<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>GQA on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/gqa/</link><description>Recent content in GQA on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Sun, 28 Jun 2026 11:01:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/gqa/index.xml" rel="self" type="application/rss+xml"/><item><title>注意力机制全景解析：Self/Cross/Multi-Query/Latent Attention</title><link>https://guijiagi.com/posts/attention-mechanisms-panorama/</link><pubDate>Sun, 28 Jun 2026 11:01:00 +0800</pubDate><guid>https://guijiagi.com/posts/attention-mechanisms-panorama/</guid><description>系统解析2026年主流注意力机制变体：Self-Attention、Cross-Attention、Multi-Query、Grouped-Query、Latent Attention的原理、数学推导与工程实现</description></item><item><title>KV Cache 优化全攻略：从 PagedAttention 到 MLA</title><link>https://guijiagi.com/posts/kv-cache-optimization-pagedattention-to-mla/</link><pubDate>Sun, 28 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/kv-cache-optimization-pagedattention-to-mla/</guid><description>大模型KV Cache优化技术全景解析：PagedAttention、GQA、MQA、MLA原理与实测对比</description></item></channel></rss>