mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
3043 lines
53 KiB
HTML
3043 lines
53 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="prev" href="../reasoning_output/">
|
|
|
|
|
|
<link rel="next" href="../early_stop/">
|
|
|
|
|
|
|
|
<link rel="alternate" href="./" hreflang="en">
|
|
|
|
<link rel="alternate" href="../../zh/features/thinking_budget/" hreflang="zh">
|
|
|
|
|
|
|
|
<link rel="icon" href="../../assets/images/favicon.ico">
|
|
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.6">
|
|
|
|
|
|
|
|
<title>Thinking Budget - 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="#thinking-budget-logits-processor" 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">
|
|
|
|
Thinking Budget
|
|
|
|
</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/thinking_budget/" 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--active md-nav__item--nested">
|
|
|
|
|
|
|
|
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" checked>
|
|
|
|
|
|
<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="true">
|
|
<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 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">
|
|
|
|
|
|
Thinking Budget
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<a href="./" class="md-nav__link md-nav__link--active">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
|
|
|
|
Thinking Budget
|
|
|
|
|
|
|
|
</span>
|
|
|
|
|
|
|
|
</a>
|
|
|
|
|
|
|
|
<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>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#when-to-use" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
When to Use
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#how-it-works" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
How It Works
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#requirements" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Requirements
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#request-parameters" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Request Parameters
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#operator-level-vs-logitsprocessor" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Operator-Level vs LogitsProcessor
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#practical-guidance" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Practical guidance
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#online-usage" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Online Usage
|
|
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Online Usage">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#1-start-service" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
1. Start service
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#2-send-request" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
2. Send request
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#3-operator-level-thinking-cap-only-no-logits-processor" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
3. Operator-level thinking cap only (no logits processor)
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#offline-usage" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Offline Usage
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#performance-note" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Performance Note
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
|
|
</nav>
|
|
|
|
</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>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#when-to-use" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
When to Use
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#how-it-works" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
How It Works
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#requirements" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Requirements
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#request-parameters" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Request Parameters
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#operator-level-vs-logitsprocessor" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Operator-Level vs LogitsProcessor
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#practical-guidance" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Practical guidance
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#online-usage" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Online Usage
|
|
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Online Usage">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#1-start-service" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
1. Start service
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#2-send-request" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
2. Send request
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#3-operator-level-thinking-cap-only-no-logits-processor" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
3. Operator-level thinking cap only (no logits processor)
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#offline-usage" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Offline Usage
|
|
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#performance-note" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
|
|
Performance Note
|
|
|
|
</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="thinking-budget-logits-processor">Thinking Budget Logits Processor</h1>
|
|
<h2 id="overview">Overview</h2>
|
|
<p><code>ThinkingBudgetLogitsProcessor</code> limits the number of tokens generated inside the <code><think> ... </think></code>
|
|
segment. When the budget is reached, it terminates thinking by forcing <code></think></code>. If
|
|
<code>think_stop_sentence</code> is configured, it forces the custom sentence first and then <code></think></code>.</p>
|
|
<h2 id="when-to-use">When to Use</h2>
|
|
<ul>
|
|
<li>Models that emit <code><think></code>/<code></think></code> tokens for reasoning.</li>
|
|
<li>You need a hard cap on thinking length without changing sampling logic.</li>
|
|
</ul>
|
|
<h2 id="how-it-works">How It Works</h2>
|
|
<ol>
|
|
<li><strong>Request-side precompute (DataProcessor)</strong>: when a request includes <code>thinking_budget</code>, the prompt token ids are scanned to determine whether thinking has started, whether it already ended, and how many tokens are already inside the thinking section.</li>
|
|
<li><strong>Per-step update</strong>: during decoding, the processor tracks <code>last_token_id</code> and <code>tokens_after_start</code>.</li>
|
|
<li><strong>Budget enforcement</strong>: once the budget is reached, it forces <code></think></code> directly. If <code>think_stop_sentence</code>
|
|
is configured, it forces that sentence first and then <code></think></code>.</li>
|
|
</ol>
|
|
<h2 id="requirements">Requirements</h2>
|
|
<ul>
|
|
<li>The model must provide valid token ids for <code>think_start_id</code> and <code>think_end_id</code> (via <code>ModelConfig</code>).</li>
|
|
<li>If either of these ids is invalid, the processor is disabled and <code>thinking_budget</code> will not take effect.</li>
|
|
</ul>
|
|
<h2 id="request-parameters">Request Parameters</h2>
|
|
<ul>
|
|
<li><code>thinking_budget</code> (int, required to enable): maximum number of decode-time tokens after <code><think></code> before forced
|
|
termination.</li>
|
|
<li><code>think_stop_sentence</code> (string, optional): a literal custom sentence that will be tokenized on the request side
|
|
and enforced near the budget boundary.</li>
|
|
</ul>
|
|
<h2 id="operator-level-vs-logitsprocessor">Operator-Level vs LogitsProcessor</h2>
|
|
<p>FastDeploy has two ways to limit thinking length:</p>
|
|
<ul>
|
|
<li><strong>Operator-level limit</strong> (<code>enable_thinking=true</code> + <code>reasoning_max_tokens</code>):</li>
|
|
<li>Implemented in built-in post-processing kernels.</li>
|
|
<li>Lower overhead and better throughput under high concurrency.</li>
|
|
<li>Best for simple "cap the thinking length" use cases.</li>
|
|
<li><strong><code>ThinkingBudgetLogitsProcessor</code></strong> (<code>logits_processors_args.thinking_budget</code>):</li>
|
|
<li>Implemented in per-step Python logits processing.</li>
|
|
<li>Supports flexible controls, such as <code>think_stop_sentence</code> (custom inserted sentence before ending thinking).</li>
|
|
<li>Higher runtime overhead under high concurrency compared with operator-level limit.</li>
|
|
</ul>
|
|
<p>In short:</p>
|
|
<ul>
|
|
<li>If you only need a hard cap on thinking length, prefer <code>reasoning_max_tokens</code>.</li>
|
|
<li>If you need custom behavior (for example, inserting a custom sentence before <code></think></code>), use
|
|
<code>ThinkingBudgetLogitsProcessor</code>.</li>
|
|
</ul>
|
|
<h2 id="practical-guidance">Practical guidance</h2>
|
|
<p><code>reasoning_max_tokens</code> and <code>thinking_budget</code> are not mutually exclusive in current implementation.
|
|
If both are configured for the same request, both constraints can take effect, and whichever triggers first will end the thinking phase.</p>
|
|
<ul>
|
|
<li>To use <strong>operator-level-only</strong> behavior: this is request-level config only. Set
|
|
<code>enable_thinking=true</code> and <code>reasoning_max_tokens</code> in request, and do not set <code>thinking_budget</code>.</li>
|
|
<li>To use <strong>logits-processor-only</strong> behavior (especially with <code>think_stop_sentence</code>): this requires
|
|
service-level + request-level config. Start service with <code>--logits-processors ThinkingBudgetLogitsProcessor</code>,
|
|
and set <code>thinking_budget</code> (and optional <code>think_stop_sentence</code>) in <code>logits_processors_args</code>; leave
|
|
<code>reasoning_max_tokens</code> unset.</li>
|
|
<li><code>thinking_budget</code> itself does not require <code>enable_thinking=true</code>.</li>
|
|
<li>If an ERNIE chat template already appends <code><think></code> in the prompt, <code>thinking_budget</code> should still take effect; it
|
|
does not require the model to emit another <code><think></code> during decoding.</li>
|
|
<li>Avoid enabling both for strict custom sentence insertion requirements, because operator-level
|
|
termination may cut the custom sentence path earlier.</li>
|
|
</ul>
|
|
<h2 id="online-usage">Online Usage</h2>
|
|
<h3 id="1-start-service">1. Start service</h3>
|
|
<pre><code class="language-bash">python -m fastdeploy.entrypoints.openai.api_server \
|
|
--model Qwen/Qwen3-0.6B \
|
|
--port 8180 \
|
|
--metrics-port 8181 \
|
|
--engine-worker-queue-port 8182 \
|
|
--max-model-len 32768 \
|
|
--max-num-seqs 32 \
|
|
--logits-processors ThinkingBudgetLogitsProcessor
|
|
</code></pre>
|
|
<h3 id="2-send-request">2. Send request</h3>
|
|
<pre><code class="language-bash">curl -X POST "http://0.0.0.0:8180/v1/chat/completions" \
|
|
-H "Content-Type: application/json" \
|
|
-d '{
|
|
"messages": [{"role": "user", "content": "Hello!"}],
|
|
"max_completion_tokens": 30,
|
|
"logits_processors_args": {
|
|
"thinking_budget": 20,
|
|
"think_stop_sentence": "Thinking limit reached, now replying."
|
|
}
|
|
}'
|
|
</code></pre>
|
|
<p>If you do not need thinking control for a request, simply omit <code>thinking_budget</code>.</p>
|
|
<h3 id="3-operator-level-thinking-cap-only-no-logits-processor">3. Operator-level thinking cap only (no logits processor)</h3>
|
|
<pre><code class="language-bash">curl -X POST "http://0.0.0.0:8180/v1/chat/completions" \
|
|
-H "Content-Type: application/json" \
|
|
-d '{
|
|
"messages": [{"role": "user", "content": "Hello!"}],
|
|
"max_completion_tokens": 512,
|
|
"enable_thinking": true,
|
|
"reasoning_max_tokens": 200
|
|
}'
|
|
</code></pre>
|
|
<h2 id="offline-usage">Offline Usage</h2>
|
|
<pre><code class="language-python">from fastdeploy import LLM, SamplingParams
|
|
|
|
llm = LLM(
|
|
model="Qwen/Qwen3-0.6B",
|
|
engine_worker_queue_port=8282,
|
|
cache_queue_port=8383,
|
|
logits_processors=["ThinkingBudgetLogitsProcessor"],
|
|
)
|
|
|
|
sampling_params = SamplingParams(
|
|
max_tokens=512,
|
|
logits_processors_args={"thinking_budget": 20, "think_stop_sentence": "Thinking limit reached, now replying."},
|
|
)
|
|
|
|
outputs = llm.chat([{"role": "user", "content": "Hello, who are u?"}], sampling_params)
|
|
print(outputs[0].outputs.text)
|
|
</code></pre>
|
|
<h2 id="performance-note">Performance Note</h2>
|
|
<p>This processor runs <code>update_state</code> and <code>apply</code> on every decode step. If you only need a hard
|
|
thinking-length cap and care most about throughput, consider the operator-level reasoning-length
|
|
controls instead of per-step logits processing.</p>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</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 © 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> |