<?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>部署优化 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E9%83%A8%E7%BD%B2%E4%BC%98%E5%8C%96/</link><description>Recent content in 部署优化 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>Thu, 02 Jul 2026 10:59:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E9%83%A8%E7%BD%B2%E4%BC%98%E5%8C%96/index.xml" rel="self" type="application/rss+xml"/><item><title>量化对性能影响2026实测：精度与效率的平衡术</title><link>https://guijiagi.com/posts/model-quantization-impact-2026/</link><pubDate>Thu, 02 Jul 2026 10:59:00 +0800</pubDate><guid>https://guijiagi.com/posts/model-quantization-impact-2026/</guid><description>2026年主流模型量化方案实测对比，从FP16到INT2的精度损失与性能提升</description></item><item><title>大模型推理加速2026：vLLM vs SGLang vs TensorRT-LLM</title><link>https://guijiagi.com/posts/llm-inference-speedup-2026/</link><pubDate>Tue, 30 Jun 2026 11:40:00 +0800</pubDate><guid>https://guijiagi.com/posts/llm-inference-speedup-2026/</guid><description>全面对比2026年三大推理引擎vLLM、SGLang和TensorRT-LLM的性能与特性</description></item></channel></rss>