Files
ktransformers/en/multi-gpu-tutorial.html
T
2025-07-27 09:20:13 +00:00

338 lines
16 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<!DOCTYPE HTML>
<html lang="zh-CN" class="light sidebar-visible" dir="ltr">
<head>
<!-- Book generated using mdBook -->
<meta charset="UTF-8">
<title>Multi-GPU Tutorial - Ktransformers</title>
<!-- Custom HTML head -->
<meta name="description" content="">
<meta name="viewport" content="width=device-width, initial-scale=1">
<meta name="theme-color" content="#ffffff">
<link rel="icon" href="../favicon.svg">
<link rel="shortcut icon" href="../favicon.png">
<link rel="stylesheet" href="../css/variables.css">
<link rel="stylesheet" href="../css/general.css">
<link rel="stylesheet" href="../css/chrome.css">
<link rel="stylesheet" href="../css/print.css" media="print">
<!-- Fonts -->
<link rel="stylesheet" href="../FontAwesome/css/font-awesome.css">
<link rel="stylesheet" href="../fonts/fonts.css">
<!-- Highlight.js Stylesheets -->
<link rel="stylesheet" id="highlight-css" href="../highlight.css">
<link rel="stylesheet" id="tomorrow-night-css" href="../tomorrow-night.css">
<link rel="stylesheet" id="ayu-highlight-css" href="../ayu-highlight.css">
<!-- Custom theme stylesheets -->
<!-- Provide site root and default themes to javascript -->
<script>
const path_to_root = "../";
const default_light_theme = "light";
const default_dark_theme = "navy";
window.path_to_searchindex_js = "../searchindex.js";
</script>
<!-- Start loading toc.js asap -->
<script src="../toc.js"></script>
</head>
<body>
<div id="mdbook-help-container">
<div id="mdbook-help-popup">
<h2 class="mdbook-help-title">Keyboard shortcuts</h2>
<div>
<p>Press <kbd>←</kbd> or <kbd>→</kbd> to navigate between chapters</p>
<p>Press <kbd>S</kbd> or <kbd>/</kbd> to search in the book</p>
<p>Press <kbd>?</kbd> to show this help</p>
<p>Press <kbd>Esc</kbd> to hide this help</p>
</div>
</div>
</div>
<div id="body-container">
<!-- Work around some values being stored in localStorage wrapped in quotes -->
<script>
try {
let theme = localStorage.getItem('mdbook-theme');
let sidebar = localStorage.getItem('mdbook-sidebar');
if (theme.startsWith('"') && theme.endsWith('"')) {
localStorage.setItem('mdbook-theme', theme.slice(1, theme.length - 1));
}
if (sidebar.startsWith('"') && sidebar.endsWith('"')) {
localStorage.setItem('mdbook-sidebar', sidebar.slice(1, sidebar.length - 1));
}
} catch (e) { }
</script>
<!-- Set the theme before any content is loaded, prevents flash -->
<script>
const default_theme = window.matchMedia("(prefers-color-scheme: dark)").matches ? default_dark_theme : default_light_theme;
let theme;
try { theme = localStorage.getItem('mdbook-theme'); } catch(e) { }
if (theme === null || theme === undefined) { theme = default_theme; }
const html = document.documentElement;
html.classList.remove('light')
html.classList.add(theme);
html.classList.add("js");
</script>
<input type="checkbox" id="sidebar-toggle-anchor" class="hidden">
<!-- Hide / unhide sidebar before it is displayed -->
<script>
let sidebar = null;
const sidebar_toggle = document.getElementById("sidebar-toggle-anchor");
if (document.body.clientWidth >= 1080) {
try { sidebar = localStorage.getItem('mdbook-sidebar'); } catch(e) { }
sidebar = sidebar || 'visible';
} else {
sidebar = 'hidden';
sidebar_toggle.checked = false;
}
if (sidebar === 'visible') {
sidebar_toggle.checked = true;
} else {
html.classList.remove('sidebar-visible');
}
</script>
<nav id="sidebar" class="sidebar" aria-label="Table of contents">
<!-- populated by js -->
<mdbook-sidebar-scrollbox class="sidebar-scrollbox"></mdbook-sidebar-scrollbox>
<noscript>
<iframe class="sidebar-iframe-outer" src="../toc.html"></iframe>
</noscript>
<div id="sidebar-resize-handle" class="sidebar-resize-handle">
<div class="sidebar-resize-indicator"></div>
</div>
</nav>
<div id="page-wrapper" class="page-wrapper">
<div class="page">
<div id="menu-bar-hover-placeholder"></div>
<div id="menu-bar" class="menu-bar sticky">
<div class="left-buttons">
<label id="sidebar-toggle" class="icon-button" for="sidebar-toggle-anchor" title="Toggle Table of Contents" aria-label="Toggle Table of Contents" aria-controls="sidebar">
<i class="fa fa-bars"></i>
</label>
<button id="theme-toggle" class="icon-button" type="button" title="Change theme" aria-label="Change theme" aria-haspopup="true" aria-expanded="false" aria-controls="theme-list">
<i class="fa fa-paint-brush"></i>
</button>
<ul id="theme-list" class="theme-popup" aria-label="Themes" role="menu">
<li role="none"><button role="menuitem" class="theme" id="default_theme">Auto</button></li>
<li role="none"><button role="menuitem" class="theme" id="light">Light</button></li>
<li role="none"><button role="menuitem" class="theme" id="rust">Rust</button></li>
<li role="none"><button role="menuitem" class="theme" id="coal">Coal</button></li>
<li role="none"><button role="menuitem" class="theme" id="navy">Navy</button></li>
<li role="none"><button role="menuitem" class="theme" id="ayu">Ayu</button></li>
</ul>
<button id="search-toggle" class="icon-button" type="button" title="Search (`/`)" aria-label="Toggle Searchbar" aria-expanded="false" aria-keyshortcuts="/ s" aria-controls="searchbar">
<i class="fa fa-search"></i>
</button>
</div>
<h1 class="menu-title">Ktransformers</h1>
<div class="right-buttons">
<a href="../print.html" title="Print this book" aria-label="Print this book">
<i id="print-button" class="fa fa-print"></i>
</a>
<a href="https://github.com/kvcache-ai/ktransformers" title="Git repository" aria-label="Git repository">
<i id="git-repository-button" class="fa fa-github"></i>
</a>
<a href="https://github.com/kvcache-ai/ktransformers/edit/main/doc/en/multi-gpu-tutorial.md" title="Suggest an edit" aria-label="Suggest an edit" rel="edit">
<i id="git-edit-button" class="fa fa-edit"></i>
</a>
</div>
</div>
<div id="search-wrapper" class="hidden">
<form id="searchbar-outer" class="searchbar-outer">
<div class="search-wrapper">
<input type="search" id="searchbar" name="searchbar" placeholder="Search this book ..." aria-controls="searchresults-outer" aria-describedby="searchresults-header">
<div class="spinner-wrapper">
<i class="fa fa-spinner fa-spin"></i>
</div>
</div>
</form>
<div id="searchresults-outer" class="searchresults-outer hidden">
<div id="searchresults-header" class="searchresults-header"></div>
<ul id="searchresults">
</ul>
</div>
</div>
<!-- Apply ARIA attributes after the sidebar and the sidebar toggle button are added to the DOM -->
<script>
document.getElementById('sidebar-toggle').setAttribute('aria-expanded', sidebar === 'visible');
document.getElementById('sidebar').setAttribute('aria-hidden', sidebar !== 'visible');
Array.from(document.querySelectorAll('#sidebar a')).forEach(function(link) {
link.setAttribute('tabIndex', sidebar === 'visible' ? 0 : -1);
});
</script>
<div id="content" class="content">
<main>
<h1 id="muti-gpu"><a class="header" href="#muti-gpu">Muti-GPU</a></h1>
<p>Assume you have read the <a href="./injection_tutorial.html">Injection Tutorial</a> and have a basic understanding of how to inject a model. In this tutorial, we will show you how to use KTransformers to run a model on multiple GPUs.</p>
<p>If you have multiple GPUs, you can set the device for each module to different GPUs.
DeepseekV2-Chat got 60 layers, if we got 2 GPUs, we can allocate 30 layers to each GPU. Complete multi GPU rule examples <a href="https://github.com/kvcache-ai/ktransformers/blob/main/ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-multi-gpu.yaml">here</a>.</p>
<p align="center">
<picture>
<img alt="Inject-Struction" src="../assets/multi_gpu.png" width=60%>
</picture>
</p>
<p>First of all, for multi-GPU, we have to inject an new operator <code>KDeepseekV2Model</code>. And set division of the layers to different GPUs. For our case, we have to set the <code>transfer_map</code> in the <code>KDeepseekV2Model</code> operatoras as follows:</p>
<pre><code class="language-yaml">- match:
name: "^model$"
replace:
class: "ktransformers.operators.models.KDeepseekV2Model"
kwargs:
transfer_map:
30: "cuda:1"
</code></pre>
<p>And we have to set the device for each module in the model.</p>
<p>For example, for <code>routed experts</code>, the yaml for one GPU is:</p>
<pre><code class="language-yaml">- match:
name: "^model\\.layers\\..*\\.mlp\\.experts$"
replace:
class: ktransformers.operators.experts.KTransformersExperts # Custom MoE kernel with expert parallelism
kwargs:
generate_device: "cuda:0"
generate_op: "MLPCUDAExperts"
out_device: "cuda:0"
recursive: False # Don't recursively inject submodules of this module
</code></pre>
<p>But for two GPUs, we need to set the device for each module in the model.</p>
<pre><code class="language-yaml"># allcate 0-29 layers‘s out_device to cuda:0
- match:
name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\.mlp\\.experts$"
replace:
class: ktransformers.operators.experts.KTransformersExperts # custom MoE Kernel with expert paralleism
kwargs:
generate_device: "cpu"
generate_op: "KExpertsCPU"
out_device: "cuda:0"
recursive: False # don't recursively inject submodules of this module
# allocate 30-59 layers‘s out_device to cuda:1
- match:
name: "^model\\.layers\\.([345][0-9])\\.mlp\\.experts$"
replace:
class: ktransformers.operators.experts.KTransformersExperts # custom MoE Kernel with expert paralleism
kwargs:
generate_device: "cpu"
generate_op: "KExpertsCPU"
out_device: "cuda:1"
recursive: False # don't recursively inject submodules of this module
</code></pre>
<p>For other modules, we can set the device in the same way.</p>
<h1 id="how-to-fully-utilize-multi-gpus-vram"><a class="header" href="#how-to-fully-utilize-multi-gpus-vram">How to fully utilize multi-GPU's VRAM</a></h1>
<p>When you have multiple GPUs, you can fully utilize the VRAM of each GPU by moving more weights to the GPU.</p>
<p>For example, for DeepSeekV2-Chat, we can move the weights of the experts to the GPU.</p>
<p>For example, the yaml for two GPUs is:</p>
<pre><code class="language-yaml">- match:
name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\.mlp\\.experts$"
replace:
class: ktransformers.operators.experts.KTransformersExperts
kwargs:
generate_device: "cpu"
generate_op: "KExpertsCPU"
out_device: "cuda:0"
recursive: False
</code></pre>
<p>But we got extra 60GB VRAM on cuda:0, we can move experts in layer 4~8 to cuda:0.</p>
<pre><code class="language-yaml"># Add new rule before old rule.
- match:
name: "^model\\.layers\\.([4-8])\\.mlp\\.experts$" # inject experts in layer 4~8 as marlin expert
replace:
class: ktransformers.operators.experts.KTransformersExperts
kwargs:
generate_device: "cuda:0"
generate_op: "KExpertsMarlin"
recursive: False
- match:
name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\.mlp\\.experts$"
replace:
class: ktransformers.operators.experts.KTransformersExperts
kwargs:
generate_device: "cpu"
generate_op: "KExpertsCPU"
out_device: "cuda:0"
recursive: False
</code></pre>
<p>Adjust the layer range as you want. Note that:</p>
<ul>
<li>The loading speed will be significantly slower for each expert moved to the GPU.</li>
<li>You have to close the cuda graph if you want to move the experts to the GPU.</li>
<li>For DeepSeek-R1/V3, each expert moved to the GPU will consume approximately 6GB of VRAM.</li>
<li>The first matched rule in yaml will be applied. For example, if you have two rules that match the same layer, only the first rule's replacement will be valid.</li>
</ul>
</main>
<nav class="nav-wrapper" aria-label="Page navigation">
<!-- Mobile navigation buttons -->
<a rel="prev" href="../en/injection_tutorial.html" class="mobile-nav-chapters previous" title="Previous chapter" aria-label="Previous chapter" aria-keyshortcuts="Left">
<i class="fa fa-angle-left"></i>
</a>
<a rel="next prefetch" href="../en/fp8_kernel.html" class="mobile-nav-chapters next" title="Next chapter" aria-label="Next chapter" aria-keyshortcuts="Right">
<i class="fa fa-angle-right"></i>
</a>
<div style="clear: both"></div>
</nav>
</div>
</div>
<nav class="nav-wide-wrapper" aria-label="Page navigation">
<a rel="prev" href="../en/injection_tutorial.html" class="nav-chapters previous" title="Previous chapter" aria-label="Previous chapter" aria-keyshortcuts="Left">
<i class="fa fa-angle-left"></i>
</a>
<a rel="next prefetch" href="../en/fp8_kernel.html" class="nav-chapters next" title="Next chapter" aria-label="Next chapter" aria-keyshortcuts="Right">
<i class="fa fa-angle-right"></i>
</a>
</nav>
</div>
<script>
window.playground_copyable = true;
</script>
<script src="../ace.js"></script>
<script src="../mode-rust.js"></script>
<script src="../editor.js"></script>
<script src="../theme-dawn.js"></script>
<script src="../theme-tomorrow_night.js"></script>
<script src="../elasticlunr.min.js"></script>
<script src="../mark.min.js"></script>
<script src="../searcher.js"></script>
<script src="../clipboard.min.js"></script>
<script src="../highlight.js"></script>
<script src="../book.js"></script>
<!-- Custom JS scripts -->
</div>
</body>
</html>