<?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>吞吐 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%90%9E%E5%90%90/</link><description>Recent content in 吞吐 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, 25 Jun 2026 10:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%90%9E%E5%90%90/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM 推理性能 Benchmark：TTFT/TPS/延迟全景对比</title><link>https://guijiagi.com/posts/llm-latency-benchmark/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/llm-latency-benchmark/</guid><description>LLM 推理性能关键指标、测试方法论与主流模型全景对比</description></item></channel></rss>