<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>Alibaba Cloud on Shaowen Chen's Website</title><link>https://www.chenshaowen.com/en/tags/alibaba-cloud/</link><description>Recent content in Alibaba Cloud on Shaowen Chen's Website</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>&amp;copy;2016 - {year}, All Rights Reserved.</copyright><lastBuildDate>Sat, 17 Jan 2026 00:00:00 +0000</lastBuildDate><sy:updatePeriod>weekly</sy:updatePeriod><atom:link href="https://www.chenshaowen.com/en/tags/alibaba-cloud/atom.xml" rel="self" type="application/rss+xml"/><item><title>Alibaba Cloud eRDMA Testing and PD Disaggregation Application Deployment</title><link>https://www.chenshaowen.com/en/blog/test-and-deploy-pd-disagg-app-with-erdma-on-aliyun.html</link><pubDate>Sat, 17 Jan 2026 00:00:00 +0000</pubDate><atom:modified>Sat, 17 Jan 2026 00:00:00 +0000</atom:modified><guid>https://www.chenshaowen.com/en/blog/test-and-deploy-pd-disagg-app-with-erdma-on-aliyun.html</guid><description>In a PD disaggregated deployment, heterogeneous GPU models are often used to deploy the model across machines, which multiplies the cross-machine communication pressure. RDMA devices are usually brought in to accelerate kvcache transfer between nodes so as to achieve a lower FTTL. This post describes how to test eRDMA devices</description><dc:creator>微信公众号</dc:creator><category>Alibaba Cloud</category><category>eRDMA</category><category>RDMA</category><category>PD</category><category>Disaggregation</category><category>AI</category><category>Application</category><category>Operations</category></item></channel></rss>