Mathis/llamactl
1
0
Fork 0
mirror of https://github.com/lordmathis/llamactl.git synced 2025-11-05 16:44:22 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
dc21ae7cf490a44af35508f2e779e4e17e35b1c4
llamactl/v0.11.2/managing-instances/index.html

1093 lines
50 KiB
HTML
Raw Blame History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<meta name="description" content="User documentation for Llamatl - A management tool for Llama.cpp instances">
<meta name="author" content="Llamatl Team">
<link rel="canonical" href="https://llamactl.org/v0.11.2/managing-instances/">
<link rel="prev" href="../configuration/">
<link rel="next" href="../api-reference/">
<link rel="icon" href="../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.22">
<title>Managing Instances - Llamatl Documentation</title>
<link rel="stylesheet" href="../assets/stylesheets/main.84d31ad4.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>
<link rel="stylesheet" href="../css/css-v1.1.3.css">
<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="#managing-instances" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<div data-md-color-scheme="default" data-md-component="outdated" hidden>
</div>
<header class="md-header md-header--shadow md-header--lifted" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href=".." title="Llamatl Documentation" class="md-header__button md-logo" aria-label="Llamatl Documentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</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">
Llamatl Documentation
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Managing Instances
</span>
</div>
</div>
</div>
<form class="md-header__option" data-md-component="palette">
<input class="md-option" data-md-color-media="" 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="" data-md-color-scheme="slate" data-md-color-primary="indigo" data-md-color-accent="indigo" aria-label="Switch to light mode" type="radio" name="__palette" id="__palette_1">
<label class="md-header__button md-icon" title="Switch to light mode" 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>
<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">
<a href="javascript:void(0)" class="md-search__icon md-icon" title="Share" aria-label="Share" data-clipboard data-clipboard-text="" data-md-component="search-share" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M18 16.08c-.76 0-1.44.3-1.96.77L8.91 12.7c.05-.23.09-.46.09-.7s-.04-.47-.09-.7l7.05-4.11c.54.5 1.25.81 2.04.81a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3c0 .24.04.47.09.7L8.04 9.81C7.5 9.31 6.79 9 6 9a3 3 0 0 0-3 3 3 3 0 0 0 3 3c.79 0 1.5-.31 2.04-.81l7.12 4.15c-.05.21-.08.43-.08.66 0 1.61 1.31 2.91 2.92 2.91s2.92-1.3 2.92-2.91A2.92 2.92 0 0 0 18 16.08"/></svg>
</a>
<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/lordmathis/llamactl" 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">
lordmathis/llamactl
</div>
</a>
</div>
</nav>
<nav class="md-tabs" aria-label="Tabs" data-md-component="tabs">
<div class="md-grid">
<ul class="md-tabs__list">
<li class="md-tabs__item">
<a href=".." class="md-tabs__link">
Home
</a>
</li>
<li class="md-tabs__item">
<a href="../installation/" class="md-tabs__link">
Installation
</a>
</li>
<li class="md-tabs__item">
<a href="../quick-start/" class="md-tabs__link">
Quick Start
</a>
</li>
<li class="md-tabs__item">
<a href="../configuration/" class="md-tabs__link">
Configuration
</a>
</li>
<li class="md-tabs__item md-tabs__item--active">
<a href="./" class="md-tabs__link">
Managing Instances
</a>
</li>
<li class="md-tabs__item">
<a href="../api-reference/" class="md-tabs__link">
API Reference
</a>
</li>
<li class="md-tabs__item">
<a href="../troubleshooting/" class="md-tabs__link">
Troubleshooting
</a>
</li>
</ul>
</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 md-nav--lifted md-nav--integrated" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href=".." title="Llamatl Documentation" class="md-nav__button md-logo" aria-label="Llamatl Documentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
Llamatl Documentation
</label>
<div class="md-nav__source">
<a href="https://github.com/lordmathis/llamactl" 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">
lordmathis/llamactl
</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">
Home
</span>
</a>
</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="../quick-start/" class="md-nav__link">
<span class="md-ellipsis">
Quick Start
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../configuration/" class="md-nav__link">
<span class="md-ellipsis">
Configuration
</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">
Managing Instances
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Managing Instances
</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>
<nav class="md-nav" aria-label="Overview">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#authentication" class="md-nav__link">
<span class="md-ellipsis">
Authentication
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#theme-support" class="md-nav__link">
<span class="md-ellipsis">
Theme Support
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#instance-cards" class="md-nav__link">
<span class="md-ellipsis">
Instance Cards
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#create-instance" class="md-nav__link">
<span class="md-ellipsis">
Create Instance
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#start-instance" class="md-nav__link">
<span class="md-ellipsis">
Start Instance
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#stop-instance" class="md-nav__link">
<span class="md-ellipsis">
Stop Instance
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#edit-instance" class="md-nav__link">
<span class="md-ellipsis">
Edit Instance
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#view-logs" class="md-nav__link">
<span class="md-ellipsis">
View Logs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#delete-instance" class="md-nav__link">
<span class="md-ellipsis">
Delete Instance
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#instance-proxy" class="md-nav__link">
<span class="md-ellipsis">
Instance Proxy
</span>
</a>
<nav class="md-nav" aria-label="Instance Proxy">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#instance-health" class="md-nav__link">
<span class="md-ellipsis">
Instance Health
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../api-reference/" class="md-nav__link">
<span class="md-ellipsis">
API Reference
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../troubleshooting/" class="md-nav__link">
<span class="md-ellipsis">
Troubleshooting
</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="managing-instances">Managing Instances<a class="headerlink" href="#managing-instances" title="Permanent link">&para;</a></h1>
<p>Learn how to effectively manage your llama.cpp, MLX, and vLLM instances with Llamactl through both the Web UI and API. </p>
<h2 id="overview">Overview<a class="headerlink" href="#overview" title="Permanent link">&para;</a></h2>
<p>Llamactl provides two ways to manage instances: </p>
<ul>
<li><strong>Web UI</strong>: Accessible at <code>http://localhost:8080</code> with an intuitive dashboard </li>
<li><strong>REST API</strong>: Programmatic access for automation and integration </li>
</ul>
<p><img alt="Dashboard Screenshot" src="../images/dashboard.png" /> </p>
<h3 id="authentication">Authentication<a class="headerlink" href="#authentication" title="Permanent link">&para;</a></h3>
<p>Llamactl uses a <strong>Management API Key</strong> to authenticate requests to the management API (creating, starting, stopping instances). All curl examples below use <code>&lt;token&gt;</code> as a placeholder - replace this with your actual Management API Key. </p>
<p>By default, authentication is required. If you don't configure a management API key in your configuration file, llamactl will auto-generate one and print it to the terminal on startup. See the <a href="../configuration/">Configuration</a> guide for details. </p>
<p>For Web UI access:<br />
1. Navigate to the web UI<br />
2. Enter your Management API Key<br />
3. Bearer token is stored for the session </p>
<h3 id="theme-support">Theme Support<a class="headerlink" href="#theme-support" title="Permanent link">&para;</a></h3>
<ul>
<li>Switch between light and dark themes </li>
<li>Setting is remembered across sessions </li>
</ul>
<h2 id="instance-cards">Instance Cards<a class="headerlink" href="#instance-cards" title="Permanent link">&para;</a></h2>
<p>Each instance is displayed as a card showing: </p>
<ul>
<li><strong>Instance name</strong> </li>
<li><strong>Health status badge</strong> (unknown, ready, error, failed) </li>
<li><strong>Action buttons</strong> (start, stop, edit, logs, delete) </li>
</ul>
<h2 id="create-instance">Create Instance<a class="headerlink" href="#create-instance" title="Permanent link">&para;</a></h2>
<p><strong>Via Web UI</strong> </p>
<p><img alt="Create Instance Screenshot" src="../images/create_instance.png" /> </p>
<ol>
<li>Click the <strong>"Create Instance"</strong> button on the dashboard </li>
<li>Enter a unique <strong>Name</strong> for your instance (only required field) </li>
<li><strong>Select Target Node</strong>: Choose which node to deploy the instance to from the dropdown </li>
<li><strong>Choose Backend Type</strong>: <ul>
<li><strong>llama.cpp</strong>: For GGUF models using llama-server </li>
<li><strong>MLX</strong>: For MLX-optimized models (macOS only) </li>
<li><strong>vLLM</strong>: For distributed serving and high-throughput inference </li>
</ul>
</li>
<li>Configure model source: <ul>
<li><strong>For llama.cpp</strong>: GGUF model path or HuggingFace repo </li>
<li><strong>For MLX</strong>: MLX model path or identifier (e.g., <code>mlx-community/Mistral-7B-Instruct-v0.3-4bit</code>) </li>
<li><strong>For vLLM</strong>: HuggingFace model identifier (e.g., <code>microsoft/DialoGPT-medium</code>) </li>
</ul>
</li>
<li>Configure optional instance management settings: <ul>
<li><strong>Auto Restart</strong>: Automatically restart instance on failure </li>
<li><strong>Max Restarts</strong>: Maximum number of restart attempts </li>
<li><strong>Restart Delay</strong>: Delay in seconds between restart attempts </li>
<li><strong>On Demand Start</strong>: Start instance when receiving a request to the OpenAI compatible endpoint </li>
<li><strong>Idle Timeout</strong>: Minutes before stopping idle instance (set to 0 to disable) </li>
<li><strong>Environment Variables</strong>: Set custom environment variables for the instance process </li>
</ul>
</li>
<li>Configure backend-specific options: <ul>
<li><strong>llama.cpp</strong>: Threads, context size, GPU layers, port, etc. </li>
<li><strong>MLX</strong>: Temperature, top-p, adapter path, Python environment, etc. </li>
<li><strong>vLLM</strong>: Tensor parallel size, GPU memory utilization, quantization, etc. </li>
</ul>
</li>
</ol>
<div class="admonition tip">
<p class="admonition-title">Auto-Assignment</p>
<p>Llamactl automatically assigns ports from the configured port range (default: 8000-9000) and generates API keys if authentication is enabled. You typically don't need to manually specify these values. </p>
</div>
<ol>
<li>Click <strong>"Create"</strong> to save the instance </li>
</ol>
<p><strong>Via API</strong> </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a><span class="c1"># Create llama.cpp instance with local model file</span>
<a id="__codelineno-0-2" name="__codelineno-0-2" href="#__codelineno-0-2"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/v1/instances/my-llama-instance<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-3" name="__codelineno-0-3" href="#__codelineno-0-3"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-4" name="__codelineno-0-4" href="#__codelineno-0-4"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-5" name="__codelineno-0-5" href="#__codelineno-0-5"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{</span>
<a id="__codelineno-0-6" name="__codelineno-0-6" href="#__codelineno-0-6"></a><span class="s1"> &quot;backend_type&quot;: &quot;llama_cpp&quot;,</span>
<a id="__codelineno-0-7" name="__codelineno-0-7" href="#__codelineno-0-7"></a><span class="s1"> &quot;backend_options&quot;: {</span>
<a id="__codelineno-0-8" name="__codelineno-0-8" href="#__codelineno-0-8"></a><span class="s1"> &quot;model&quot;: &quot;/path/to/model.gguf&quot;,</span>
<a id="__codelineno-0-9" name="__codelineno-0-9" href="#__codelineno-0-9"></a><span class="s1"> &quot;threads&quot;: 8,</span>
<a id="__codelineno-0-10" name="__codelineno-0-10" href="#__codelineno-0-10"></a><span class="s1"> &quot;ctx_size&quot;: 4096,</span>
<a id="__codelineno-0-11" name="__codelineno-0-11" href="#__codelineno-0-11"></a><span class="s1"> &quot;gpu_layers&quot;: 32</span>
<a id="__codelineno-0-12" name="__codelineno-0-12" href="#__codelineno-0-12"></a><span class="s1"> },</span>
<a id="__codelineno-0-13" name="__codelineno-0-13" href="#__codelineno-0-13"></a><span class="s1"> &quot;nodes&quot;: [&quot;main&quot;]</span>
<a id="__codelineno-0-14" name="__codelineno-0-14" href="#__codelineno-0-14"></a><span class="s1"> }&#39;</span>
<a id="__codelineno-0-15" name="__codelineno-0-15" href="#__codelineno-0-15"></a>
<a id="__codelineno-0-16" name="__codelineno-0-16" href="#__codelineno-0-16"></a><span class="c1"># Create MLX instance (macOS only)</span>
<a id="__codelineno-0-17" name="__codelineno-0-17" href="#__codelineno-0-17"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/v1/instances/my-mlx-instance<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-18" name="__codelineno-0-18" href="#__codelineno-0-18"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-19" name="__codelineno-0-19" href="#__codelineno-0-19"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-20" name="__codelineno-0-20" href="#__codelineno-0-20"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{</span>
<a id="__codelineno-0-21" name="__codelineno-0-21" href="#__codelineno-0-21"></a><span class="s1"> &quot;backend_type&quot;: &quot;mlx_lm&quot;,</span>
<a id="__codelineno-0-22" name="__codelineno-0-22" href="#__codelineno-0-22"></a><span class="s1"> &quot;backend_options&quot;: {</span>
<a id="__codelineno-0-23" name="__codelineno-0-23" href="#__codelineno-0-23"></a><span class="s1"> &quot;model&quot;: &quot;mlx-community/Mistral-7B-Instruct-v0.3-4bit&quot;,</span>
<a id="__codelineno-0-24" name="__codelineno-0-24" href="#__codelineno-0-24"></a><span class="s1"> &quot;temp&quot;: 0.7,</span>
<a id="__codelineno-0-25" name="__codelineno-0-25" href="#__codelineno-0-25"></a><span class="s1"> &quot;top_p&quot;: 0.9,</span>
<a id="__codelineno-0-26" name="__codelineno-0-26" href="#__codelineno-0-26"></a><span class="s1"> &quot;max_tokens&quot;: 2048</span>
<a id="__codelineno-0-27" name="__codelineno-0-27" href="#__codelineno-0-27"></a><span class="s1"> },</span>
<a id="__codelineno-0-28" name="__codelineno-0-28" href="#__codelineno-0-28"></a><span class="s1"> &quot;auto_restart&quot;: true,</span>
<a id="__codelineno-0-29" name="__codelineno-0-29" href="#__codelineno-0-29"></a><span class="s1"> &quot;max_restarts&quot;: 3,</span>
<a id="__codelineno-0-30" name="__codelineno-0-30" href="#__codelineno-0-30"></a><span class="s1"> &quot;nodes&quot;: [&quot;main&quot;]</span>
<a id="__codelineno-0-31" name="__codelineno-0-31" href="#__codelineno-0-31"></a><span class="s1"> }&#39;</span>
<a id="__codelineno-0-32" name="__codelineno-0-32" href="#__codelineno-0-32"></a>
<a id="__codelineno-0-33" name="__codelineno-0-33" href="#__codelineno-0-33"></a><span class="c1"># Create vLLM instance</span>
<a id="__codelineno-0-34" name="__codelineno-0-34" href="#__codelineno-0-34"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/v1/instances/my-vllm-instance<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-35" name="__codelineno-0-35" href="#__codelineno-0-35"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-36" name="__codelineno-0-36" href="#__codelineno-0-36"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-37" name="__codelineno-0-37" href="#__codelineno-0-37"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{</span>
<a id="__codelineno-0-38" name="__codelineno-0-38" href="#__codelineno-0-38"></a><span class="s1"> &quot;backend_type&quot;: &quot;vllm&quot;,</span>
<a id="__codelineno-0-39" name="__codelineno-0-39" href="#__codelineno-0-39"></a><span class="s1"> &quot;backend_options&quot;: {</span>
<a id="__codelineno-0-40" name="__codelineno-0-40" href="#__codelineno-0-40"></a><span class="s1"> &quot;model&quot;: &quot;microsoft/DialoGPT-medium&quot;,</span>
<a id="__codelineno-0-41" name="__codelineno-0-41" href="#__codelineno-0-41"></a><span class="s1"> &quot;tensor_parallel_size&quot;: 2,</span>
<a id="__codelineno-0-42" name="__codelineno-0-42" href="#__codelineno-0-42"></a><span class="s1"> &quot;gpu_memory_utilization&quot;: 0.9</span>
<a id="__codelineno-0-43" name="__codelineno-0-43" href="#__codelineno-0-43"></a><span class="s1"> },</span>
<a id="__codelineno-0-44" name="__codelineno-0-44" href="#__codelineno-0-44"></a><span class="s1"> &quot;auto_restart&quot;: true,</span>
<a id="__codelineno-0-45" name="__codelineno-0-45" href="#__codelineno-0-45"></a><span class="s1"> &quot;on_demand_start&quot;: true,</span>
<a id="__codelineno-0-46" name="__codelineno-0-46" href="#__codelineno-0-46"></a><span class="s1"> &quot;environment&quot;: {</span>
<a id="__codelineno-0-47" name="__codelineno-0-47" href="#__codelineno-0-47"></a><span class="s1"> &quot;CUDA_VISIBLE_DEVICES&quot;: &quot;0,1&quot;,</span>
<a id="__codelineno-0-48" name="__codelineno-0-48" href="#__codelineno-0-48"></a><span class="s1"> &quot;NCCL_DEBUG&quot;: &quot;INFO&quot;,</span>
<a id="__codelineno-0-49" name="__codelineno-0-49" href="#__codelineno-0-49"></a><span class="s1"> &quot;PYTHONPATH&quot;: &quot;/custom/path&quot;</span>
<a id="__codelineno-0-50" name="__codelineno-0-50" href="#__codelineno-0-50"></a><span class="s1"> },</span>
<a id="__codelineno-0-51" name="__codelineno-0-51" href="#__codelineno-0-51"></a><span class="s1"> &quot;nodes&quot;: [&quot;main&quot;]</span>
<a id="__codelineno-0-52" name="__codelineno-0-52" href="#__codelineno-0-52"></a><span class="s1"> }&#39;</span>
<a id="__codelineno-0-53" name="__codelineno-0-53" href="#__codelineno-0-53"></a>
<a id="__codelineno-0-54" name="__codelineno-0-54" href="#__codelineno-0-54"></a><span class="c1"># Create llama.cpp instance with HuggingFace model</span>
<a id="__codelineno-0-55" name="__codelineno-0-55" href="#__codelineno-0-55"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/v1/instances/gemma-3-27b<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-56" name="__codelineno-0-56" href="#__codelineno-0-56"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-57" name="__codelineno-0-57" href="#__codelineno-0-57"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-58" name="__codelineno-0-58" href="#__codelineno-0-58"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{</span>
<a id="__codelineno-0-59" name="__codelineno-0-59" href="#__codelineno-0-59"></a><span class="s1"> &quot;backend_type&quot;: &quot;llama_cpp&quot;,</span>
<a id="__codelineno-0-60" name="__codelineno-0-60" href="#__codelineno-0-60"></a><span class="s1"> &quot;backend_options&quot;: {</span>
<a id="__codelineno-0-61" name="__codelineno-0-61" href="#__codelineno-0-61"></a><span class="s1"> &quot;hf_repo&quot;: &quot;unsloth/gemma-3-27b-it-GGUF&quot;,</span>
<a id="__codelineno-0-62" name="__codelineno-0-62" href="#__codelineno-0-62"></a><span class="s1"> &quot;hf_file&quot;: &quot;gemma-3-27b-it-GGUF.gguf&quot;,</span>
<a id="__codelineno-0-63" name="__codelineno-0-63" href="#__codelineno-0-63"></a><span class="s1"> &quot;gpu_layers&quot;: 32</span>
<a id="__codelineno-0-64" name="__codelineno-0-64" href="#__codelineno-0-64"></a><span class="s1"> },</span>
<a id="__codelineno-0-65" name="__codelineno-0-65" href="#__codelineno-0-65"></a><span class="s1"> &quot;nodes&quot;: [&quot;main&quot;]</span>
<a id="__codelineno-0-66" name="__codelineno-0-66" href="#__codelineno-0-66"></a><span class="s1"> }&#39;</span>
<a id="__codelineno-0-67" name="__codelineno-0-67" href="#__codelineno-0-67"></a>
<a id="__codelineno-0-68" name="__codelineno-0-68" href="#__codelineno-0-68"></a><span class="c1"># Create instance on specific remote node</span>
<a id="__codelineno-0-69" name="__codelineno-0-69" href="#__codelineno-0-69"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/v1/instances/remote-llama<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-70" name="__codelineno-0-70" href="#__codelineno-0-70"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-71" name="__codelineno-0-71" href="#__codelineno-0-71"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-72" name="__codelineno-0-72" href="#__codelineno-0-72"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{</span>
<a id="__codelineno-0-73" name="__codelineno-0-73" href="#__codelineno-0-73"></a><span class="s1"> &quot;backend_type&quot;: &quot;llama_cpp&quot;,</span>
<a id="__codelineno-0-74" name="__codelineno-0-74" href="#__codelineno-0-74"></a><span class="s1"> &quot;backend_options&quot;: {</span>
<a id="__codelineno-0-75" name="__codelineno-0-75" href="#__codelineno-0-75"></a><span class="s1"> &quot;model&quot;: &quot;/models/llama-7b.gguf&quot;,</span>
<a id="__codelineno-0-76" name="__codelineno-0-76" href="#__codelineno-0-76"></a><span class="s1"> &quot;gpu_layers&quot;: 32</span>
<a id="__codelineno-0-77" name="__codelineno-0-77" href="#__codelineno-0-77"></a><span class="s1"> },</span>
<a id="__codelineno-0-78" name="__codelineno-0-78" href="#__codelineno-0-78"></a><span class="s1"> &quot;nodes&quot;: [&quot;worker1&quot;]</span>
<a id="__codelineno-0-79" name="__codelineno-0-79" href="#__codelineno-0-79"></a><span class="s1"> }&#39;</span>
<a id="__codelineno-0-80" name="__codelineno-0-80" href="#__codelineno-0-80"></a>
<a id="__codelineno-0-81" name="__codelineno-0-81" href="#__codelineno-0-81"></a><span class="c1"># Create instance on multiple nodes for high availability</span>
<a id="__codelineno-0-82" name="__codelineno-0-82" href="#__codelineno-0-82"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/v1/instances/multi-node-llama<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-83" name="__codelineno-0-83" href="#__codelineno-0-83"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-84" name="__codelineno-0-84" href="#__codelineno-0-84"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-0-85" name="__codelineno-0-85" href="#__codelineno-0-85"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{</span>
<a id="__codelineno-0-86" name="__codelineno-0-86" href="#__codelineno-0-86"></a><span class="s1"> &quot;backend_type&quot;: &quot;llama_cpp&quot;,</span>
<a id="__codelineno-0-87" name="__codelineno-0-87" href="#__codelineno-0-87"></a><span class="s1"> &quot;backend_options&quot;: {</span>
<a id="__codelineno-0-88" name="__codelineno-0-88" href="#__codelineno-0-88"></a><span class="s1"> &quot;model&quot;: &quot;/models/llama-7b.gguf&quot;,</span>
<a id="__codelineno-0-89" name="__codelineno-0-89" href="#__codelineno-0-89"></a><span class="s1"> &quot;gpu_layers&quot;: 32</span>
<a id="__codelineno-0-90" name="__codelineno-0-90" href="#__codelineno-0-90"></a><span class="s1"> },</span>
<a id="__codelineno-0-91" name="__codelineno-0-91" href="#__codelineno-0-91"></a><span class="s1"> &quot;nodes&quot;: [&quot;worker1&quot;, &quot;worker2&quot;, &quot;worker3&quot;]</span>
<a id="__codelineno-0-92" name="__codelineno-0-92" href="#__codelineno-0-92"></a><span class="s1"> }&#39;</span>
</code></pre></div>
<h2 id="start-instance">Start Instance<a class="headerlink" href="#start-instance" title="Permanent link">&para;</a></h2>
<p><strong>Via Web UI</strong><br />
1. Click the <strong>"Start"</strong> button on an instance card<br />
2. Watch the status change to "Unknown"<br />
3. Monitor progress in the logs<br />
4. Instance status changes to "Ready" when ready </p>
<p><strong>Via API</strong><br />
<div class="highlight"><pre><span></span><code><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/v1/instances/<span class="o">{</span>name<span class="o">}</span>/start<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span>
</code></pre></div></p>
<h2 id="stop-instance">Stop Instance<a class="headerlink" href="#stop-instance" title="Permanent link">&para;</a></h2>
<p><strong>Via Web UI</strong><br />
1. Click the <strong>"Stop"</strong> button on an instance card<br />
2. Instance gracefully shuts down </p>
<p><strong>Via API</strong><br />
<div class="highlight"><pre><span></span><code><a id="__codelineno-2-1" name="__codelineno-2-1" href="#__codelineno-2-1"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/v1/instances/<span class="o">{</span>name<span class="o">}</span>/stop<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-2-2" name="__codelineno-2-2" href="#__codelineno-2-2"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span>
</code></pre></div></p>
<h2 id="edit-instance">Edit Instance<a class="headerlink" href="#edit-instance" title="Permanent link">&para;</a></h2>
<p><strong>Via Web UI</strong><br />
1. Click the <strong>"Edit"</strong> button on an instance card<br />
2. Modify settings in the configuration dialog<br />
3. Changes require instance restart to take effect<br />
4. Click <strong>"Update &amp; Restart"</strong> to apply changes </p>
<p><strong>Via API</strong><br />
Modify instance settings: </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-3-1" name="__codelineno-3-1" href="#__codelineno-3-1"></a>curl<span class="w"> </span>-X<span class="w"> </span>PUT<span class="w"> </span>http://localhost:8080/api/v1/instances/<span class="o">{</span>name<span class="o">}</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-3-2" name="__codelineno-3-2" href="#__codelineno-3-2"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-3-3" name="__codelineno-3-3" href="#__codelineno-3-3"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-3-4" name="__codelineno-3-4" href="#__codelineno-3-4"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{</span>
<a id="__codelineno-3-5" name="__codelineno-3-5" href="#__codelineno-3-5"></a><span class="s1"> &quot;backend_options&quot;: {</span>
<a id="__codelineno-3-6" name="__codelineno-3-6" href="#__codelineno-3-6"></a><span class="s1"> &quot;threads&quot;: 8,</span>
<a id="__codelineno-3-7" name="__codelineno-3-7" href="#__codelineno-3-7"></a><span class="s1"> &quot;context_size&quot;: 4096</span>
<a id="__codelineno-3-8" name="__codelineno-3-8" href="#__codelineno-3-8"></a><span class="s1"> }</span>
<a id="__codelineno-3-9" name="__codelineno-3-9" href="#__codelineno-3-9"></a><span class="s1"> }&#39;</span>
</code></pre></div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Configuration changes require restarting the instance to take effect. </p>
</div>
<h2 id="view-logs">View Logs<a class="headerlink" href="#view-logs" title="Permanent link">&para;</a></h2>
<p><strong>Via Web UI</strong> </p>
<ol>
<li>Click the <strong>"Logs"</strong> button on any instance card </li>
<li>Real-time log viewer opens </li>
</ol>
<p><strong>Via API</strong><br />
Check instance status in real-time: </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-4-1" name="__codelineno-4-1" href="#__codelineno-4-1"></a><span class="c1"># Get instance logs</span>
<a id="__codelineno-4-2" name="__codelineno-4-2" href="#__codelineno-4-2"></a>curl<span class="w"> </span>http://localhost:8080/api/v1/instances/<span class="o">{</span>name<span class="o">}</span>/logs<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-4-3" name="__codelineno-4-3" href="#__codelineno-4-3"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span>
</code></pre></div>
<h2 id="delete-instance">Delete Instance<a class="headerlink" href="#delete-instance" title="Permanent link">&para;</a></h2>
<p><strong>Via Web UI</strong><br />
1. Click the <strong>"Delete"</strong> button on an instance card<br />
2. Only stopped instances can be deleted<br />
3. Confirm deletion in the dialog </p>
<p><strong>Via API</strong><br />
<div class="highlight"><pre><span></span><code><a id="__codelineno-5-1" name="__codelineno-5-1" href="#__codelineno-5-1"></a>curl<span class="w"> </span>-X<span class="w"> </span>DELETE<span class="w"> </span>http://localhost:8080/api/v1/instances/<span class="o">{</span>name<span class="o">}</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-5-2" name="__codelineno-5-2" href="#__codelineno-5-2"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span>
</code></pre></div></p>
<h2 id="instance-proxy">Instance Proxy<a class="headerlink" href="#instance-proxy" title="Permanent link">&para;</a></h2>
<p>Llamactl proxies all requests to the underlying backend instances (llama-server, MLX, or vLLM). </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-6-1" name="__codelineno-6-1" href="#__codelineno-6-1"></a><span class="c1"># Proxy requests to the instance</span>
<a id="__codelineno-6-2" name="__codelineno-6-2" href="#__codelineno-6-2"></a>curl<span class="w"> </span>http://localhost:8080/api/v1/instances/<span class="o">{</span>name<span class="o">}</span>/proxy/<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-6-3" name="__codelineno-6-3" href="#__codelineno-6-3"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span>
</code></pre></div>
<p>All backends provide OpenAI-compatible endpoints. Check the respective documentation:<br />
- <a href="https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md">llama-server docs</a><br />
- <a href="https://github.com/ml-explore/mlx-lm/blob/main/mlx_lm/SERVER.md">MLX-LM docs</a><br />
- <a href="https://docs.vllm.ai/en/latest/">vLLM docs</a> </p>
<h3 id="instance-health">Instance Health<a class="headerlink" href="#instance-health" title="Permanent link">&para;</a></h3>
<p><strong>Via Web UI</strong> </p>
<ol>
<li>The health status badge is displayed on each instance card </li>
</ol>
<p><strong>Via API</strong> </p>
<p>Check the health status of your instances: </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-7-1" name="__codelineno-7-1" href="#__codelineno-7-1"></a>curl<span class="w"> </span>http://localhost:8080/api/v1/instances/<span class="o">{</span>name<span class="o">}</span>/proxy/health<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-7-2" name="__codelineno-7-2" href="#__codelineno-7-2"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer &lt;token&gt;&quot;</span>
</code></pre></div>
<aside class="md-source-file">
<span class="md-source-file__fact">
<span class="md-icon" title="Last update">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M21 13.1c-.1 0-.3.1-.4.2l-1 1 2.1 2.1 1-1c.2-.2.2-.6 0-.8l-1.3-1.3c-.1-.1-.2-.2-.4-.2m-1.9 1.8-6.1 6V23h2.1l6.1-6.1zM12.5 7v5.2l4 2.4-1 1L11 13V7zM11 21.9c-5.1-.5-9-4.8-9-9.9C2 6.5 6.5 2 12 2c5.3 0 9.6 4.1 10 9.3-.3-.1-.6-.2-1-.2s-.7.1-1 .2C19.6 7.2 16.2 4 12 4c-4.4 0-8 3.6-8 8 0 4.1 3.1 7.5 7.1 7.9l-.1.2z"/></svg>
</span>
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date" title="October 26, 2025 16:28:01 UTC">October 26, 2025</span>
</span>
</aside>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
<button type="button" class="md-top md-icon" data-md-component="top" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8z"/></svg>
Back to top
</button>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
<div class="md-social">
<a href="https://github.com/lordmathis/llamactl" target="_blank" rel="noopener" title="github.com" class="md-social__link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><!--! 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="M173.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6m-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3m44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9M252.8 8C114.1 8 8 113.3 8 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C436.2 457.8 504 362.9 504 252 504 113.3 391.5 8 252.8 8M105.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1m-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7m32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1m-11.4-14.7c-1.6 1-1.6 3.6 0 5.9s4.3 3.3 5.6 2.3c1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2"/></svg>
</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": ["navigation.tabs", "navigation.tabs.sticky", "toc.integrate", "navigation.top", "search.highlight", "search.share", "content.code.copy"], "search": "../assets/javascripts/workers/search.973d3a69.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": {"default": "stable", "provider": "mike"}}</script>
<script src="../assets/javascripts/bundle.f55a23d4.min.js"></script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink