<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Networking on Jaehun's Blog</title><link>https://jaehun.me/tags/networking/</link><description>Recent content in Networking on Jaehun's Blog</description><generator>Hugo</generator><language>ko-kr</language><lastBuildDate>Sat, 19 Sep 2026 01:44:51 +0900</lastBuildDate><atom:link href="https://jaehun.me/tags/networking/index.xml" rel="self" type="application/rss+xml"/><item><title>CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving</title><link>https://jaehun.me/posts/cachegen-kv-cache-compression-and-streaming-for-fast-large-language-model-serving/</link><pubDate>Tue, 10 Dec 2024 00:00:00 +0900</pubDate><guid>https://jaehun.me/posts/cachegen-kv-cache-compression-and-streaming-for-fast-large-language-model-serving/</guid><description>&lt;p&gt;&lt;a&#10; href="https://arxiv.org/abs/2310.07240"target="_blank"&#10; class="inline-flex items-center gap-1"&#10; &gt;논문 링크&lt;svg class="h-3 w-3 flex-shrink-0" id="external-link" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"&gt;&lt;path fill="none" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M15 3h6v6m-11 5L21 3m-3 10v6a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V8a2 2 0 0 1 2-2h6"/&gt;&lt;/svg&gt;&#10; &lt;/a&gt;&lt;/p&gt;&#10;&lt;h2 id="강점과-독창성-핵심-알고리즘-그리고-한계"&gt;강점과 독창성, 핵심 알고리즘, 그리고 한계&lt;a href="#%ea%b0%95%ec%a0%90%ea%b3%bc-%eb%8f%85%ec%b0%bd%ec%84%b1-%ed%95%b5%ec%8b%ac-%ec%95%8c%ea%b3%a0%eb%a6%ac%ec%a6%98-%ea%b7%b8%eb%a6%ac%ea%b3%a0-%ed%95%9c%ea%b3%84" class="heading-anchor" aria-label="이 섹션에 대한 링크"&gt;&lt;/a&gt;&lt;/h2&gt;&#10; &lt;blockquote&#10; class="border-primary bg-muted/30 hover:bg-muted/40 my-6 rounded-r-lg border-l-4 py-4 pr-4 pl-6 italic transition-all duration-200 ease-out hover:translate-x-1"&#10; &gt;&#10; &lt;div class="prose prose-sm max-w-none"&gt;&#10; &lt;p&gt;물어본 것: 이 논문을 아주 자세하게 읽고 논문의 강점과 독창적인 지점을 설명해주고 핵심 알고리즘을 예시 입력을 들어서 전체적인 과정을 설명해줘 추가적으로 논문의 한계점에 대해서도 알려줘&lt;/p&gt;</description></item><item><title>Teola Towards End-to-End Optimization of LLM-based Applications</title><link>https://jaehun.me/posts/teola-towards-end-to-end-optimization-of-llm-based-applications/</link><pubDate>Fri, 01 Nov 2024 00:00:00 +0900</pubDate><guid>https://jaehun.me/posts/teola-towards-end-to-end-optimization-of-llm-based-applications/</guid><description>&lt;p&gt;논문 : &lt;a&#10; href="https://arxiv.org/abs/2407.00326"target="_blank"&#10; class="inline-flex items-center gap-1"&#10; &gt;https://arxiv.org/abs/2407.00326&lt;svg class="h-3 w-3 flex-shrink-0" id="external-link" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"&gt;&lt;path fill="none" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M15 3h6v6m-11 5L21 3m-3 10v6a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V8a2 2 0 0 1 2-2h6"/&gt;&lt;/svg&gt;&#10; &lt;/a&gt;&lt;/p&gt;&#10;&lt;p&gt;개인의견 : 결국 프리미티브라고 하는 작은 단위로 나눈다는 개념을 도입하는거 같고 이게 LLM이 아닌 경우도 고려해서 한번에 serving을 한다는것이라고 이해를 했는데 vllm의 continuous batching + sequence를 unit한 단위로 나누어서 스케줄링하는거에 대비 얼마만큼의 이득이 있을까 궁금하긴하다.&lt;/p&gt;</description></item></channel></rss>