<?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>剪枝 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%89%AA%E6%9E%9D/</link><description>Recent content in 剪枝 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>Mon, 13 Jul 2026 08:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%89%AA%E6%9E%9D/index.xml" rel="self" type="application/rss+xml"/><item><title>大模型压缩技术全景：剪枝、量化、蒸馏的工程实践</title><link>https://guijiagi.com/posts/article-91/</link><pubDate>Mon, 13 Jul 2026 08:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/article-91/</guid><description>系统梳理大模型压缩的三大技术路线，从原理到工程落地，让大模型跑在每一台设备上</description></item><item><title>LLM剪枝2026：结构化vs非结构化</title><link>https://guijiagi.com/posts/pruning-llm-2026/</link><pubDate>Thu, 02 Jul 2026 11:01:00 +0800</pubDate><guid>https://guijiagi.com/posts/pruning-llm-2026/</guid><description>从幅度剪枝到稀疏训练，系统对比LLM剪枝的两大路线及2026年最新方案</description></item><item><title>AI推理加速技术2026：量化、剪枝、蒸馏全景</title><link>https://guijiagi.com/posts/ai-inference-optimization-2026/</link><pubDate>Tue, 30 Jun 2026 09:10:00 +0800</pubDate><guid>https://guijiagi.com/posts/ai-inference-optimization-2026/</guid><description>2026年大模型推理优化全攻略：FP8/INT4量化、结构化/动态剪枝、知识蒸馏、推测解码、投机采样等核心技术的深度解析与实战对比</description></item></channel></rss>