<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>GPU on Edwardesire</title><link>/en/tags/gpu/</link><description>Recent content in GPU on Edwardesire</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>&amp;copy; 2021 &lt;a href="https://www.edwardesire.com/">Edward Desire&lt;/a></copyright><lastBuildDate>Sun, 18 Oct 2026 11:40:00 +0800</lastBuildDate><atom:link href="/en/tags/gpu/index.xml" rel="self" type="application/rss+xml"/><item><title>Accelerating LLM Inference Cold Starts: From the First Instance to Scale-Out</title><link>/en/posts/inference-cold-start-acceleration/</link><pubDate>Sun, 18 Oct 2026 11:40:00 +0800</pubDate><guid>/en/posts/inference-cold-start-acceleration/</guid><description>This article was translated from the Chinese original using AI and reviewed by the author.
As large language model applications grow, inference services have become a core workload in AI infrastructure. For platform teams, the challenge extends beyond simply getting a model to run; they must also ensure that compute capacity keeps pace with changing demand.
On a Model-as-a-Service (MaaS) platform, request volumes can vary significantly between different models, and even the same model&amp;rsquo;s traffic can fluctuate throughout the day.</description></item></channel></rss>