSE, C/R, and CUDA-checkpoint&lt;/a> · 作者：Charles Frye / Jonathan Belotti / Erik Bernhardsson / Akshat Bubna（Modal） · 发布：2026-05-12 · 阅读时长：~20 分钟&lt;/p></description></item><item><title>DeepSeek V4延期与去CUDA化：中国AI生态的关键抉择</title><link>https://xiejiayun.github.io/post/deepseek-v4-de-cuda-ecosystem-2026/</link><pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate><guid>https://xiejiayun.github.io/post/deepseek-v4-de-cuda-ecosystem-2026/</guid><description>&lt;h2 id="v4为什么迟迟不来">V4为什么迟迟不来&lt;/h2>
&lt;p>2026年已经过去近四个月，DeepSeek V4的发布窗口一再推迟。这款预计参数规模达万亿级、支持百万token上下文的多模态开源模型，已成为AI社区最受期待的发布之一。&lt;/p></description></item></channel></rss>