<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLM推理优化 on zzszmyf</title><link>https://zzszmyf.github.io/tags/llm%E6%8E%A8%E7%90%86%E4%BC%98%E5%8C%96/</link><description>Recent content in LLM推理优化 on zzszmyf</description><generator>Hugo</generator><language>zh-CN</language><copyright>© 2026 zzszmyf</copyright><lastBuildDate>Mon, 17 Aug 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://zzszmyf.github.io/tags/llm%E6%8E%A8%E7%90%86%E4%BC%98%E5%8C%96/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM 推理优化 · 量化（Quantization）系统学习笔记</title><link>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E7%90%86%E4%BC%98%E5%8C%96-quantization%E9%87%8F%E5%8C%96%E5%AD%A6%E4%B9%A0%E7%AC%94%E8%AE%B0/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E7%90%86%E4%BC%98%E5%8C%96-quantization%E9%87%8F%E5%8C%96%E5%AD%A6%E4%B9%A0%E7%AC%94%E8%AE%B0/</guid><description/></item><item><title>LLM 量化精读笔记 · 00 总览与学习地图</title><link>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-00-%E6%80%BB%E8%A7%88%E4%B8%8E%E5%AD%A6%E4%B9%A0%E5%9C%B0%E5%9B%BE/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-00-%E6%80%BB%E8%A7%88%E4%B8%8E%E5%AD%A6%E4%B9%A0%E5%9C%B0%E5%9B%BE/</guid><description/></item><item><title>LLM 量化精读笔记 · 01 数值编码与计算机表示基础（信息论 · 整数 · IEEE 754 · 舍入与截断）</title><link>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-01-%E6%95%B0%E5%80%BC%E7%BC%96%E7%A0%81%E4%B8%8E%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A1%A8%E7%A4%BA%E5%9F%BA%E7%A1%80/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-01-%E6%95%B0%E5%80%BC%E7%BC%96%E7%A0%81%E4%B8%8E%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A1%A8%E7%A4%BA%E5%9F%BA%E7%A1%80/</guid><description/></item><item><title>LLM 量化精读笔记 · 02 量化问题的形式化与均匀量化理论</title><link>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-02-%E9%87%8F%E5%8C%96%E9%97%AE%E9%A2%98%E5%BD%A2%E5%BC%8F%E5%8C%96%E4%B8%8E%E5%9D%87%E5%8C%80%E9%87%8F%E5%8C%96%E7%90%86%E8%AE%BA/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-02-%E9%87%8F%E5%8C%96%E9%97%AE%E9%A2%98%E5%BD%A2%E5%BC%8F%E5%8C%96%E4%B8%8E%E5%9D%87%E5%8C%80%E9%87%8F%E5%8C%96%E7%90%86%E8%AE%BA/</guid><description/></item><item><title>LLM 量化精读笔记 · 03 数值格式：FP16 / BF16 / FP8 / FP4 / MXFP8 / NVFP4 与硬件</title><link>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-03-%E6%95%B0%E5%80%BC%E6%A0%BC%E5%BC%8F%E4%B8%8E%E7%A1%AC%E4%BB%B6/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-03-%E6%95%B0%E5%80%BC%E6%A0%BC%E5%BC%8F%E4%B8%8E%E7%A1%AC%E4%BB%B6/</guid><description/></item><item><title>LLM 量化精读笔记 · 04 量化粒度、校准与离群值</title><link>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-04-%E9%87%8F%E5%8C%96%E7%B2%92%E5%BA%A6%E6%A0%A1%E5%87%86%E4%B8%8E%E7%A6%BB%E7%BE%A4%E5%80%BC/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-04-%E9%87%8F%E5%8C%96%E7%B2%92%E5%BA%A6%E6%A0%A1%E5%87%86%E4%B8%8E%E7%A6%BB%E7%BE%A4%E5%80%BC/</guid><description/></item><item><title>LLM 量化精读笔记 · 05 权重量化 I：RTN 与 GPTQ（含二阶误差补偿推导）</title><link>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-05-%E6%9D%83%E9%87%8D%E9%87%8F%E5%8C%96i-rtn%E4%B8%8Egptq/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-05-%E6%9D%83%E9%87%8D%E9%87%8F%E5%8C%96i-rtn%E4%B8%8Egptq/</guid><description/></item><item><title>LLM 量化精读笔记 · 06 权重量化 II：AWQ、SqueezeLLM、QuIP#</title><link>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-06-%E6%9D%83%E9%87%8D%E9%87%8F%E5%8C%96ii-awq-squeezellm-quip/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-06-%E6%9D%83%E9%87%8D%E9%87%8F%E5%8C%96ii-awq-squeezellm-quip/</guid><description/></item><item><title>LLM 量化精读笔记 · 07 激活量化：LLM.int8() 与 SmoothQuant（W8A8）</title><link>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-07-%E6%BF%80%E6%B4%BB%E9%87%8F%E5%8C%96-llm-int8%E4%B8%8Esmoothquant/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-07-%E6%BF%80%E6%B4%BB%E9%87%8F%E5%8C%96-llm-int8%E4%B8%8Esmoothquant/</guid><description/></item><item><title>LLM 量化精读笔记 · 08 KV Cache 量化：KIVI 与误差累积</title><link>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-08-kv-cache%E9%87%8F%E5%8C%96%E4%B8%8Ekivi/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-08-kv-cache%E9%87%8F%E5%8C%96%E4%B8%8Ekivi/</guid><description/></item><item><title>LLM 量化精读笔记 · 09 QAT 与训练内量化：STE、QLoRA、BitNet b1.58</title><link>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-09-qat%E4%B8%8E%E8%AE%AD%E7%BB%83%E5%86%85%E9%87%8F%E5%8C%96-ste-qlora-bitnet/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-09-qat%E4%B8%8E%E8%AE%AD%E7%BB%83%E5%86%85%E9%87%8F%E5%8C%96-ste-qlora-bitnet/</guid><description/></item><item><title>LLM 量化精读笔记 · 10 质量评估方法论：perplexity、基准与自定义评测</title><link>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-10-%E8%B4%A8%E9%87%8F%E8%AF%84%E4%BC%B0%E6%96%B9%E6%B3%95%E8%AE%BA/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-10-%E8%B4%A8%E9%87%8F%E8%AF%84%E4%BC%B0%E6%96%B9%E6%B3%95%E8%AE%BA/</guid><description/></item><item><title>LLM 量化精读笔记 · 11 系统协同与部署：QServe、FP8 Attention 与工程工具</title><link>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-11-%E7%B3%BB%E7%BB%9F%E5%8D%8F%E5%90%8C%E4%B8%8E%E9%83%A8%E7%BD%B2/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E9%87%8F%E5%8C%96%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-11-%E7%B3%BB%E7%BB%9F%E5%8D%8F%E5%90%8C%E4%B8%8E%E9%83%A8%E7%BD%B2/</guid><description/></item><item><title>LLM 推测解码精读笔记 · 00 总览与学习地图</title><link>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-00-%E6%80%BB%E8%A7%88%E4%B8%8E%E5%AD%A6%E4%B9%A0%E5%9C%B0%E5%9B%BE/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-00-%E6%80%BB%E8%A7%88%E4%B8%8E%E5%AD%A6%E4%B9%A0%E5%9C%B0%E5%9B%BE/</guid><description/></item><item><title>LLM 推测解码精读笔记 · 01 问题形式化与接受率数学</title><link>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-01-%E9%97%AE%E9%A2%98%E5%BD%A2%E5%BC%8F%E5%8C%96%E4%B8%8E%E6%8E%A5%E5%8F%97%E7%8E%87%E6%95%B0%E5%AD%A6/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-01-%E9%97%AE%E9%A2%98%E5%BD%A2%E5%BC%8F%E5%8C%96%E4%B8%8E%E6%8E%A5%E5%8F%97%E7%8E%87%E6%95%B0%E5%AD%A6/</guid><description/></item><item><title>LLM 推测解码精读笔记 · 02 原始推测解码：草稿模型与拒绝采样</title><link>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-02-%E5%8E%9F%E5%A7%8B%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81-%E8%8D%89%E7%A8%BF%E6%A8%A1%E5%9E%8B%E4%B8%8E%E6%8B%92%E7%BB%9D%E9%87%87%E6%A0%B7/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-02-%E5%8E%9F%E5%A7%8B%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81-%E8%8D%89%E7%A8%BF%E6%A8%A1%E5%9E%8B%E4%B8%8E%E6%8B%92%E7%BB%9D%E9%87%87%E6%A0%B7/</guid><description/></item><item><title>LLM 推测解码精读笔记 · 03 Medusa：多头解码</title><link>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-03-medusa-%E5%A4%9A%E5%A4%B4%E8%A7%A3%E7%A0%81/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-03-medusa-%E5%A4%9A%E5%A4%B4%E8%A7%A3%E7%A0%81/</guid><description/></item><item><title>LLM 推测解码精读笔记 · 04 EAGLE：特征空间草稿</title><link>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-04-eagle-%E7%89%B9%E5%BE%81%E7%A9%BA%E9%97%B4%E8%8D%89%E7%A8%BF/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-04-eagle-%E7%89%B9%E5%BE%81%E7%A9%BA%E9%97%B4%E8%8D%89%E7%A8%BF/</guid><description/></item><item><title>LLM 推测解码精读笔记 · 05 n-gram / 检索式与无模型路线</title><link>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-05-n-gram%E6%A3%80%E7%B4%A2%E5%BC%8F%E4%B8%8E%E6%97%A0%E6%A8%A1%E5%9E%8B%E8%B7%AF%E7%BA%BF/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-05-n-gram%E6%A3%80%E7%B4%A2%E5%BC%8F%E4%B8%8E%E6%97%A0%E6%A8%A1%E5%9E%8B%E8%B7%AF%E7%BA%BF/</guid><description/></item><item><title>LLM 推测解码精读笔记 · 06 系统集成与生产验收</title><link>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-06-%E7%B3%BB%E7%BB%9F%E9%9B%86%E6%88%90%E4%B8%8E%E7%94%9F%E4%BA%A7%E9%AA%8C%E6%94%B6/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%8E%A8%E6%B5%8B%E8%A7%A3%E7%A0%81%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-06-%E7%B3%BB%E7%BB%9F%E9%9B%86%E6%88%90%E4%B8%8E%E7%94%9F%E4%BA%A7%E9%AA%8C%E6%94%B6/</guid><description/></item><item><title>LLM 注意力与计算内核精读笔记 · 00 总览与学习地图</title><link>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-00-%E6%80%BB%E8%A7%88%E4%B8%8E%E5%AD%A6%E4%B9%A0%E5%9C%B0%E5%9B%BE/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-00-%E6%80%BB%E8%A7%88%E4%B8%8E%E5%AD%A6%E4%B9%A0%E5%9C%B0%E5%9B%BE/</guid><description/></item><item><title>LLM 注意力与计算内核精读笔记 · 01 注意力机制基础与复杂度分析</title><link>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-01-%E6%B3%A8%E6%84%8F%E5%8A%9B%E6%9C%BA%E5%88%B6%E5%9F%BA%E7%A1%80%E4%B8%8E%E5%A4%8D%E6%9D%82%E5%BA%A6%E5%88%86%E6%9E%90/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-01-%E6%B3%A8%E6%84%8F%E5%8A%9B%E6%9C%BA%E5%88%B6%E5%9F%BA%E7%A1%80%E4%B8%8E%E5%A4%8D%E6%9D%82%E5%BA%A6%E5%88%86%E6%9E%90/</guid><description/></item><item><title>LLM 注意力与计算内核精读笔记 · 02 FlashAttention：IO 感知的精确注意力</title><link>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-02-flashattention-io%E6%84%9F%E7%9F%A5%E7%9A%84%E7%B2%BE%E7%A1%AE%E6%B3%A8%E6%84%8F%E5%8A%9B/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-02-flashattention-io%E6%84%9F%E7%9F%A5%E7%9A%84%E7%B2%BE%E7%A1%AE%E6%B3%A8%E6%84%8F%E5%8A%9B/</guid><description/></item><item><title>LLM 注意力与计算内核精读笔记 · 03 注意力头变体：MQA / GQA / MLA</title><link>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-03-%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%A4%B4%E5%8F%98%E4%BD%93-mqa-gqa-mla/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-03-%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%A4%B4%E5%8F%98%E4%BD%93-mqa-gqa-mla/</guid><description/></item><item><title>LLM 注意力与计算内核精读笔记 · 04 稀疏、滑动窗口与线性注意力</title><link>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-04-%E7%A8%80%E7%96%8F%E6%BB%91%E5%8A%A8%E7%AA%97%E5%8F%A3%E4%B8%8E%E7%BA%BF%E6%80%A7%E6%B3%A8%E6%84%8F%E5%8A%9B/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-04-%E7%A8%80%E7%96%8F%E6%BB%91%E5%8A%A8%E7%AA%97%E5%8F%A3%E4%B8%8E%E7%BA%BF%E6%80%A7%E6%B3%A8%E6%84%8F%E5%8A%9B/</guid><description/></item><item><title>LLM 注意力与计算内核精读笔记 · 05 PagedAttention 与 KV 显存管理</title><link>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-05-pagedattention%E4%B8%8Ekv%E6%98%BE%E5%AD%98%E7%AE%A1%E7%90%86/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-05-pagedattention%E4%B8%8Ekv%E6%98%BE%E5%AD%98%E7%AE%A1%E7%90%86/</guid><description/></item><item><title>LLM 注意力与计算内核精读笔记 · 06 内核优化与算子融合</title><link>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-06-%E5%86%85%E6%A0%B8%E4%BC%98%E5%8C%96%E4%B8%8E%E7%AE%97%E5%AD%90%E8%9E%8D%E5%90%88/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-06-%E5%86%85%E6%A0%B8%E4%BC%98%E5%8C%96%E4%B8%8E%E7%AE%97%E5%AD%90%E8%9E%8D%E5%90%88/</guid><description/></item><item><title>LLM 注意力与计算内核精读笔记 · 07 系统集成与生产验收</title><link>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-07-%E7%B3%BB%E7%BB%9F%E9%9B%86%E6%88%90%E4%B8%8E%E7%94%9F%E4%BA%A7%E9%AA%8C%E6%94%B6/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-07-%E7%B3%BB%E7%BB%9F%E9%9B%86%E6%88%90%E4%B8%8E%E7%94%9F%E4%BA%A7%E9%AA%8C%E6%94%B6/</guid><description/></item><item><title>LLM 注意力与计算内核精读笔记 · 08 前缀缓存与 KV 复用</title><link>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-08-%E5%89%8D%E7%BC%80%E7%BC%93%E5%AD%98%E4%B8%8Ekv%E5%A4%8D%E7%94%A8/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/llm%E6%B3%A8%E6%84%8F%E5%8A%9B%E5%86%85%E6%A0%B8%E7%B2%BE%E8%AF%BB%E7%AC%94%E8%AE%B0-08-%E5%89%8D%E7%BC%80%E7%BC%93%E5%AD%98%E4%B8%8Ekv%E5%A4%8D%E7%94%A8/</guid><description/></item><item><title>笔记</title><link>https://zzszmyf.github.io/notes/</link><pubDate>Mon, 17 Aug 2026 00:00:00 +0800</pubDate><guid>https://zzszmyf.github.io/notes/</guid><description/></item></channel></rss>