<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>RadixAttention on Yiwen Cai</title><link>https://yiwen-cai.github.io/tags/radixattention/</link><description>Recent content in RadixAttention on Yiwen Cai</description><generator>Hugo -- gohugo.io</generator><language>zh-cn</language><managingEditor>caiyiwen.cs@foxmail.com (Yiwen Cai)</managingEditor><webMaster>caiyiwen.cs@foxmail.com (Yiwen Cai)</webMaster><copyright>© 2026 Yiwen Cai</copyright><lastBuildDate>Tue, 03 Nov 2026 16:17:09 +0800</lastBuildDate><atom:link href="https://yiwen-cai.github.io/tags/radixattention/index.xml" rel="self" type="application/rss+xml"/><item><title>SGLang 架构精读（一）：从三级页表、Piecewise CUDA Graph 到 MLA 矩阵吸收与投机解码</title><link>https://yiwen-cai.github.io/notes/llm-inference/sglang-single-gpu-engine/</link><pubDate>Tue, 03 Nov 2026 00:00:00 +0000</pubDate><author>caiyiwen.cs@foxmail.com (Yiwen Cai)</author><guid>https://yiwen-cai.github.io/notes/llm-inference/sglang-single-gpu-engine/</guid><description>以单步耗时方程 t_step = max(t_cpu, t_comm, max(t_mem, t_compute)) 与 H100 上 Llama-3-8B 的硬件账本为主线，系统拆解 SGLang 单卡引擎与编译器栈（Ch 01–15）：涵盖 page_size=1 三级页表、RadixCache 末位盲区、Overlap Scheduling 双缓冲闭环、Piecewise CUDA Graph 拆图算术、Dynamo/Inductor 融合、DeepSeek MLA 矩阵吸收（128 FLOP/byte）及三代投机解码（EAGLE-3 / DFlash / DSpark）。</description></item></channel></rss>