<?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>延迟 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%BB%B6%E8%BF%9F/</link><description>Recent content in 延迟 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>Tue, 30 Jun 2026 11:25:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%BB%B6%E8%BF%9F/index.xml" rel="self" type="application/rss+xml"/><item><title>Agent性能基准测试：吞吐、延迟、并发全评测</title><link>https://guijiagi.com/posts/agent-performance-benchmark-throughput-latency/</link><pubDate>Tue, 30 Jun 2026 11:25:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-performance-benchmark-throughput-latency/</guid><description>系统介绍Agent系统性能基准测试的方法论与工具，涵盖吞吐量测试、延迟分析、并发压力测试及结果解读</description></item><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><item><title>多区域 LLM 部署：全球低延迟 AI 服务</title><link>https://guijiagi.com/posts/multi-region-llm-deploy/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/multi-region-llm-deploy/</guid><description>多区域 LLM 部署架构：GeoDNS 流量路由、数据合规、模型同步、灾难恢复与成本分析</description></item></channel></rss>