<?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>lmcache on Shaowen Chen's Website</title><link>https://www.chenshaowen.com/en/tags/lmcache/</link><description>Recent content in lmcache on Shaowen Chen's Website</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>&amp;copy;2016 - {year}, All Rights Reserved.</copyright><lastBuildDate>Wed, 17 Sep 2025 00:00:00 +0000</lastBuildDate><sy:updatePeriod>weekly</sy:updatePeriod><atom:link href="https://www.chenshaowen.com/en/tags/lmcache/atom.xml" rel="self" type="application/rss+xml"/><item><title>Using lmcache Can Significantly Improve TTFT in Model Inference</title><link>https://www.chenshaowen.com/en/blog/use-lmcache-to-improve-ttft.html</link><pubDate>Wed, 17 Sep 2025 00:00:00 +0000</pubDate><atom:modified>Wed, 17 Sep 2025 00:00:00 +0000</atom:modified><guid>https://www.chenshaowen.com/en/blog/use-lmcache-to-improve-ttft.html</guid><description>1. Introduction to LMCache TTFT is the time from when a request is issued until the model generates its first token. Because the Prefill phase has to encode the input context into a KV Cache before generation can begin, producing that first token requires a large amount of computation, which makes TTFT high.</description><dc:creator>微信公众号</dc:creator><category>AI</category><category>LLM</category><category>vLLM</category><category>Inference</category><category>lmcache</category><category>Operations</category></item></channel></rss>