<?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>流式 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%B5%81%E5%BC%8F/</link><description>Recent content in 流式 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/%E6%B5%81%E5%BC%8F/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM 流式响应实现指南：SSE vs WebSocket vs gRPC</title><link>https://guijiagi.com/posts/llm-streaming-implementation-deep/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/llm-streaming-implementation-deep/</guid><description>深入对比 SSE、WebSocket、gRPC 三种流式协议在 LLM 场景下的实现，包含前后端代码示例与生产级最佳实践</description></item><item><title>实时 Agent 架构设计：低延迟智能体</title><link>https://guijiagi.com/posts/realtime-agent-architecture/</link><pubDate>Wed, 24 Jun 2026 14:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/realtime-agent-architecture/</guid><description>探讨实时 Agent 架构设计，涵盖 WebSocket/SSE 流式输出、流式推理、管道并行、延迟优化与边缘部署策略</description></item></channel></rss>