Files
FastDeploy/zh/quantization/index.html

1941 lines
38 KiB
HTML
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!doctype html>
<html lang="zh" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="prev" href="../best_practices/FAQ/">
<link rel="next" href="online_quantization/">
<link rel="icon" href="../../assets/images/favicon.ico">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.20">
<title>概述 - 飞桨大语言模型推理部署工具包</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.e53b48f4.min.css">
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.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="#_1" class="md-skip">
跳转至
</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="页眉">
<a href="../" title="飞桨大语言模型推理部署工具包" class="md-header__button md-logo" aria-label="飞桨大语言模型推理部署工具包" 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">
飞桨大语言模型推理部署工具包
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
概述
</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="选择当前语言">
<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="../../quantization/" hreflang="en" class="md-select__link">
English
</a>
</li>
<li class="md-select__item">
<a href="./" 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="搜索" placeholder="搜索" 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="查找">
<button type="reset" class="md-search__icon md-icon" title="清空当前内容" aria-label="清空当前内容" 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">
正在初始化搜索引擎
</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="前往仓库" 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 7.0.0 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="导航栏" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../" title="飞桨大语言模型推理部署工具包" class="md-nav__button md-logo" aria-label="飞桨大语言模型推理部署工具包" data-md-component="logo">
<img src="../../assets/images/logo.jpg" alt="logo">
</a>
飞桨大语言模型推理部署工具包
</label>
<div class="md-nav__source">
<a href="https://github.com/PaddlePaddle/FastDeploy" title="前往仓库" 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 7.0.0 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">
快速入门
</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>
快速入门
</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">
安装
</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>
安装
</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">
英伟达 GPU
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../get_started/installation/kunlunxin_xpu/" class="md-nav__link">
<span class="md-ellipsis">
昆仑芯 XPU
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../get_started/installation/hygon_dcu/" class="md-nav__link">
<span class="md-ellipsis">
海光 DCU
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../get_started/installation/Enflame_gcu/" class="md-nav__link">
<span class="md-ellipsis">
燧原 S60
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../get_started/installation/iluvatar_gpu/" class="md-nav__link">
<span class="md-ellipsis">
天数 CoreX
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../get_started/installation/metax_gpu/" class="md-nav__link">
<span class="md-ellipsis">
沐曦 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">
ERNIE-4.5-0.3B快速部署
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../get_started/quick_start_vl/" class="md-nav__link">
<span class="md-ellipsis">
ERNIE-4.5-VL-28B-A3B快速部署
</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">
Qwen3-0.6b快速部署
</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">
在线服务
</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>
在线服务
</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">
兼容 OpenAI 协议的服务化部署
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../online_serving/metrics/" class="md-nav__link">
<span class="md-ellipsis">
监控Metrics
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../online_serving/scheduler/" class="md-nav__link">
<span class="md-ellipsis">
调度器
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../online_serving/graceful_shutdown_service/" class="md-nav__link">
<span class="md-ellipsis">
服务优雅关闭
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../offline_inference/" class="md-nav__link">
<span class="md-ellipsis">
离线推理
</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">
最佳实践
</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>
最佳实践
</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/FAQ/" class="md-nav__link">
<span class="md-ellipsis">
常见问题
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6" checked>
<label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0">
<span class="md-ellipsis">
量化
</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="true">
<label class="md-nav__title" for="__nav_6">
<span class="md-nav__icon md-icon"></span>
量化
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
概述
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
概述
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="目录">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
目录
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#1" class="md-nav__link">
<span class="md-ellipsis">
1. 精度支持列表
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#2" class="md-nav__link">
<span class="md-ellipsis">
2. 模型支持列表
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#3" class="md-nav__link">
<span class="md-ellipsis">
3. 量化精度术语
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="online_quantization/" class="md-nav__link">
<span class="md-ellipsis">
在线量化
</span>
</a>
</li>
<li class="md-nav__item">
<a href="wint2/" class="md-nav__link">
<span class="md-ellipsis">
WINT2量化
</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">
特性
</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>
特性
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../features/prefix_caching/" class="md-nav__link">
<span class="md-ellipsis">
前缀缓存
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/disaggregated/" class="md-nav__link">
<span class="md-ellipsis">
分离式部署
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/chunked_prefill/" class="md-nav__link">
<span class="md-ellipsis">
分块预填充
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/load_balance/" class="md-nav__link">
<span class="md-ellipsis">
负载均衡
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/speculative_decoding/" class="md-nav__link">
<span class="md-ellipsis">
投机解码
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/structured_outputs/" class="md-nav__link">
<span class="md-ellipsis">
结构化输出
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/reasoning_output/" class="md-nav__link">
<span class="md-ellipsis">
思考链内容
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/early_stop/" class="md-nav__link">
<span class="md-ellipsis">
早停功能
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/plugins/" class="md-nav__link">
<span class="md-ellipsis">
插件机制
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/sampling/" class="md-nav__link">
<span class="md-ellipsis">
采样策略
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/multi-node_deployment/" class="md-nav__link">
<span class="md-ellipsis">
多机部署
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/graph_optimization/" class="md-nav__link">
<span class="md-ellipsis">
图优化
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/data_parallel_service/" class="md-nav__link">
<span class="md-ellipsis">
数据并行
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../features/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">
支持模型列表
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../benchmark/" class="md-nav__link">
<span class="md-ellipsis">
基准测试
</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">
用法
</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>
用法
</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">
日志说明
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../usage/code_overview/" class="md-nav__link">
<span class="md-ellipsis">
代码概述
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../usage/environment_variables/" class="md-nav__link">
<span class="md-ellipsis">
环境变量
</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="目录">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
目录
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#1" class="md-nav__link">
<span class="md-ellipsis">
1. 精度支持列表
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#2" class="md-nav__link">
<span class="md-ellipsis">
2. 模型支持列表
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#3" class="md-nav__link">
<span class="md-ellipsis">
3. 量化精度术语
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="_1">量化</h1>
<p>FastDeploy支持FP8、INT8、INT4、2-bit等多种量化推理精度支持模型权重、激活和KVCache 3种张量的不同精度推理可以满足低成本、低时延、长上下文等不同场景的推理需求。</p>
<h2 id="1">1. 精度支持列表</h2>
<table>
<thead>
<tr>
<th>量化方法</th>
<th>权重精度</th>
<th>激活精度</th>
<th>KVCache精度</th>
<th>在线/离线</th>
<th>支持硬件</th>
</tr>
</thead>
<tbody>
<tr>
<td><a href="online_quantization/#1-wint8--wint4">WINT8</a></td>
<td>INT8</td>
<td>BF16</td>
<td>BF16</td>
<td>在线</td>
<td>GPU, XPU</td>
</tr>
<tr>
<td><a href="online_quantization/#1-wint8--wint4">WINT4</a></td>
<td>INT4</td>
<td>BF16</td>
<td>BF16</td>
<td>在线</td>
<td>GPU, XPU</td>
</tr>
<tr>
<td><a href="online_quantization/#2-block-wise-fp8">block_wise_fp8</a></td>
<td>block-wise static FP8</td>
<td>token-wise dynamic FP8</td>
<td>BF16</td>
<td>在线</td>
<td>GPU</td>
</tr>
<tr>
<td><a href="wint2/">WINT2</a></td>
<td>2Bits</td>
<td>BF16</td>
<td>BF16</td>
<td>离线</td>
<td>GPU</td>
</tr>
<tr>
<td>MixQuant</td>
<td>INT4/INT8</td>
<td>INT8/BF16</td>
<td>INT8/BF16</td>
<td>离线</td>
<td>GPU, XPU</td>
</tr>
</tbody>
</table>
<p><strong>说明</strong></p>
<ol>
<li><strong>量化方法</strong>:对应量化配置文件中的"quantization"字段;</li>
<li><strong>在线/离线量化</strong>:主要用于区分权重的量化时间</li>
<li><strong>在线量化</strong>:推理引擎在加载 BF16 权重后,再对权重做量化;</li>
<li><strong>离线量化</strong>:在推理之前,将权重离线地量化并存储为低比特数值类型,推理时,加载量化后的低比特数值。</li>
<li><strong>动态量化/静态量化</strong>:主要用于区别激活的量化方式</li>
<li><strong>静态量化static</strong>在推理之前确定并存储量化系数推理时加载提前计算好的量化系数。因为量化系数在推理时是固定不变的所以叫静态量化static quantization</li>
<li><strong>动态量化dynamic</strong>在推理时即时地统计当前batch的量化系数。因为量化系数在推理时是动态地变化的所以叫动态量化dynamic quantization</li>
</ol>
<h2 id="2">2. 模型支持列表</h2>
<table>
<thead>
<tr>
<th>模型名称</th>
<th>支持量化精度</th>
</tr>
</thead>
<tbody>
<tr>
<td>ERNIE-4.5-300B-A47B</td>
<td>WINT8, WINT4, Block_wise= FP8, MixQuant</td>
</tr>
</tbody>
</table>
<h2 id="3">3. 量化精度术语</h2>
<p>FastDeploy 按以下格式命名各种量化精度:</p>
<pre><code>{tensor缩写}{数值类型}{tensor缩写}{数值类型}{tensor缩写}{数值类型}
</code></pre>
<p>部分示例如下:</p>
<ul>
<li><strong>W8A8C8</strong>W=weightsA=activationsC=CacheKV8默认为INT8</li>
<li><strong>W8A8C16</strong>16默认为BF16其它同上</li>
<li><strong>W4A16C16 / WInt4 / weight-only int4</strong>4默认为INT4</li>
<li><strong>WNF4A8C8</strong>NF4指4bit norm-float数值类型</li>
<li><strong>Wfp8Afp8</strong>权重和激活均为FP8精度</li>
<li><strong>W4Afp8</strong>权重为INT4, 激活为FP8</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">{"base": "../..", "features": [], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "\u5df2\u590d\u5236", "clipboard.copy": "\u590d\u5236", "search.result.more.one": "\u5728\u8be5\u9875\u4e0a\u8fd8\u6709 1 \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.more.other": "\u5728\u8be5\u9875\u4e0a\u8fd8\u6709 # \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.none": "\u6ca1\u6709\u627e\u5230\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.one": "\u627e\u5230 1 \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.other": "# \u4e2a\u7b26\u5408\u6761\u4ef6\u7684\u7ed3\u679c", "search.result.placeholder": "\u952e\u5165\u4ee5\u5f00\u59cb\u641c\u7d22", "search.result.term.missing": "\u7f3a\u5c11", "select.version": "\u9009\u62e9\u5f53\u524d\u7248\u672c"}, "version": null}</script>
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
</body>
</html>