Files
FastDeploy/features/global_cache_pooling/index.html
T

3231 lines
60 KiB
HTML

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="alternate" href="./" hreflang="en">
<link rel="alternate" href="../../zh/features/global_cache_pooling/" hreflang="zh">
<link rel="icon" href="../../assets/images/favicon.ico">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.6">
<title>Global cache pooling - FastDeploy: Large Language Model Deployment</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.484c7ddc.min.css">
<link rel="stylesheet" href="../../assets/stylesheets/palette.ab4e12ef.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#global-cache-pooling" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../.." title="FastDeploy: Large Language Model Deployment" class="md-header__button md-logo" aria-label="FastDeploy: Large Language Model Deployment" data-md-component="logo">
<img src="../../assets/images/logo.jpg" alt="logo">
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
FastDeploy: Large Language Model Deployment
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Global cache pooling
</span>
</div>
</div>
</div>
<form class="md-header__option" data-md-component="palette">
<input class="md-option" data-md-color-media="(prefers-color-scheme: light)" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo" aria-label="Switch to dark mode" type="radio" name="__palette" id="__palette_0">
<label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_1" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a4 4 0 0 0-4 4 4 4 0 0 0 4 4 4 4 0 0 0 4-4 4 4 0 0 0-4-4m0 10a6 6 0 0 1-6-6 6 6 0 0 1 6-6 6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
<input class="md-option" data-md-color-media="(prefers-color-scheme: dark)" data-md-color-scheme="slate" data-md-color-primary="black" data-md-color-accent="indigo" aria-label="Switch to system preference" type="radio" name="__palette" id="__palette_1">
<label class="md-header__button md-icon" title="Switch to system preference" for="__palette_0" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12s-1.44-4.5-3.5-5.45C10.26 6.2 11.11 6 12 6a6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
</form>
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
<div class="md-header__option">
<div class="md-select">
<button class="md-header__button md-icon" aria-label="Select language">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m12.87 15.07-2.54-2.51.03-.03A17.5 17.5 0 0 0 14.07 6H17V4h-7V2H8v2H1v2h11.17C11.5 7.92 10.44 9.75 9 11.35 8.07 10.32 7.3 9.19 6.69 8h-2c.73 1.63 1.73 3.17 2.98 4.56l-5.09 5.02L4 19l5-5 3.11 3.11zM18.5 10h-2L12 22h2l1.12-3h4.75L21 22h2zm-2.62 7 1.62-4.33L19.12 17z"/></svg>
</button>
<div class="md-select__inner">
<ul class="md-select__list">
<li class="md-select__item">
<a href="./" hreflang="en" class="md-select__link">
English
</a>
</li>
<li class="md-select__item">
<a href="../../zh/features/global_cache_pooling/" hreflang="zh" class="md-select__link">
简体中文
</a>
</li>
</ul>
</div>
</div>
</div>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
<div class="md-header__source">
<a href="https://github.com/PaddlePaddle/FastDeploy" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M439.6 236.1 244 40.5c-5.4-5.5-12.8-8.5-20.4-8.5s-15 3-20.4 8.4L162.5 81l51.5 51.5c27.1-9.1 52.7 16.8 43.4 43.7l49.7 49.7c34.2-11.8 61.2 31 35.5 56.7-26.5 26.5-70.2-2.9-56-37.3L240.3 199v121.9c25.3 12.5 22.3 41.8 9.1 55-6.4 6.4-15.2 10.1-24.3 10.1s-17.8-3.6-24.3-10.1c-17.6-17.6-11.1-46.9 11.2-56v-123c-20.8-8.5-24.6-30.7-18.6-45L142.6 101 8.5 235.1C3 240.6 0 247.9 0 255.5s3 15 8.5 20.4l195.6 195.7c5.4 5.4 12.7 8.4 20.4 8.4s15-3 20.4-8.4l194.7-194.7c5.4-5.4 8.4-12.8 8.4-20.4s-3-15-8.4-20.4"/></svg>
</div>
<div class="md-source__repository">
FastDeploy
</div>
</a>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../.." title="FastDeploy: Large Language Model Deployment" class="md-nav__button md-logo" aria-label="FastDeploy: Large Language Model Deployment" data-md-component="logo">
<img src="../../assets/images/logo.jpg" alt="logo">
</a>
FastDeploy: Large Language Model Deployment
</label>
<div class="md-nav__source">
<a href="https://github.com/PaddlePaddle/FastDeploy" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M439.6 236.1 244 40.5c-5.4-5.5-12.8-8.5-20.4-8.5s-15 3-20.4 8.4L162.5 81l51.5 51.5c27.1-9.1 52.7 16.8 43.4 43.7l49.7 49.7c34.2-11.8 61.2 31 35.5 56.7-26.5 26.5-70.2-2.9-56-37.3L240.3 199v121.9c25.3 12.5 22.3 41.8 9.1 55-6.4 6.4-15.2 10.1-24.3 10.1s-17.8-3.6-24.3-10.1c-17.6-17.6-11.1-46.9 11.2-56v-123c-20.8-8.5-24.6-30.7-18.6-45L142.6 101 8.5 235.1C3 240.6 0 247.9 0 255.5s3 15 8.5 20.4l195.6 195.7c5.4 5.4 12.7 8.4 20.4 8.4s15-3 20.4-8.4l194.7-194.7c5.4-5.4 8.4-12.8 8.4-20.4s-3-15-8.4-20.4"/></svg>
</div>
<div class="md-source__repository">
FastDeploy
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../.." class="md-nav__link">
<span class="md-ellipsis">
FastDeploy
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2" >
<label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
<span class="md-ellipsis">
Quick Start
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
Quick Start
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2_1" >
<label class="md-nav__link" for="__nav_2_1" id="__nav_2_1_label" tabindex="0">
<span class="md-ellipsis">
Installation
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_2_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2_1">
<span class="md-nav__icon md-icon"></span>
Installation
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../get_started/installation/nvidia_gpu/" class="md-nav__link">
<span class="md-ellipsis">
Nvidia GPU
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../get_started/installation/kunlunxin_xpu/" class="md-nav__link">
<span class="md-ellipsis">
KunlunXin XPU
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../get_started/installation/intel_gaudi/" class="md-nav__link">
<span class="md-ellipsis">
Intel Gaudi
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../get_started/installation/hygon_dcu/" class="md-nav__link">
<span class="md-ellipsis">
HYGON DCU
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../get_started/installation/Enflame_gcu/" class="md-nav__link">
<span class="md-ellipsis">
Enflame S60
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../get_started/installation/iluvatar_gpu/" class="md-nav__link">
<span class="md-ellipsis">
Iluvatar CoreX
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../get_started/installation/metax_gpu/" class="md-nav__link">
<span class="md-ellipsis">
Metax C550
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../get_started/quick_start/" class="md-nav__link">
<span class="md-ellipsis">
Quick Deployment For ERNIE-4.5-0.3B
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../get_started/quick_start_vl/" class="md-nav__link">
<span class="md-ellipsis">
Quick Deployment for ERNIE-4.5-VL-28B-A3B
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../get_started/ernie-4.5/" class="md-nav__link">
<span class="md-ellipsis">
ERNIE-4.5-300B-A47B
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../get_started/ernie-4.5-vl/" class="md-nav__link">
<span class="md-ellipsis">
ERNIE-4.5-VL-424B-A47B
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../get_started/quick_start_qwen/" class="md-nav__link">
<span class="md-ellipsis">
Quick Deployment For QWEN
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../get_started/quick_start_qwen25_vl/" class="md-nav__link">
<span class="md-ellipsis">
Quick Deployment For QWEN2.5-VL
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3" >
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0">
<span class="md-ellipsis">
Online Serving
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Online Serving
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../online_serving/" class="md-nav__link">
<span class="md-ellipsis">
OpenAI-Compatible API Server
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../online_serving/metrics/" class="md-nav__link">
<span class="md-ellipsis">
Monitor Metrics
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../online_serving/scheduler/" class="md-nav__link">
<span class="md-ellipsis">
Scheduler
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../online_serving/graceful_shutdown_service/" class="md-nav__link">
<span class="md-ellipsis">
Graceful Shutdown
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../online_serving/router/" class="md-nav__link">
<span class="md-ellipsis">
Load-Balancing Scheduling Router
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../offline_inference/" class="md-nav__link">
<span class="md-ellipsis">
Offline Inference
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" >
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
<span class="md-ellipsis">
Best Practices
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
Best Practices
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../best_practices/ERNIE-4.5-0.3B-Paddle/" class="md-nav__link">
<span class="md-ellipsis">
ERNIE-4.5-0.3B
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../best_practices/ERNIE-4.5-21B-A3B-Paddle/" class="md-nav__link">
<span class="md-ellipsis">
ERNIE-4.5-21B-A3B
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../best_practices/ERNIE-4.5-300B-A47B-Paddle/" class="md-nav__link">
<span class="md-ellipsis">
ERNIE-4.5-300B-A47B
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../best_practices/ERNIE-4.5-21B-A3B-Thinking/" class="md-nav__link">
<span class="md-ellipsis">
ERNIE-4.5-21B-A3B-Thinking
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../best_practices/ERNIE-4.5-VL-28B-A3B-Paddle/" class="md-nav__link">
<span class="md-ellipsis">
ERNIE-4.5-VL-28B-A3B
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../best_practices/ERNIE-4.5-VL-424B-A47B-Paddle/" class="md-nav__link">
<span class="md-ellipsis">
ERNIE-4.5-VL-424B-A47B
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../best_practices/PaddleOCR-VL-0.9B/" class="md-nav__link">
<span class="md-ellipsis">
PaddleOCR-VL-0.9B
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../best_practices/FAQ/" class="md-nav__link">
<span class="md-ellipsis">
FAQ
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6" >
<label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
<span class="md-ellipsis">
Quantization
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_6">
<span class="md-nav__icon md-icon"></span>
Quantization
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../quantization/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../quantization/online_quantization/" class="md-nav__link">
<span class="md-ellipsis">
Online Quantization
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../quantization/wint2/" class="md-nav__link">
<span class="md-ellipsis">
WINT2 Quantization
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" >
<label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
<span class="md-ellipsis">
Features
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7">
<span class="md-nav__icon md-icon"></span>
Features
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../prefix_caching/" class="md-nav__link">
<span class="md-ellipsis">
Prefix Caching
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../disaggregated/" class="md-nav__link">
<span class="md-ellipsis">
Disaggregation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../chunked_prefill/" class="md-nav__link">
<span class="md-ellipsis">
Chunked Prefill
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../load_balance/" class="md-nav__link">
<span class="md-ellipsis">
Load Balance
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../speculative_decoding/" class="md-nav__link">
<span class="md-ellipsis">
Speculative Decoding
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../structured_outputs/" class="md-nav__link">
<span class="md-ellipsis">
Structured Outputs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../reasoning_output/" class="md-nav__link">
<span class="md-ellipsis">
Reasoning Output
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../thinking_budget/" class="md-nav__link">
<span class="md-ellipsis">
Thinking Budget
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../early_stop/" class="md-nav__link">
<span class="md-ellipsis">
Early Stop
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../plugins/" class="md-nav__link">
<span class="md-ellipsis">
Plugins
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../paddleformers_backend/" class="md-nav__link">
<span class="md-ellipsis">
PaddleFormers Backend
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../sampling/" class="md-nav__link">
<span class="md-ellipsis">
Sampling
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../multi-node_deployment/" class="md-nav__link">
<span class="md-ellipsis">
MultiNode Deployment
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../graph_optimization/" class="md-nav__link">
<span class="md-ellipsis">
Graph Optimization
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../data_parallel_service/" class="md-nav__link">
<span class="md-ellipsis">
Data Parallelism
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../plas_attention/" class="md-nav__link">
<span class="md-ellipsis">
PLAS
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../supported_models/" class="md-nav__link">
<span class="md-ellipsis">
Supported Models
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../benchmark/" class="md-nav__link">
<span class="md-ellipsis">
Benchmark
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_10" >
<label class="md-nav__link" for="__nav_10" id="__nav_10_label" tabindex="0">
<span class="md-ellipsis">
Usage
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_10_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10">
<span class="md-nav__icon md-icon"></span>
Usage
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../usage/log/" class="md-nav__link">
<span class="md-ellipsis">
Log Description
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../usage/code_overview/" class="md-nav__link">
<span class="md-ellipsis">
Code Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../usage/environment_variables/" class="md-nav__link">
<span class="md-ellipsis">
Environment Variables
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_11" >
<label class="md-nav__link" for="__nav_11" id="__nav_11_label" tabindex="0">
<span class="md-ellipsis">
CLI
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_11_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_11">
<span class="md-nav__icon md-icon"></span>
CLI
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../cli/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cli/chat/" class="md-nav__link">
<span class="md-ellipsis">
Chat
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cli/complete/" class="md-nav__link">
<span class="md-ellipsis">
Complete
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cli/serve/" class="md-nav__link">
<span class="md-ellipsis">
Server
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cli/collect-env/" class="md-nav__link">
<span class="md-ellipsis">
Collect Env
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cli/bench/" class="md-nav__link">
<span class="md-ellipsis">
Bench
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cli/run-batch/" class="md-nav__link">
<span class="md-ellipsis">
Run Batch
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cli/tokenizer/" class="md-nav__link">
<span class="md-ellipsis">
Tokenizer
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_12" >
<label class="md-nav__link" for="__nav_12" id="__nav_12_label" tabindex="0">
<span class="md-ellipsis">
Observability
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_12_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_12">
<span class="md-nav__icon md-icon"></span>
Observability
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../observability/trace/" class="md-nav__link">
<span class="md-ellipsis">
Trace
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#overview" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
<nav class="md-nav" aria-label="Overview">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#what-is-global-cache-pooling" class="md-nav__link">
<span class="md-ellipsis">
What is Global Cache Pooling?
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#architecture" class="md-nav__link">
<span class="md-ellipsis">
Architecture
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#example-scripts" class="md-nav__link">
<span class="md-ellipsis">
Example Scripts
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#prerequisites" class="md-nav__link">
<span class="md-ellipsis">
Prerequisites
</span>
</a>
<nav class="md-nav" aria-label="Prerequisites">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#hardware-requirements" class="md-nav__link">
<span class="md-ellipsis">
Hardware Requirements
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#software-requirements" class="md-nav__link">
<span class="md-ellipsis">
Software Requirements
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#installation" class="md-nav__link">
<span class="md-ellipsis">
Installation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#configuration" class="md-nav__link">
<span class="md-ellipsis">
Configuration
</span>
</a>
<nav class="md-nav" aria-label="Configuration">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#mooncake-configuration-file" class="md-nav__link">
<span class="md-ellipsis">
Mooncake Configuration File
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#environment-variables" class="md-nav__link">
<span class="md-ellipsis">
Environment Variables
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#usage-scenarios" class="md-nav__link">
<span class="md-ellipsis">
Usage Scenarios
</span>
</a>
<nav class="md-nav" aria-label="Usage Scenarios">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#scenario-1-multi-instance-cache-sharing" class="md-nav__link">
<span class="md-ellipsis">
Scenario 1: Multi-Instance Cache Sharing
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#scenario-2-pd-disaggregation-with-global-cache" class="md-nav__link">
<span class="md-ellipsis">
Scenario 2: PD Disaggregation with Global Cache
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#fastdeploy-parameters-for-mooncake" class="md-nav__link">
<span class="md-ellipsis">
FastDeploy Parameters for Mooncake
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#verification" class="md-nav__link">
<span class="md-ellipsis">
Verification
</span>
</a>
<nav class="md-nav" aria-label="Verification">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#check-cache-hit" class="md-nav__link">
<span class="md-ellipsis">
Check Cache Hit
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#monitor-mooncake-master" class="md-nav__link">
<span class="md-ellipsis">
Monitor Mooncake Master
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#troubleshooting" class="md-nav__link">
<span class="md-ellipsis">
Troubleshooting
</span>
</a>
<nav class="md-nav" aria-label="Troubleshooting">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#common-issues" class="md-nav__link">
<span class="md-ellipsis">
Common Issues
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#debug-mode" class="md-nav__link">
<span class="md-ellipsis">
Debug Mode
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#more-resources" class="md-nav__link">
<span class="md-ellipsis">
More Resources
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<p><a href="../zh/features/global_cache_pooling.md">中文文档</a> | English</p>
<h1 id="global-cache-pooling">Global Cache Pooling</h1>
<p>This document describes how to use MooncakeStore as the KV Cache storage backend for FastDeploy, enabling <strong>Global Cache Pooling</strong> across multiple inference instances.</p>
<h2 id="overview">Overview</h2>
<h3 id="what-is-global-cache-pooling">What is Global Cache Pooling?</h3>
<p>Global Cache Pooling allows multiple FastDeploy instances to share KV Cache through a distributed storage layer. This enables:</p>
<ul>
<li><strong>Cross-instance cache reuse</strong>: KV Cache computed by one instance can be reused by another</li>
<li><strong>PD Disaggregation optimization</strong>: Prefill and Decode instances can share cache seamlessly</li>
<li><strong>Reduced computation</strong>: Avoid redundant prefix computation across requests</li>
</ul>
<h3 id="architecture">Architecture</h3>
<pre><code>┌─────────────────────────────────────────────────────────────────┐
│ Mooncake Master Server │
│ (Metadata &amp; Coordination Service) │
└────────────────────────────┬────────────────────────────────────┘
┌───────────────────┼───────────────────┐
│ │ │
▼ ▼ ▼
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ FastDeploy │ │ FastDeploy │ │ FastDeploy │
│ Instance P │ │ Instance D │ │ Instance X │
│ (Prefill) │ │ (Decode) │ │ (Standalone) │
└────────┬────────┘ └────────┬────────┘ └────────┬────────┘
│ │ │
└───────────────────┼───────────────────┘
┌────────▼────────┐
│ MooncakeStore │
│ (Shared KV │
│ Cache Pool) │
└─────────────────┘
</code></pre>
<h2 id="example-scripts">Example Scripts</h2>
<p>Ready-to-use example scripts are available in <a href="../../../examples/cache_storage/">examples/cache_storage/</a>.</p>
<table>
<thead>
<tr>
<th>Script</th>
<th>Scenario</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>run.sh</code></td>
<td>Multi-Instance</td>
<td>Two standalone instances sharing cache</td>
</tr>
<tr>
<td><code>run_03b_pd_storage.sh</code></td>
<td>PD Disaggregation</td>
<td>P+D instances with global cache pooling</td>
</tr>
</tbody>
</table>
<h2 id="prerequisites">Prerequisites</h2>
<h3 id="hardware-requirements">Hardware Requirements</h3>
<ul>
<li>NVIDIA GPU with CUDA support</li>
<li>RDMA network (recommended for production) or TCP</li>
</ul>
<h3 id="software-requirements">Software Requirements</h3>
<ul>
<li>Python 3.8+</li>
<li>CUDA 11.8+</li>
<li>FastDeploy (see installation below)</li>
</ul>
<h2 id="installation">Installation</h2>
<p>Refer to <a href="https://paddlepaddle.github.io/FastDeploy/get_started/installation/nvidia_gpu/">NVIDIA CUDA GPU Installation</a> for FastDeploy installation.</p>
<pre><code class="language-bash"># Option 1: Install from PyPI
pip install fastdeploy-gpu
# Option 2: Build from source
bash build.sh
pip install ./dist/fastdeploy*.whl
</code></pre>
<p>MooncakeStore is automatically installed when you install FastDeploy.</p>
<h2 id="configuration">Configuration</h2>
<p>We support two ways to configure MooncakeStore: via configuration file <code>mooncake_config.json</code> or via environment variables.</p>
<h3 id="mooncake-configuration-file">Mooncake Configuration File</h3>
<p>Create a <code>mooncake_config.json</code> file:</p>
<pre><code class="language-json">{
&quot;metadata_server&quot;: &quot;http://0.0.0.0:15002/metadata&quot;,
&quot;master_server_addr&quot;: &quot;0.0.0.0:15001&quot;,
&quot;global_segment_size&quot;: 1000000000,
&quot;local_buffer_size&quot;: 1048576,
&quot;protocol&quot;: &quot;rdma&quot;,
&quot;rdma_devices&quot;: &quot;&quot;
}
</code></pre>
<p>Set the <code>MOONCAKE_CONFIG_PATH</code> environment variable to enable the configuration:</p>
<pre><code class="language-bash">export MOONCAKE_CONFIG_PATH=path/to/mooncake_config.json
</code></pre>
<p>Configuration parameters:</p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>metadata_server</code></td>
<td>HTTP metadata server URL</td>
<td>Required</td>
</tr>
<tr>
<td><code>master_server_addr</code></td>
<td>Master server address</td>
<td>Required</td>
</tr>
<tr>
<td><code>global_segment_size</code></td>
<td>Memory space each TP process shares to global shared memory (bytes)</td>
<td>1GB</td>
</tr>
<tr>
<td><code>local_buffer_size</code></td>
<td>Local buffer size for data transfer (bytes)</td>
<td>128MB</td>
</tr>
<tr>
<td><code>protocol</code></td>
<td>Transfer protocol: <code>rdma</code> or <code>tcp</code></td>
<td><code>rdma</code></td>
</tr>
<tr>
<td><code>rdma_devices</code></td>
<td>RDMA device names (comma-separated)</td>
<td>Auto-detect</td>
</tr>
</tbody>
</table>
<h3 id="environment-variables">Environment Variables</h3>
<p>Mooncake can also be configured via environment variables:</p>
<table>
<thead>
<tr>
<th>Variable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>MOONCAKE_MASTER_SERVER_ADDR</code></td>
<td>Master server address (e.g., <code>10.0.0.1:15001</code>)</td>
</tr>
<tr>
<td><code>MOONCAKE_METADATA_SERVER</code></td>
<td>Metadata server URL</td>
</tr>
<tr>
<td><code>MOONCAKE_GLOBAL_SEGMENT_SIZE</code></td>
<td>Memory space each TP process shares to global shared memory (bytes)</td>
</tr>
<tr>
<td><code>MOONCAKE_LOCAL_BUFFER_SIZE</code></td>
<td>Local buffer size (bytes)</td>
</tr>
<tr>
<td><code>MOONCAKE_PROTOCOL</code></td>
<td>Transfer protocol (<code>rdma</code> or <code>tcp</code>)</td>
</tr>
<tr>
<td><code>MOONCAKE_RDMA_DEVICES</code></td>
<td>RDMA device names</td>
</tr>
</tbody>
</table>
<h2 id="usage-scenarios">Usage Scenarios</h2>
<h3 id="scenario-1-multi-instance-cache-sharing">Scenario 1: Multi-Instance Cache Sharing</h3>
<p>Run multiple FastDeploy instances sharing a global KV Cache pool.</p>
<p><strong>Step 1: Start Mooncake Master</strong></p>
<pre><code class="language-bash">mooncake_master \
--port=15001 \
--enable_http_metadata_server=true \
--http_metadata_server_host=0.0.0.0 \
--http_metadata_server_port=15002 \
--metrics_port=15003
</code></pre>
<p><strong>Step 2: Start FastDeploy Instances</strong></p>
<p>Instance 0:</p>
<pre><code class="language-bash">export MOONCAKE_CONFIG_PATH=&quot;./mooncake_config.json&quot;
export CUDA_VISIBLE_DEVICES=0
python -m fastdeploy.entrypoints.openai.api_server \
--model ${MODEL_NAME} \
--port 52700 \
--max-model-len 32768 \
--max-num-seqs 32 \
--kvcache-storage-backend mooncake
</code></pre>
<p>Instance 1:</p>
<pre><code class="language-bash">export MOONCAKE_CONFIG_PATH=&quot;./mooncake_config.json&quot;
export CUDA_VISIBLE_DEVICES=1
python -m fastdeploy.entrypoints.openai.api_server \
--model ${MODEL_NAME} \
--port 52800 \
--max-model-len 32768 \
--max-num-seqs 32 \
--kvcache-storage-backend mooncake
</code></pre>
<p><strong>Step 3: Test Cache Reuse</strong></p>
<p>Send the same prompt to both instances. The second instance should reuse the KV Cache computed by the first instance.</p>
<pre><code class="language-bash"># Request to Instance 0
curl -X POST &quot;http://0.0.0.0:52700/v1/chat/completions&quot; \
-H &quot;Content-Type: application/json&quot; \
-d '{&quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Hello, world!&quot;}], &quot;max_tokens&quot;: 50}'
# Request to Instance 1 (should hit cached KV)
curl -X POST &quot;http://0.0.0.0:52800/v1/chat/completions&quot; \
-H &quot;Content-Type: application/json&quot; \
-d '{&quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Hello, world!&quot;}], &quot;max_tokens&quot;: 50}'
</code></pre>
<h3 id="scenario-2-pd-disaggregation-with-global-cache">Scenario 2: PD Disaggregation with Global Cache</h3>
<p>This scenario combines <strong>PD Disaggregation</strong> with <strong>Global Cache Pooling</strong>, enabling:</p>
<ul>
<li>Prefill instances to read Decode instances' output cache</li>
<li>Optimal multi-turn conversation performance</li>
</ul>
<p><strong>Architecture:</strong></p>
<pre><code> ┌──────────────────────────────────────────┐
│ Router │
│ (Load Balancer) │
└─────────────────┬────────────────────────┘
┌───────────────┴───────────────┐
│ │
▼ ▼
┌─────────────┐ ┌─────────────┐
│ Prefill │ │ Decode │
│ Instance │◄───────────────►│ Instance │
│ │ KV Transfer │ │
└──────┬──────┘ └──────┬──────┘
│ │
└───────────────┬───────────────┘
┌────────▼────────┐
│ MooncakeStore │
│ (Global Cache) │
└─────────────────┘
</code></pre>
<p><strong>Step 1: Start Mooncake Master</strong></p>
<pre><code class="language-bash">mooncake_master \
--port=15001 \
--enable_http_metadata_server=true \
--http_metadata_server_host=0.0.0.0 \
--http_metadata_server_port=15002
</code></pre>
<p><strong>Step 2: Start Router</strong></p>
<pre><code class="language-bash">python -m fastdeploy.router.launch \
--port 52700 \
--splitwise
</code></pre>
<p><strong>Step 3: Start Prefill Instance</strong></p>
<pre><code class="language-bash">export MOONCAKE_MASTER_SERVER_ADDR=&quot;127.0.0.1:15001&quot;
export MOONCAKE_METADATA_SERVER=&quot;http://127.0.0.1:15002/metadata&quot;
export MOONCAKE_PROTOCOL=&quot;rdma&quot;
export CUDA_VISIBLE_DEVICES=0
python -m fastdeploy.entrypoints.openai.api_server \
--model ${MODEL_NAME} \
--port 52400 \
--max-model-len 32768 \
--max-num-seqs 32 \
--splitwise-role prefill \
--cache-transfer-protocol rdma \
--router &quot;0.0.0.0:52700&quot; \
--kvcache-storage-backend mooncake
</code></pre>
<p><strong>Step 4: Start Decode Instance</strong></p>
<pre><code class="language-bash">export MOONCAKE_MASTER_SERVER_ADDR=&quot;127.0.0.1:15001&quot;
export MOONCAKE_METADATA_SERVER=&quot;http://127.0.0.1:15002/metadata&quot;
export MOONCAKE_PROTOCOL=&quot;rdma&quot;
export CUDA_VISIBLE_DEVICES=1
python -m fastdeploy.entrypoints.openai.api_server \
--model ${MODEL_NAME} \
--port 52500 \
--max-model-len 32768 \
--max-num-seqs 32 \
--splitwise-role decode \
--cache-transfer-protocol rdma \
--router &quot;0.0.0.0:52700&quot; \
--enable-output-caching \
--kvcache-storage-backend mooncake
</code></pre>
<p><strong>Step 5: Send Requests via Router</strong></p>
<pre><code class="language-bash">curl -X POST &quot;http://0.0.0.0:52700/v1/chat/completions&quot; \
-H &quot;Content-Type: application/json&quot; \
-d '{&quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Hello!&quot;}], &quot;max_tokens&quot;: 50}'
</code></pre>
<h2 id="fastdeploy-parameters-for-mooncake">FastDeploy Parameters for Mooncake</h2>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>--kvcache-storage-backend mooncake</code></td>
<td>Enable Mooncake as KV Cache storage backend</td>
</tr>
<tr>
<td><code>--enable-output-caching</code></td>
<td>Enable output token caching (Decode instance recommended)</td>
</tr>
<tr>
<td><code>--cache-transfer-protocol rdma</code></td>
<td>Use RDMA for KV transfer between P and D</td>
</tr>
<tr>
<td><code>--splitwise-role prefill/decode</code></td>
<td>Set instance role in PD disaggregation</td>
</tr>
<tr>
<td><code>--router</code></td>
<td>Router address for PD disaggregation</td>
</tr>
</tbody>
</table>
<h2 id="verification">Verification</h2>
<h3 id="check-cache-hit">Check Cache Hit</h3>
<p>To verify cache hit in logs:</p>
<pre><code class="language-bash"># For multi-instance scenario
grep -E &quot;storage_cache_token_num&quot; log_*/api_server.log
# For PD disaggregation scenario
grep -E &quot;storage_cache_token_num&quot; log_prefill/api_server.log
</code></pre>
<p>If <code>storage_cache_token_num &gt; 0</code>, the instance successfully read cached KV blocks from the global pool.</p>
<h3 id="monitor-mooncake-master">Monitor Mooncake Master</h3>
<pre><code class="language-bash"># Check master status
curl http://localhost:15002/metadata
# Check metrics (if metrics_port is configured)
curl http://localhost:15003/metrics
</code></pre>
<h2 id="troubleshooting">Troubleshooting</h2>
<h3 id="common-issues">Common Issues</h3>
<p><strong>1. Port Already in Use</strong></p>
<pre><code class="language-bash"># Check port usage
ss -ltn | grep 15001
# Kill existing process
kill -9 $(lsof -t -i:15001)
</code></pre>
<p><strong>2. RDMA Connection Failed</strong></p>
<ul>
<li>Verify RDMA devices: <code>ibv_devices</code></li>
<li>Check RDMA network: <code>ibv_devinfo</code></li>
<li>Fallback to TCP: Set <code>MOONCAKE_PROTOCOL=tcp</code></li>
</ul>
<p><strong>3. Cache Not Being Shared</strong></p>
<ul>
<li>Verify all instances connect to the same Mooncake master</li>
<li>Check metadata server URL is consistent</li>
<li>Verify <code>global_segment_size</code> is large enough</li>
</ul>
<p><strong>4. Permission Denied on /dev/shm</strong></p>
<pre><code class="language-bash"># Clean up stale shared memory files
find /dev/shm -type f -print0 | xargs -0 rm -f
</code></pre>
<h3 id="debug-mode">Debug Mode</h3>
<p>Enable debug logging:</p>
<pre><code class="language-bash">export FD_DEBUG=1
</code></pre>
<h2 id="more-resources">More Resources</h2>
<ul>
<li><a href="https://github.com/kvcache-ai/Mooncake">Mooncake Official Documentation</a></li>
<li><a href="https://github.com/kvcache-ai/Mooncake/blob/main/docs/source/troubleshooting/troubleshooting.md">Mooncake Troubleshooting Guide</a></li>
<li><a href="https://paddlepaddle.github.io/FastDeploy/">FastDeploy Documentation</a></li>
</ul>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
<div class="md-copyright__highlight">
Copyright &copy; 2025 Maintained by FastDeploy
</div>
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"annotate": null, "base": "../..", "features": [], "search": "../../assets/javascripts/workers/search.2c215733.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script src="../../assets/javascripts/bundle.79ae519e.min.js"></script>
</body>
</html>