1427 lines
83 KiB
HTML
1427 lines
83 KiB
HTML
<!DOCTYPE html>
|
||
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
|
||
|
||
<meta charset="utf-8">
|
||
<meta name="generator" content="quarto-1.7.33">
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
|
||
|
||
|
||
<title>Multi-GPU – Axolotl</title>
|
||
<style>
|
||
code{white-space: pre-wrap;}
|
||
span.smallcaps{font-variant: small-caps;}
|
||
div.columns{display: flex; gap: min(4vw, 1.5em);}
|
||
div.column{flex: auto; overflow-x: auto;}
|
||
div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;}
|
||
ul.task-list{list-style: none;}
|
||
ul.task-list li input[type="checkbox"] {
|
||
width: 0.8em;
|
||
margin: 0 0.8em 0.2em -1em; /* quarto-specific, see https://github.com/quarto-dev/quarto-cli/issues/4556 */
|
||
vertical-align: middle;
|
||
}
|
||
/* CSS for syntax highlighting */
|
||
html { -webkit-text-size-adjust: 100%; }
|
||
pre > code.sourceCode { white-space: pre; position: relative; }
|
||
pre > code.sourceCode > span { display: inline-block; line-height: 1.25; }
|
||
pre > code.sourceCode > span:empty { height: 1.2em; }
|
||
.sourceCode { overflow: visible; }
|
||
code.sourceCode > span { color: inherit; text-decoration: inherit; }
|
||
div.sourceCode { margin: 1em 0; }
|
||
pre.sourceCode { margin: 0; }
|
||
@media screen {
|
||
div.sourceCode { overflow: auto; }
|
||
}
|
||
@media print {
|
||
pre > code.sourceCode { white-space: pre-wrap; }
|
||
pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; }
|
||
}
|
||
pre.numberSource code
|
||
{ counter-reset: source-line 0; }
|
||
pre.numberSource code > span
|
||
{ position: relative; left: -4em; counter-increment: source-line; }
|
||
pre.numberSource code > span > a:first-child::before
|
||
{ content: counter(source-line);
|
||
position: relative; left: -1em; text-align: right; vertical-align: baseline;
|
||
border: none; display: inline-block;
|
||
-webkit-touch-callout: none; -webkit-user-select: none;
|
||
-khtml-user-select: none; -moz-user-select: none;
|
||
-ms-user-select: none; user-select: none;
|
||
padding: 0 4px; width: 4em;
|
||
}
|
||
pre.numberSource { margin-left: 3em; padding-left: 4px; }
|
||
div.sourceCode
|
||
{ }
|
||
@media screen {
|
||
pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
|
||
}
|
||
</style>
|
||
|
||
|
||
<script src="../site_libs/quarto-nav/quarto-nav.js"></script>
|
||
<script src="../site_libs/clipboard/clipboard.min.js"></script>
|
||
<script src="../site_libs/quarto-search/autocomplete.umd.js"></script>
|
||
<script src="../site_libs/quarto-search/fuse.min.js"></script>
|
||
<script src="../site_libs/quarto-search/quarto-search.js"></script>
|
||
<meta name="quarto:offset" content="../">
|
||
<link href="../favicon.jpg" rel="icon" type="image/jpeg">
|
||
<script src="../site_libs/quarto-html/quarto.js" type="module"></script>
|
||
<script src="../site_libs/quarto-html/tabsets/tabsets.js" type="module"></script>
|
||
<script src="../site_libs/quarto-html/popper.min.js"></script>
|
||
<script src="../site_libs/quarto-html/tippy.umd.min.js"></script>
|
||
<script src="../site_libs/quarto-html/anchor.min.js"></script>
|
||
<link href="../site_libs/quarto-html/tippy.css" rel="stylesheet">
|
||
<link href="../site_libs/quarto-html/quarto-syntax-highlighting-dark-bc185b5c5bdbcb35c2eb49d8a876ef70.css" rel="stylesheet" id="quarto-text-highlighting-styles">
|
||
<script src="../site_libs/bootstrap/bootstrap.min.js"></script>
|
||
<link href="../site_libs/bootstrap/bootstrap-icons.css" rel="stylesheet">
|
||
<link href="../site_libs/bootstrap/bootstrap-e9895ec3143e9833a687747e8d39d226.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="dark">
|
||
<script id="quarto-search-options" type="application/json">{
|
||
"location": "navbar",
|
||
"copy-button": false,
|
||
"collapse-after": 3,
|
||
"panel-placement": "end",
|
||
"type": "overlay",
|
||
"limit": 50,
|
||
"keyboard-shortcut": [
|
||
"f",
|
||
"/",
|
||
"s"
|
||
],
|
||
"show-item-context": false,
|
||
"language": {
|
||
"search-no-results-text": "No results",
|
||
"search-matching-documents-text": "matching documents",
|
||
"search-copy-link-title": "Copy link to search",
|
||
"search-hide-matches-text": "Hide additional matches",
|
||
"search-more-match-text": "more match in this document",
|
||
"search-more-matches-text": "more matches in this document",
|
||
"search-clear-button-title": "Clear",
|
||
"search-text-placeholder": "",
|
||
"search-detached-cancel-button-title": "Cancel",
|
||
"search-submit-button-title": "Submit",
|
||
"search-label": "Search"
|
||
}
|
||
}</script>
|
||
<script async="" src="https://www.googletagmanager.com/gtag/js?id=G-9KYCVJBNMQ"></script>
|
||
|
||
<script type="text/javascript">
|
||
|
||
window.dataLayer = window.dataLayer || [];
|
||
function gtag(){dataLayer.push(arguments);}
|
||
gtag('js', new Date());
|
||
gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||
</script>
|
||
|
||
|
||
<link rel="stylesheet" href="../styles.css">
|
||
</head>
|
||
|
||
<body class="nav-sidebar docked nav-fixed quarto-light">
|
||
|
||
<div id="quarto-search-results"></div>
|
||
<header id="quarto-header" class="headroom fixed-top">
|
||
<nav class="navbar navbar-expand " data-bs-theme="dark">
|
||
<div class="navbar-container container-fluid">
|
||
<div class="navbar-brand-container mx-auto">
|
||
<a href="../index.html" class="navbar-brand navbar-brand-logo">
|
||
<img src="../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo">
|
||
</a>
|
||
</div>
|
||
<div class="quarto-navbar-tools tools-wide tools-end">
|
||
<a href="https://twitter.com/axolotl_ai" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-twitter"></i></a>
|
||
<a href="https://github.com/axolotl-ai-cloud/axolotl/" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-github"></i></a>
|
||
<a href="https://discord.gg/7m9sfhzaf3" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-discord"></i></a>
|
||
</div>
|
||
<div id="quarto-search" class="" title="Search"></div>
|
||
</div> <!-- /container-fluid -->
|
||
</nav>
|
||
<nav class="quarto-secondary-nav">
|
||
<div class="container-fluid d-flex">
|
||
<button type="button" class="quarto-btn-toggle btn" data-bs-toggle="collapse" role="button" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
|
||
<i class="bi bi-layout-text-sidebar-reverse"></i>
|
||
</button>
|
||
<nav class="quarto-page-breadcrumbs" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item"><a href="../docs/docker.html">Deployments</a></li><li class="breadcrumb-item"><a href="../docs/multi-gpu.html">Multi-GPU</a></li></ol></nav>
|
||
<a class="flex-grow-1" role="navigation" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
|
||
</a>
|
||
</div>
|
||
</nav>
|
||
</header>
|
||
<!-- content -->
|
||
<div id="quarto-content" class="quarto-container page-columns page-rows-contents page-layout-article page-navbar">
|
||
<!-- sidebar -->
|
||
<nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal quarto-sidebar-collapse-item sidebar-navigation docked overflow-auto">
|
||
<div class="sidebar-menu-container">
|
||
<ul class="list-unstyled mt-1">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../index.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Home</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">Getting Started</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-1" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/getting-started.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Quickstart</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/installation.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Installation</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/inference.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Inference and Merging</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/cli.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Command Line Interface (CLI)</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/config-reference.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Config Reference</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/api" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">API Reference</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/dataset-formats/index.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Dataset Formats</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-2" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/dataset-formats/pretraining.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Pre-training</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/dataset-formats/inst_tune.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Instruction Tuning</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/dataset-formats/conversation.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Conversation</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/dataset-formats/stepwise_supervised.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Stepwise Supervised Format</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/dataset-formats/template_free.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Template-Free</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/dataset-formats/tokenized.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Custom Pre-Tokenized Dataset</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">Deployments</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/docker.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Docker</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/multi-gpu.html" class="sidebar-item-text sidebar-link active">
|
||
<span class="menu-text">Multi-GPU</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/multi-node.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Multi Node</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/ray-integration.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Ray Train</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/amd_hpc.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">AMD GPUs on HPC Systems</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/mac.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Mac M-series</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-4" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">How To Guides</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-4" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-4" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/multimodal.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">MultiModal / Vision Language Models (BETA)</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/rlhf.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">RLHF (Beta)</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/reward_modelling.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Reward Modelling</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/lr_groups.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Learning Rate Groups</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/lora_optims.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">LoRA Optimizations</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/dataset_loading.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Dataset Loading</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/qat.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Quantization Aware Training (QAT)</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/quantize.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Quantization with torchao</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-5" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">Core Concepts</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-5" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-5" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/batch_vs_grad.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Batch size vs Gradient accumulation</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/dataset_preprocessing.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Dataset Preprocessing</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/multipack.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Multipack (Sample Packing)</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/mixed_precision.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Mixed Precision Training</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/optimizers.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Optimizers</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-6" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">Advanced Features</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-6" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-6" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">FDSP + QLoRA</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/unsloth.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Unsloth</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/torchao.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">PyTorch ao</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/custom_integrations.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Custom Integrations</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/sequence_parallelism.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Sequence Parallelism</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/gradient_checkpointing.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Gradient Checkpointing and Activation Offloading</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/nd_parallelism.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">N-D Parallelism (Beta)</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="sidebar-item sidebar-item-section">
|
||
<div class="sidebar-item-container">
|
||
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-7" role="navigation" aria-expanded="true">
|
||
<span class="menu-text">Troubleshooting</span></a>
|
||
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-7" role="navigation" aria-expanded="true" aria-label="Toggle section">
|
||
<i class="bi bi-chevron-right ms-2"></i>
|
||
</a>
|
||
</div>
|
||
<ul id="quarto-sidebar-section-7" class="collapse list-unstyled sidebar-section depth1 show">
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/faq.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">FAQ</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/debugging.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Debugging</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../docs/nccl.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">NCCL</span></a>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</div>
|
||
</nav>
|
||
<div id="quarto-sidebar-glass" class="quarto-sidebar-collapse-item" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item"></div>
|
||
<!-- margin-sidebar -->
|
||
<div id="quarto-margin-sidebar" class="sidebar margin-sidebar">
|
||
<nav id="TOC" role="doc-toc" class="toc-active">
|
||
<h2 id="toc-title">On this page</h2>
|
||
|
||
<ul>
|
||
<li><a href="#sec-overview" id="toc-sec-overview" class="nav-link active" data-scroll-target="#sec-overview"><span class="header-section-number">1</span> Overview</a></li>
|
||
<li><a href="#sec-deepspeed" id="toc-sec-deepspeed" class="nav-link" data-scroll-target="#sec-deepspeed"><span class="header-section-number">2</span> DeepSpeed</a>
|
||
<ul class="collapse">
|
||
<li><a href="#sec-deepspeed-config" id="toc-sec-deepspeed-config" class="nav-link" data-scroll-target="#sec-deepspeed-config"><span class="header-section-number">2.1</span> Configuration</a></li>
|
||
<li><a href="#sec-deepspeed-usage" id="toc-sec-deepspeed-usage" class="nav-link" data-scroll-target="#sec-deepspeed-usage"><span class="header-section-number">2.2</span> Usage</a></li>
|
||
<li><a href="#sec-zero-stages" id="toc-sec-zero-stages" class="nav-link" data-scroll-target="#sec-zero-stages"><span class="header-section-number">2.3</span> ZeRO Stages</a></li>
|
||
</ul></li>
|
||
<li><a href="#sec-fsdp" id="toc-sec-fsdp" class="nav-link" data-scroll-target="#sec-fsdp"><span class="header-section-number">3</span> Fully Sharded Data Parallel (FSDP)</a>
|
||
<ul class="collapse">
|
||
<li><a href="#sec-migrate-fsdp1-fsdp2" id="toc-sec-migrate-fsdp1-fsdp2" class="nav-link" data-scroll-target="#sec-migrate-fsdp1-fsdp2"><span class="header-section-number">3.1</span> Migrating from FSDP1 to FSDP2</a></li>
|
||
<li><a href="#sec-fsdp-config" id="toc-sec-fsdp-config" class="nav-link" data-scroll-target="#sec-fsdp-config"><span class="header-section-number">3.2</span> FSDP1 (deprecated)</a></li>
|
||
</ul></li>
|
||
<li><a href="#sec-sequence-parallelism" id="toc-sec-sequence-parallelism" class="nav-link" data-scroll-target="#sec-sequence-parallelism"><span class="header-section-number">4</span> Sequence parallelism</a>
|
||
<ul class="collapse">
|
||
<li><a href="#sec-fsdp-qlora" id="toc-sec-fsdp-qlora" class="nav-link" data-scroll-target="#sec-fsdp-qlora"><span class="header-section-number">4.1</span> FSDP + QLoRA</a></li>
|
||
</ul></li>
|
||
<li><a href="#sec-performance" id="toc-sec-performance" class="nav-link" data-scroll-target="#sec-performance"><span class="header-section-number">5</span> Performance Optimization</a>
|
||
<ul class="collapse">
|
||
<li><a href="#sec-liger" id="toc-sec-liger" class="nav-link" data-scroll-target="#sec-liger"><span class="header-section-number">5.1</span> Liger Kernel Integration</a></li>
|
||
</ul></li>
|
||
<li><a href="#sec-troubleshooting" id="toc-sec-troubleshooting" class="nav-link" data-scroll-target="#sec-troubleshooting"><span class="header-section-number">6</span> Troubleshooting</a>
|
||
<ul class="collapse">
|
||
<li><a href="#sec-nccl" id="toc-sec-nccl" class="nav-link" data-scroll-target="#sec-nccl"><span class="header-section-number">6.1</span> NCCL Issues</a></li>
|
||
<li><a href="#sec-common-problems" id="toc-sec-common-problems" class="nav-link" data-scroll-target="#sec-common-problems"><span class="header-section-number">6.2</span> Common Problems</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
<!-- main -->
|
||
<main class="content" id="quarto-document-content">
|
||
|
||
<header id="title-block-header" class="quarto-title-block default"><nav class="quarto-page-breadcrumbs quarto-title-breadcrumbs d-none d-lg-block" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item"><a href="../docs/docker.html">Deployments</a></li><li class="breadcrumb-item"><a href="../docs/multi-gpu.html">Multi-GPU</a></li></ol></nav>
|
||
<div class="quarto-title">
|
||
<div class="quarto-title-block"><div><h1 class="title">Multi-GPU</h1><button type="button" class="btn code-tools-button" id="quarto-code-tools-source"><i class="bi"></i> Code</button></div></div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="quarto-title-meta">
|
||
|
||
|
||
|
||
|
||
</div>
|
||
|
||
|
||
|
||
</header>
|
||
|
||
|
||
<p>This guide covers advanced training configurations for multi-GPU setups using Axolotl.</p>
|
||
<section id="sec-overview" class="level2" data-number="1">
|
||
<h2 data-number="1" class="anchored" data-anchor-id="sec-overview"><span class="header-section-number">1</span> Overview</h2>
|
||
<p>Axolotl supports several methods for multi-GPU training:</p>
|
||
<ul>
|
||
<li>DeepSpeed (recommended)</li>
|
||
<li>FSDP (Fully Sharded Data Parallel)</li>
|
||
<li>Sequence parallelism</li>
|
||
<li>FSDP + QLoRA</li>
|
||
</ul>
|
||
</section>
|
||
<section id="sec-deepspeed" class="level2" data-number="2">
|
||
<h2 data-number="2" class="anchored" data-anchor-id="sec-deepspeed"><span class="header-section-number">2</span> DeepSpeed</h2>
|
||
<section id="sec-deepspeed-config" class="level3" data-number="2.1">
|
||
<h3 data-number="2.1" class="anchored" data-anchor-id="sec-deepspeed-config"><span class="header-section-number">2.1</span> Configuration</h3>
|
||
<p>Add to your YAML config:</p>
|
||
<div class="sourceCode" id="cb1"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">deepspeed</span><span class="kw">:</span><span class="at"> deepspeed_configs/zero1.json</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="sec-deepspeed-usage" class="level3" data-number="2.2">
|
||
<h3 data-number="2.2" class="anchored" data-anchor-id="sec-deepspeed-usage"><span class="header-section-number">2.2</span> Usage</h3>
|
||
<div class="sourceCode" id="cb2"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Fetch deepspeed configs (if not already present)</span></span>
|
||
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> fetch deepspeed_configs</span>
|
||
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a><span class="co"># Passing arg via config</span></span>
|
||
<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> train config.yml</span>
|
||
<span id="cb2-6"><a href="#cb2-6" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb2-7"><a href="#cb2-7" aria-hidden="true" tabindex="-1"></a><span class="co"># Passing arg via cli</span></span>
|
||
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> train config.yml <span class="at">--deepspeed</span> deepspeed_configs/zero1.json</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
<section id="sec-zero-stages" class="level3" data-number="2.3">
|
||
<h3 data-number="2.3" class="anchored" data-anchor-id="sec-zero-stages"><span class="header-section-number">2.3</span> ZeRO Stages</h3>
|
||
<p>We provide default configurations for:</p>
|
||
<ul>
|
||
<li>ZeRO Stage 1 (<code>zero1.json</code>)</li>
|
||
<li>ZeRO Stage 1 with torch compile (<code>zero1_torch_compile.json</code>)</li>
|
||
<li>ZeRO Stage 2 (<code>zero2.json</code>)</li>
|
||
<li>ZeRO Stage 3 (<code>zero3.json</code>)</li>
|
||
<li>ZeRO Stage 3 with bf16 (<code>zero3_bf16.json</code>)</li>
|
||
<li>ZeRO Stage 3 with bf16 and CPU offload params(<code>zero3_bf16_cpuoffload_params.json</code>)</li>
|
||
<li>ZeRO Stage 3 with bf16 and CPU offload params and optimizer (<code>zero3_bf16_cpuoffload_all.json</code>)</li>
|
||
</ul>
|
||
<div class="callout callout-style-default callout-tip callout-titled">
|
||
<div class="callout-header d-flex align-content-center">
|
||
<div class="callout-icon-container">
|
||
<i class="callout-icon"></i>
|
||
</div>
|
||
<div class="callout-title-container flex-fill">
|
||
Tip
|
||
</div>
|
||
</div>
|
||
<div class="callout-body-container callout-body">
|
||
<p>Choose the configuration that offloads the least amount to memory while still being able to fit on VRAM for best performance.</p>
|
||
<p>Start from Stage 1 -> Stage 2 -> Stage 3.</p>
|
||
</div>
|
||
</div>
|
||
<div class="callout callout-style-default callout-tip callout-titled">
|
||
<div class="callout-header d-flex align-content-center">
|
||
<div class="callout-icon-container">
|
||
<i class="callout-icon"></i>
|
||
</div>
|
||
<div class="callout-title-container flex-fill">
|
||
Tip
|
||
</div>
|
||
</div>
|
||
<div class="callout-body-container callout-body">
|
||
<p>Using ZeRO Stage 3 with Single-GPU training</p>
|
||
<p>ZeRO Stage 3 can be used for training on a single GPU by manually setting the environment variables:
|
||
<code>WORLD_SIZE=1 LOCAL_RANK=0 MASTER_ADDR=0.0.0.0 MASTER_PORT=29500</code></p>
|
||
</div>
|
||
</div>
|
||
</section>
|
||
</section>
|
||
<section id="sec-fsdp" class="level2" data-number="3">
|
||
<h2 data-number="3" class="anchored" data-anchor-id="sec-fsdp"><span class="header-section-number">3</span> Fully Sharded Data Parallel (FSDP)</h2>
|
||
<div class="callout callout-style-default callout-note callout-titled">
|
||
<div class="callout-header d-flex align-content-center">
|
||
<div class="callout-icon-container">
|
||
<i class="callout-icon"></i>
|
||
</div>
|
||
<div class="callout-title-container flex-fill">
|
||
Note
|
||
</div>
|
||
</div>
|
||
<div class="callout-body-container callout-body">
|
||
<p>FSDP2 is recommended for new users. FSDP1 is deprecated and will be removed in an upcoming release of Axolotl.</p>
|
||
</div>
|
||
</div>
|
||
<section id="sec-migrate-fsdp1-fsdp2" class="level3" data-number="3.1">
|
||
<h3 data-number="3.1" class="anchored" data-anchor-id="sec-migrate-fsdp1-fsdp2"><span class="header-section-number">3.1</span> Migrating from FSDP1 to FSDP2</h3>
|
||
<p>To migrate your config from FSDP1 to FSDP2, you must use the <code>fsdp_version</code> top-level config field to specify the FSDP version, and
|
||
also follow the config field mapping below to update field names.</p>
|
||
<section id="config-mapping" class="level4" data-number="3.1.1">
|
||
<h4 data-number="3.1.1" class="anchored" data-anchor-id="config-mapping"><span class="header-section-number">3.1.1</span> Config mapping</h4>
|
||
<table class="caption-top table">
|
||
<thead>
|
||
<tr class="header">
|
||
<th>FSDP1</th>
|
||
<th>FSDP2</th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr class="odd">
|
||
<td>fsdp_sharding_strategy</td>
|
||
<td>reshard_after_forward</td>
|
||
</tr>
|
||
<tr class="even">
|
||
<td>fsdp_backward_prefetch_policy</td>
|
||
<td><strong>REMOVED</strong></td>
|
||
</tr>
|
||
<tr class="odd">
|
||
<td>fsdp_backward_prefetch</td>
|
||
<td><strong>REMOVED</strong></td>
|
||
</tr>
|
||
<tr class="even">
|
||
<td>fsdp_forward_prefetch</td>
|
||
<td><strong>REMOVED</strong></td>
|
||
</tr>
|
||
<tr class="odd">
|
||
<td>fsdp_sync_module_states</td>
|
||
<td><strong>REMOVED</strong></td>
|
||
</tr>
|
||
<tr class="even">
|
||
<td>fsdp_cpu_ram_efficient_loading</td>
|
||
<td>cpu_ram_efficient_loading</td>
|
||
</tr>
|
||
<tr class="odd">
|
||
<td>fsdp_state_dict_type</td>
|
||
<td>state_dict_type</td>
|
||
</tr>
|
||
<tr class="even">
|
||
<td>fsdp_use_orig_params</td>
|
||
<td><strong>REMOVED</strong></td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
<p>For more details, please see the migration guide in the <a href="https://github.com/pytorch/torchtitan/blob/main/docs/fsdp.md">torchtitan repo</a>. In Axolotl,
|
||
if you were using the following FSDP1 config:</p>
|
||
<div class="sourceCode" id="cb3"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_version</span><span class="kw">:</span><span class="at"> </span><span class="dv">1</span></span>
|
||
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</span><span class="kw">:</span></span>
|
||
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_offload_params</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
|
||
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_cpu_ram_efficient_loading</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||
<span id="cb3-5"><a href="#cb3-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_auto_wrap_policy</span><span class="kw">:</span><span class="at"> TRANSFORMER_BASED_WRAP</span></span>
|
||
<span id="cb3-6"><a href="#cb3-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_transformer_layer_cls_to_wrap</span><span class="kw">:</span><span class="at"> Qwen3DecoderLayer</span></span>
|
||
<span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_state_dict_type</span><span class="kw">:</span><span class="at"> FULL_STATE_DICT</span></span>
|
||
<span id="cb3-8"><a href="#cb3-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_sharding_strategy</span><span class="kw">:</span><span class="at"> FULL_SHARD</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
<p>You can migrate to the following FSDP2 config:</p>
|
||
<div class="sourceCode" id="cb4"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_version</span><span class="kw">:</span><span class="at"> </span><span class="dv">2</span></span>
|
||
<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</span><span class="kw">:</span></span>
|
||
<span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">offload_params</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
|
||
<span id="cb4-4"><a href="#cb4-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">cpu_ram_efficient_loading</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||
<span id="cb4-5"><a href="#cb4-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">auto_wrap_policy</span><span class="kw">:</span><span class="at"> TRANSFORMER_BASED_WRAP</span></span>
|
||
<span id="cb4-6"><a href="#cb4-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">transformer_layer_cls_to_wrap</span><span class="kw">:</span><span class="at"> Qwen3DecoderLayer</span></span>
|
||
<span id="cb4-7"><a href="#cb4-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">state_dict_type</span><span class="kw">:</span><span class="at"> FULL_STATE_DICT</span></span>
|
||
<span id="cb4-8"><a href="#cb4-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">reshard_after_forward</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
</section>
|
||
<section id="sec-fsdp-config" class="level3" data-number="3.2">
|
||
<h3 data-number="3.2" class="anchored" data-anchor-id="sec-fsdp-config"><span class="header-section-number">3.2</span> FSDP1 (deprecated)</h3>
|
||
<div class="callout callout-style-default callout-note callout-titled">
|
||
<div class="callout-header d-flex align-content-center">
|
||
<div class="callout-icon-container">
|
||
<i class="callout-icon"></i>
|
||
</div>
|
||
<div class="callout-title-container flex-fill">
|
||
Note
|
||
</div>
|
||
</div>
|
||
<div class="callout-body-container callout-body">
|
||
<p>Using <code>fsdp</code> to configure FSDP is deprecated and will be removed in an upcoming release of Axolotl. Please use <code>fsdp_config</code> as above instead.</p>
|
||
</div>
|
||
</div>
|
||
<div class="sourceCode" id="cb5"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp</span><span class="kw">:</span></span>
|
||
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> full_shard</span></span>
|
||
<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> auto_wrap</span></span>
|
||
<span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</span><span class="kw">:</span></span>
|
||
<span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_offload_params</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||
<span id="cb5-6"><a href="#cb5-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_state_dict_type</span><span class="kw">:</span><span class="at"> FULL_STATE_DICT</span></span>
|
||
<span id="cb5-7"><a href="#cb5-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_transformer_layer_cls_to_wrap</span><span class="kw">:</span><span class="at"> LlamaDecoderLayer</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||
</section>
|
||
</section>
|
||
<section id="sec-sequence-parallelism" class="level2" data-number="4">
|
||
<h2 data-number="4" class="anchored" data-anchor-id="sec-sequence-parallelism"><span class="header-section-number">4</span> Sequence parallelism</h2>
|
||
<p>We support sequence parallelism (SP) via the
|
||
<a href="https://github.com/zhuzilin/ring-flash-attention">ring-flash-attention</a> project. This
|
||
allows one to split up sequences across GPUs, which is useful in the event that a
|
||
single sequence causes OOM errors during model training.</p>
|
||
<p>See our <a href="../docs/sequence_parallelism.html">dedicated guide</a> for more information.</p>
|
||
<section id="sec-fsdp-qlora" class="level3" data-number="4.1">
|
||
<h3 data-number="4.1" class="anchored" data-anchor-id="sec-fsdp-qlora"><span class="header-section-number">4.1</span> FSDP + QLoRA</h3>
|
||
<p>For combining FSDP with QLoRA, see our <a href="../docs/fsdp_qlora.html">dedicated guide</a>.</p>
|
||
</section>
|
||
</section>
|
||
<section id="sec-performance" class="level2" data-number="5">
|
||
<h2 data-number="5" class="anchored" data-anchor-id="sec-performance"><span class="header-section-number">5</span> Performance Optimization</h2>
|
||
<section id="sec-liger" class="level3" data-number="5.1">
|
||
<h3 data-number="5.1" class="anchored" data-anchor-id="sec-liger"><span class="header-section-number">5.1</span> Liger Kernel Integration</h3>
|
||
<p>Please see <a href="../docs/custom_integrations.html#liger">docs</a> for more info.</p>
|
||
</section>
|
||
</section>
|
||
<section id="sec-troubleshooting" class="level2" data-number="6">
|
||
<h2 data-number="6" class="anchored" data-anchor-id="sec-troubleshooting"><span class="header-section-number">6</span> Troubleshooting</h2>
|
||
<section id="sec-nccl" class="level3" data-number="6.1">
|
||
<h3 data-number="6.1" class="anchored" data-anchor-id="sec-nccl"><span class="header-section-number">6.1</span> NCCL Issues</h3>
|
||
<p>For NCCL-related problems, see our <a href="../docs/nccl.html">NCCL troubleshooting guide</a>.</p>
|
||
</section>
|
||
<section id="sec-common-problems" class="level3" data-number="6.2">
|
||
<h3 data-number="6.2" class="anchored" data-anchor-id="sec-common-problems"><span class="header-section-number">6.2</span> Common Problems</h3>
|
||
<div class="tabset-margin-container"></div><div class="panel-tabset">
|
||
<ul class="nav nav-tabs" role="tablist"><li class="nav-item" role="presentation"><a class="nav-link active" id="tabset-1-1-tab" data-bs-toggle="tab" data-bs-target="#tabset-1-1" role="tab" aria-controls="tabset-1-1" aria-selected="true" aria-current="page">Memory Issues</a></li><li class="nav-item" role="presentation"><a class="nav-link" id="tabset-1-2-tab" data-bs-toggle="tab" data-bs-target="#tabset-1-2" role="tab" aria-controls="tabset-1-2" aria-selected="false">Training Instability</a></li></ul>
|
||
<div class="tab-content">
|
||
<div id="tabset-1-1" class="tab-pane active" role="tabpanel" aria-labelledby="tabset-1-1-tab">
|
||
<ul>
|
||
<li>Reduce <code>micro_batch_size</code></li>
|
||
<li>Reduce <code>eval_batch_size</code></li>
|
||
<li>Adjust <code>gradient_accumulation_steps</code></li>
|
||
<li>Consider using a higher ZeRO stage</li>
|
||
</ul>
|
||
</div>
|
||
<div id="tabset-1-2" class="tab-pane" role="tabpanel" aria-labelledby="tabset-1-2-tab">
|
||
<ul>
|
||
<li>Start with DeepSpeed ZeRO-2</li>
|
||
<li>Monitor loss values</li>
|
||
<li>Check learning rates</li>
|
||
</ul>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
<p>For more detailed troubleshooting, see our <a href="../docs/debugging.html">debugging guide</a>.</p>
|
||
|
||
|
||
<!-- -->
|
||
|
||
</section>
|
||
</section>
|
||
|
||
</main> <!-- /main -->
|
||
<script id="quarto-html-after-body" type="application/javascript">
|
||
window.document.addEventListener("DOMContentLoaded", function (event) {
|
||
const icon = "";
|
||
const anchorJS = new window.AnchorJS();
|
||
anchorJS.options = {
|
||
placement: 'right',
|
||
icon: icon
|
||
};
|
||
anchorJS.add('.anchored');
|
||
const isCodeAnnotation = (el) => {
|
||
for (const clz of el.classList) {
|
||
if (clz.startsWith('code-annotation-')) {
|
||
return true;
|
||
}
|
||
}
|
||
return false;
|
||
}
|
||
const onCopySuccess = function(e) {
|
||
// button target
|
||
const button = e.trigger;
|
||
// don't keep focus
|
||
button.blur();
|
||
// flash "checked"
|
||
button.classList.add('code-copy-button-checked');
|
||
var currentTitle = button.getAttribute("title");
|
||
button.setAttribute("title", "Copied!");
|
||
let tooltip;
|
||
if (window.bootstrap) {
|
||
button.setAttribute("data-bs-toggle", "tooltip");
|
||
button.setAttribute("data-bs-placement", "left");
|
||
button.setAttribute("data-bs-title", "Copied!");
|
||
tooltip = new bootstrap.Tooltip(button,
|
||
{ trigger: "manual",
|
||
customClass: "code-copy-button-tooltip",
|
||
offset: [0, -8]});
|
||
tooltip.show();
|
||
}
|
||
setTimeout(function() {
|
||
if (tooltip) {
|
||
tooltip.hide();
|
||
button.removeAttribute("data-bs-title");
|
||
button.removeAttribute("data-bs-toggle");
|
||
button.removeAttribute("data-bs-placement");
|
||
}
|
||
button.setAttribute("title", currentTitle);
|
||
button.classList.remove('code-copy-button-checked');
|
||
}, 1000);
|
||
// clear code selection
|
||
e.clearSelection();
|
||
}
|
||
const getTextToCopy = function(trigger) {
|
||
const codeEl = trigger.previousElementSibling.cloneNode(true);
|
||
for (const childEl of codeEl.children) {
|
||
if (isCodeAnnotation(childEl)) {
|
||
childEl.remove();
|
||
}
|
||
}
|
||
return codeEl.innerText;
|
||
}
|
||
const clipboard = new window.ClipboardJS('.code-copy-button:not([data-in-quarto-modal])', {
|
||
text: getTextToCopy
|
||
});
|
||
clipboard.on('success', onCopySuccess);
|
||
if (window.document.getElementById('quarto-embedded-source-code-modal')) {
|
||
const clipboardModal = new window.ClipboardJS('.code-copy-button[data-in-quarto-modal]', {
|
||
text: getTextToCopy,
|
||
container: window.document.getElementById('quarto-embedded-source-code-modal')
|
||
});
|
||
clipboardModal.on('success', onCopySuccess);
|
||
}
|
||
const viewSource = window.document.getElementById('quarto-view-source') ||
|
||
window.document.getElementById('quarto-code-tools-source');
|
||
if (viewSource) {
|
||
const sourceUrl = viewSource.getAttribute("data-quarto-source-url");
|
||
viewSource.addEventListener("click", function(e) {
|
||
if (sourceUrl) {
|
||
// rstudio viewer pane
|
||
if (/\bcapabilities=\b/.test(window.location)) {
|
||
window.open(sourceUrl);
|
||
} else {
|
||
window.location.href = sourceUrl;
|
||
}
|
||
} else {
|
||
const modal = new bootstrap.Modal(document.getElementById('quarto-embedded-source-code-modal'));
|
||
modal.show();
|
||
}
|
||
return false;
|
||
});
|
||
}
|
||
function toggleCodeHandler(show) {
|
||
return function(e) {
|
||
const detailsSrc = window.document.querySelectorAll(".cell > details > .sourceCode");
|
||
for (let i=0; i<detailsSrc.length; i++) {
|
||
const details = detailsSrc[i].parentElement;
|
||
if (show) {
|
||
details.open = true;
|
||
} else {
|
||
details.removeAttribute("open");
|
||
}
|
||
}
|
||
const cellCodeDivs = window.document.querySelectorAll(".cell > .sourceCode");
|
||
const fromCls = show ? "hidden" : "unhidden";
|
||
const toCls = show ? "unhidden" : "hidden";
|
||
for (let i=0; i<cellCodeDivs.length; i++) {
|
||
const codeDiv = cellCodeDivs[i];
|
||
if (codeDiv.classList.contains(fromCls)) {
|
||
codeDiv.classList.remove(fromCls);
|
||
codeDiv.classList.add(toCls);
|
||
}
|
||
}
|
||
return false;
|
||
}
|
||
}
|
||
const hideAllCode = window.document.getElementById("quarto-hide-all-code");
|
||
if (hideAllCode) {
|
||
hideAllCode.addEventListener("click", toggleCodeHandler(false));
|
||
}
|
||
const showAllCode = window.document.getElementById("quarto-show-all-code");
|
||
if (showAllCode) {
|
||
showAllCode.addEventListener("click", toggleCodeHandler(true));
|
||
}
|
||
var localhostRegex = new RegExp(/^(?:http|https):\/\/localhost\:?[0-9]*\//);
|
||
var mailtoRegex = new RegExp(/^mailto:/);
|
||
var filterRegex = new RegExp("https:\/\/docs\.axolotl\.ai");
|
||
var isInternal = (href) => {
|
||
return filterRegex.test(href) || localhostRegex.test(href) || mailtoRegex.test(href);
|
||
}
|
||
// Inspect non-navigation links and adorn them if external
|
||
var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item):not(.quarto-navigation-tool):not(.about-link)');
|
||
for (var i=0; i<links.length; i++) {
|
||
const link = links[i];
|
||
if (!isInternal(link.href)) {
|
||
// undo the damage that might have been done by quarto-nav.js in the case of
|
||
// links that we want to consider external
|
||
if (link.dataset.originalHref !== undefined) {
|
||
link.href = link.dataset.originalHref;
|
||
}
|
||
}
|
||
}
|
||
function tippyHover(el, contentFn, onTriggerFn, onUntriggerFn) {
|
||
const config = {
|
||
allowHTML: true,
|
||
maxWidth: 500,
|
||
delay: 100,
|
||
arrow: false,
|
||
appendTo: function(el) {
|
||
return el.parentElement;
|
||
},
|
||
interactive: true,
|
||
interactiveBorder: 10,
|
||
theme: 'quarto',
|
||
placement: 'bottom-start',
|
||
};
|
||
if (contentFn) {
|
||
config.content = contentFn;
|
||
}
|
||
if (onTriggerFn) {
|
||
config.onTrigger = onTriggerFn;
|
||
}
|
||
if (onUntriggerFn) {
|
||
config.onUntrigger = onUntriggerFn;
|
||
}
|
||
window.tippy(el, config);
|
||
}
|
||
const noterefs = window.document.querySelectorAll('a[role="doc-noteref"]');
|
||
for (var i=0; i<noterefs.length; i++) {
|
||
const ref = noterefs[i];
|
||
tippyHover(ref, function() {
|
||
// use id or data attribute instead here
|
||
let href = ref.getAttribute('data-footnote-href') || ref.getAttribute('href');
|
||
try { href = new URL(href).hash; } catch {}
|
||
const id = href.replace(/^#\/?/, "");
|
||
const note = window.document.getElementById(id);
|
||
if (note) {
|
||
return note.innerHTML;
|
||
} else {
|
||
return "";
|
||
}
|
||
});
|
||
}
|
||
const xrefs = window.document.querySelectorAll('a.quarto-xref');
|
||
const processXRef = (id, note) => {
|
||
// Strip column container classes
|
||
const stripColumnClz = (el) => {
|
||
el.classList.remove("page-full", "page-columns");
|
||
if (el.children) {
|
||
for (const child of el.children) {
|
||
stripColumnClz(child);
|
||
}
|
||
}
|
||
}
|
||
stripColumnClz(note)
|
||
if (id === null || id.startsWith('sec-')) {
|
||
// Special case sections, only their first couple elements
|
||
const container = document.createElement("div");
|
||
if (note.children && note.children.length > 2) {
|
||
container.appendChild(note.children[0].cloneNode(true));
|
||
for (let i = 1; i < note.children.length; i++) {
|
||
const child = note.children[i];
|
||
if (child.tagName === "P" && child.innerText === "") {
|
||
continue;
|
||
} else {
|
||
container.appendChild(child.cloneNode(true));
|
||
break;
|
||
}
|
||
}
|
||
if (window.Quarto?.typesetMath) {
|
||
window.Quarto.typesetMath(container);
|
||
}
|
||
return container.innerHTML
|
||
} else {
|
||
if (window.Quarto?.typesetMath) {
|
||
window.Quarto.typesetMath(note);
|
||
}
|
||
return note.innerHTML;
|
||
}
|
||
} else {
|
||
// Remove any anchor links if they are present
|
||
const anchorLink = note.querySelector('a.anchorjs-link');
|
||
if (anchorLink) {
|
||
anchorLink.remove();
|
||
}
|
||
if (window.Quarto?.typesetMath) {
|
||
window.Quarto.typesetMath(note);
|
||
}
|
||
if (note.classList.contains("callout")) {
|
||
return note.outerHTML;
|
||
} else {
|
||
return note.innerHTML;
|
||
}
|
||
}
|
||
}
|
||
for (var i=0; i<xrefs.length; i++) {
|
||
const xref = xrefs[i];
|
||
tippyHover(xref, undefined, function(instance) {
|
||
instance.disable();
|
||
let url = xref.getAttribute('href');
|
||
let hash = undefined;
|
||
if (url.startsWith('#')) {
|
||
hash = url;
|
||
} else {
|
||
try { hash = new URL(url).hash; } catch {}
|
||
}
|
||
if (hash) {
|
||
const id = hash.replace(/^#\/?/, "");
|
||
const note = window.document.getElementById(id);
|
||
if (note !== null) {
|
||
try {
|
||
const html = processXRef(id, note.cloneNode(true));
|
||
instance.setContent(html);
|
||
} finally {
|
||
instance.enable();
|
||
instance.show();
|
||
}
|
||
} else {
|
||
// See if we can fetch this
|
||
fetch(url.split('#')[0])
|
||
.then(res => res.text())
|
||
.then(html => {
|
||
const parser = new DOMParser();
|
||
const htmlDoc = parser.parseFromString(html, "text/html");
|
||
const note = htmlDoc.getElementById(id);
|
||
if (note !== null) {
|
||
const html = processXRef(id, note);
|
||
instance.setContent(html);
|
||
}
|
||
}).finally(() => {
|
||
instance.enable();
|
||
instance.show();
|
||
});
|
||
}
|
||
} else {
|
||
// See if we can fetch a full url (with no hash to target)
|
||
// This is a special case and we should probably do some content thinning / targeting
|
||
fetch(url)
|
||
.then(res => res.text())
|
||
.then(html => {
|
||
const parser = new DOMParser();
|
||
const htmlDoc = parser.parseFromString(html, "text/html");
|
||
const note = htmlDoc.querySelector('main.content');
|
||
if (note !== null) {
|
||
// This should only happen for chapter cross references
|
||
// (since there is no id in the URL)
|
||
// remove the first header
|
||
if (note.children.length > 0 && note.children[0].tagName === "HEADER") {
|
||
note.children[0].remove();
|
||
}
|
||
const html = processXRef(null, note);
|
||
instance.setContent(html);
|
||
}
|
||
}).finally(() => {
|
||
instance.enable();
|
||
instance.show();
|
||
});
|
||
}
|
||
}, function(instance) {
|
||
});
|
||
}
|
||
let selectedAnnoteEl;
|
||
const selectorForAnnotation = ( cell, annotation) => {
|
||
let cellAttr = 'data-code-cell="' + cell + '"';
|
||
let lineAttr = 'data-code-annotation="' + annotation + '"';
|
||
const selector = 'span[' + cellAttr + '][' + lineAttr + ']';
|
||
return selector;
|
||
}
|
||
const selectCodeLines = (annoteEl) => {
|
||
const doc = window.document;
|
||
const targetCell = annoteEl.getAttribute("data-target-cell");
|
||
const targetAnnotation = annoteEl.getAttribute("data-target-annotation");
|
||
const annoteSpan = window.document.querySelector(selectorForAnnotation(targetCell, targetAnnotation));
|
||
const lines = annoteSpan.getAttribute("data-code-lines").split(",");
|
||
const lineIds = lines.map((line) => {
|
||
return targetCell + "-" + line;
|
||
})
|
||
let top = null;
|
||
let height = null;
|
||
let parent = null;
|
||
if (lineIds.length > 0) {
|
||
//compute the position of the single el (top and bottom and make a div)
|
||
const el = window.document.getElementById(lineIds[0]);
|
||
top = el.offsetTop;
|
||
height = el.offsetHeight;
|
||
parent = el.parentElement.parentElement;
|
||
if (lineIds.length > 1) {
|
||
const lastEl = window.document.getElementById(lineIds[lineIds.length - 1]);
|
||
const bottom = lastEl.offsetTop + lastEl.offsetHeight;
|
||
height = bottom - top;
|
||
}
|
||
if (top !== null && height !== null && parent !== null) {
|
||
// cook up a div (if necessary) and position it
|
||
let div = window.document.getElementById("code-annotation-line-highlight");
|
||
if (div === null) {
|
||
div = window.document.createElement("div");
|
||
div.setAttribute("id", "code-annotation-line-highlight");
|
||
div.style.position = 'absolute';
|
||
parent.appendChild(div);
|
||
}
|
||
div.style.top = top - 2 + "px";
|
||
div.style.height = height + 4 + "px";
|
||
div.style.left = 0;
|
||
let gutterDiv = window.document.getElementById("code-annotation-line-highlight-gutter");
|
||
if (gutterDiv === null) {
|
||
gutterDiv = window.document.createElement("div");
|
||
gutterDiv.setAttribute("id", "code-annotation-line-highlight-gutter");
|
||
gutterDiv.style.position = 'absolute';
|
||
const codeCell = window.document.getElementById(targetCell);
|
||
const gutter = codeCell.querySelector('.code-annotation-gutter');
|
||
gutter.appendChild(gutterDiv);
|
||
}
|
||
gutterDiv.style.top = top - 2 + "px";
|
||
gutterDiv.style.height = height + 4 + "px";
|
||
}
|
||
selectedAnnoteEl = annoteEl;
|
||
}
|
||
};
|
||
const unselectCodeLines = () => {
|
||
const elementsIds = ["code-annotation-line-highlight", "code-annotation-line-highlight-gutter"];
|
||
elementsIds.forEach((elId) => {
|
||
const div = window.document.getElementById(elId);
|
||
if (div) {
|
||
div.remove();
|
||
}
|
||
});
|
||
selectedAnnoteEl = undefined;
|
||
};
|
||
// Handle positioning of the toggle
|
||
window.addEventListener(
|
||
"resize",
|
||
throttle(() => {
|
||
elRect = undefined;
|
||
if (selectedAnnoteEl) {
|
||
selectCodeLines(selectedAnnoteEl);
|
||
}
|
||
}, 10)
|
||
);
|
||
function throttle(fn, ms) {
|
||
let throttle = false;
|
||
let timer;
|
||
return (...args) => {
|
||
if(!throttle) { // first call gets through
|
||
fn.apply(this, args);
|
||
throttle = true;
|
||
} else { // all the others get throttled
|
||
if(timer) clearTimeout(timer); // cancel #2
|
||
timer = setTimeout(() => {
|
||
fn.apply(this, args);
|
||
timer = throttle = false;
|
||
}, ms);
|
||
}
|
||
};
|
||
}
|
||
// Attach click handler to the DT
|
||
const annoteDls = window.document.querySelectorAll('dt[data-target-cell]');
|
||
for (const annoteDlNode of annoteDls) {
|
||
annoteDlNode.addEventListener('click', (event) => {
|
||
const clickedEl = event.target;
|
||
if (clickedEl !== selectedAnnoteEl) {
|
||
unselectCodeLines();
|
||
const activeEl = window.document.querySelector('dt[data-target-cell].code-annotation-active');
|
||
if (activeEl) {
|
||
activeEl.classList.remove('code-annotation-active');
|
||
}
|
||
selectCodeLines(clickedEl);
|
||
clickedEl.classList.add('code-annotation-active');
|
||
} else {
|
||
// Unselect the line
|
||
unselectCodeLines();
|
||
clickedEl.classList.remove('code-annotation-active');
|
||
}
|
||
});
|
||
}
|
||
const findCites = (el) => {
|
||
const parentEl = el.parentElement;
|
||
if (parentEl) {
|
||
const cites = parentEl.dataset.cites;
|
||
if (cites) {
|
||
return {
|
||
el,
|
||
cites: cites.split(' ')
|
||
};
|
||
} else {
|
||
return findCites(el.parentElement)
|
||
}
|
||
} else {
|
||
return undefined;
|
||
}
|
||
};
|
||
var bibliorefs = window.document.querySelectorAll('a[role="doc-biblioref"]');
|
||
for (var i=0; i<bibliorefs.length; i++) {
|
||
const ref = bibliorefs[i];
|
||
const citeInfo = findCites(ref);
|
||
if (citeInfo) {
|
||
tippyHover(citeInfo.el, function() {
|
||
var popup = window.document.createElement('div');
|
||
citeInfo.cites.forEach(function(cite) {
|
||
var citeDiv = window.document.createElement('div');
|
||
citeDiv.classList.add('hanging-indent');
|
||
citeDiv.classList.add('csl-entry');
|
||
var biblioDiv = window.document.getElementById('ref-' + cite);
|
||
if (biblioDiv) {
|
||
citeDiv.innerHTML = biblioDiv.innerHTML;
|
||
}
|
||
popup.appendChild(citeDiv);
|
||
});
|
||
return popup.innerHTML;
|
||
});
|
||
}
|
||
}
|
||
});
|
||
</script><div class="modal fade" id="quarto-embedded-source-code-modal" tabindex="-1" aria-labelledby="quarto-embedded-source-code-modal-label" aria-hidden="true"><div class="modal-dialog modal-dialog-scrollable"><div class="modal-content"><div class="modal-header"><h5 class="modal-title" id="quarto-embedded-source-code-modal-label">Source Code</h5><button class="btn-close" data-bs-dismiss="modal"></button></div><div class="modal-body"><div class="">
|
||
<div class="sourceCode" id="cb6" data-shortcodes="false"><pre class="sourceCode markdown code-with-copy"><code class="sourceCode markdown"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="co">---</span></span>
|
||
<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a><span class="an">title:</span><span class="co"> "Multi-GPU"</span></span>
|
||
<span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a><span class="an">format:</span></span>
|
||
<span id="cb6-4"><a href="#cb6-4" aria-hidden="true" tabindex="-1"></a><span class="co"> html:</span></span>
|
||
<span id="cb6-5"><a href="#cb6-5" aria-hidden="true" tabindex="-1"></a><span class="co"> toc: true</span></span>
|
||
<span id="cb6-6"><a href="#cb6-6" aria-hidden="true" tabindex="-1"></a><span class="co"> toc-depth: 3</span></span>
|
||
<span id="cb6-7"><a href="#cb6-7" aria-hidden="true" tabindex="-1"></a><span class="co"> number-sections: true</span></span>
|
||
<span id="cb6-8"><a href="#cb6-8" aria-hidden="true" tabindex="-1"></a><span class="co"> code-tools: true</span></span>
|
||
<span id="cb6-9"><a href="#cb6-9" aria-hidden="true" tabindex="-1"></a><span class="an">execute:</span></span>
|
||
<span id="cb6-10"><a href="#cb6-10" aria-hidden="true" tabindex="-1"></a><span class="co"> enabled: false</span></span>
|
||
<span id="cb6-11"><a href="#cb6-11" aria-hidden="true" tabindex="-1"></a><span class="co">---</span></span>
|
||
<span id="cb6-12"><a href="#cb6-12" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-13"><a href="#cb6-13" aria-hidden="true" tabindex="-1"></a>This guide covers advanced training configurations for multi-GPU setups using Axolotl.</span>
|
||
<span id="cb6-14"><a href="#cb6-14" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-15"><a href="#cb6-15" aria-hidden="true" tabindex="-1"></a><span class="fu">## Overview {#sec-overview}</span></span>
|
||
<span id="cb6-16"><a href="#cb6-16" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-17"><a href="#cb6-17" aria-hidden="true" tabindex="-1"></a>Axolotl supports several methods for multi-GPU training:</span>
|
||
<span id="cb6-18"><a href="#cb6-18" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-19"><a href="#cb6-19" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>DeepSpeed (recommended)</span>
|
||
<span id="cb6-20"><a href="#cb6-20" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>FSDP (Fully Sharded Data Parallel)</span>
|
||
<span id="cb6-21"><a href="#cb6-21" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>Sequence parallelism</span>
|
||
<span id="cb6-22"><a href="#cb6-22" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>FSDP + QLoRA</span>
|
||
<span id="cb6-23"><a href="#cb6-23" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-24"><a href="#cb6-24" aria-hidden="true" tabindex="-1"></a><span class="fu">## DeepSpeed {#sec-deepspeed}</span></span>
|
||
<span id="cb6-25"><a href="#cb6-25" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-26"><a href="#cb6-26" aria-hidden="true" tabindex="-1"></a><span class="fu">### Configuration {#sec-deepspeed-config}</span></span>
|
||
<span id="cb6-27"><a href="#cb6-27" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-28"><a href="#cb6-28" aria-hidden="true" tabindex="-1"></a>Add to your YAML config:</span>
|
||
<span id="cb6-29"><a href="#cb6-29" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-30"><a href="#cb6-30" aria-hidden="true" tabindex="-1"></a><span class="in">```{.yaml}</span></span>
|
||
<span id="cb6-31"><a href="#cb6-31" aria-hidden="true" tabindex="-1"></a><span class="fu">deepspeed</span><span class="kw">:</span><span class="at"> deepspeed_configs/zero1.json</span></span>
|
||
<span id="cb6-32"><a href="#cb6-32" aria-hidden="true" tabindex="-1"></a><span class="in">```</span></span>
|
||
<span id="cb6-33"><a href="#cb6-33" aria-hidden="true" tabindex="-1"></a><span class="fu">### Usage {#sec-deepspeed-usage}</span></span>
|
||
<span id="cb6-34"><a href="#cb6-34" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-35"><a href="#cb6-35" aria-hidden="true" tabindex="-1"></a><span class="in">```{.bash}</span></span>
|
||
<span id="cb6-36"><a href="#cb6-36" aria-hidden="true" tabindex="-1"></a><span class="co"># Fetch deepspeed configs (if not already present)</span></span>
|
||
<span id="cb6-37"><a href="#cb6-37" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> fetch deepspeed_configs</span>
|
||
<span id="cb6-38"><a href="#cb6-38" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-39"><a href="#cb6-39" aria-hidden="true" tabindex="-1"></a><span class="co"># Passing arg via config</span></span>
|
||
<span id="cb6-40"><a href="#cb6-40" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> train config.yml</span>
|
||
<span id="cb6-41"><a href="#cb6-41" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-42"><a href="#cb6-42" aria-hidden="true" tabindex="-1"></a><span class="co"># Passing arg via cli</span></span>
|
||
<span id="cb6-43"><a href="#cb6-43" aria-hidden="true" tabindex="-1"></a><span class="ex">axolotl</span> train config.yml <span class="at">--deepspeed</span> deepspeed_configs/zero1.json</span>
|
||
<span id="cb6-44"><a href="#cb6-44" aria-hidden="true" tabindex="-1"></a><span class="in">```</span></span>
|
||
<span id="cb6-45"><a href="#cb6-45" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-46"><a href="#cb6-46" aria-hidden="true" tabindex="-1"></a><span class="fu">### ZeRO Stages {#sec-zero-stages}</span></span>
|
||
<span id="cb6-47"><a href="#cb6-47" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-48"><a href="#cb6-48" aria-hidden="true" tabindex="-1"></a>We provide default configurations for:</span>
|
||
<span id="cb6-49"><a href="#cb6-49" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-50"><a href="#cb6-50" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>ZeRO Stage 1 (<span class="in">`zero1.json`</span>)</span>
|
||
<span id="cb6-51"><a href="#cb6-51" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>ZeRO Stage 1 with torch compile (<span class="in">`zero1_torch_compile.json`</span>)</span>
|
||
<span id="cb6-52"><a href="#cb6-52" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>ZeRO Stage 2 (<span class="in">`zero2.json`</span>)</span>
|
||
<span id="cb6-53"><a href="#cb6-53" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>ZeRO Stage 3 (<span class="in">`zero3.json`</span>)</span>
|
||
<span id="cb6-54"><a href="#cb6-54" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>ZeRO Stage 3 with bf16 (<span class="in">`zero3_bf16.json`</span>)</span>
|
||
<span id="cb6-55"><a href="#cb6-55" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>ZeRO Stage 3 with bf16 and CPU offload params(<span class="in">`zero3_bf16_cpuoffload_params.json`</span>)</span>
|
||
<span id="cb6-56"><a href="#cb6-56" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>ZeRO Stage 3 with bf16 and CPU offload params and optimizer (<span class="in">`zero3_bf16_cpuoffload_all.json`</span>)</span>
|
||
<span id="cb6-57"><a href="#cb6-57" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-58"><a href="#cb6-58" aria-hidden="true" tabindex="-1"></a>::: {.callout-tip}</span>
|
||
<span id="cb6-59"><a href="#cb6-59" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-60"><a href="#cb6-60" aria-hidden="true" tabindex="-1"></a>Choose the configuration that offloads the least amount to memory while still being able to fit on VRAM for best performance.</span>
|
||
<span id="cb6-61"><a href="#cb6-61" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-62"><a href="#cb6-62" aria-hidden="true" tabindex="-1"></a>Start from Stage 1 -> Stage 2 -> Stage 3.</span>
|
||
<span id="cb6-63"><a href="#cb6-63" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-64"><a href="#cb6-64" aria-hidden="true" tabindex="-1"></a>:::</span>
|
||
<span id="cb6-65"><a href="#cb6-65" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-66"><a href="#cb6-66" aria-hidden="true" tabindex="-1"></a>::: {.callout-tip}</span>
|
||
<span id="cb6-67"><a href="#cb6-67" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-68"><a href="#cb6-68" aria-hidden="true" tabindex="-1"></a>Using ZeRO Stage 3 with Single-GPU training</span>
|
||
<span id="cb6-69"><a href="#cb6-69" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-70"><a href="#cb6-70" aria-hidden="true" tabindex="-1"></a>ZeRO Stage 3 can be used for training on a single GPU by manually setting the environment variables:</span>
|
||
<span id="cb6-71"><a href="#cb6-71" aria-hidden="true" tabindex="-1"></a><span class="in">`WORLD_SIZE=1 LOCAL_RANK=0 MASTER_ADDR=0.0.0.0 MASTER_PORT=29500`</span></span>
|
||
<span id="cb6-72"><a href="#cb6-72" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-73"><a href="#cb6-73" aria-hidden="true" tabindex="-1"></a>:::</span>
|
||
<span id="cb6-74"><a href="#cb6-74" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-75"><a href="#cb6-75" aria-hidden="true" tabindex="-1"></a><span class="fu">## Fully Sharded Data Parallel (FSDP) {#sec-fsdp}</span></span>
|
||
<span id="cb6-76"><a href="#cb6-76" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-77"><a href="#cb6-77" aria-hidden="true" tabindex="-1"></a>::: {.callout-note}</span>
|
||
<span id="cb6-78"><a href="#cb6-78" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-79"><a href="#cb6-79" aria-hidden="true" tabindex="-1"></a>FSDP2 is recommended for new users. FSDP1 is deprecated and will be removed in an upcoming release of Axolotl.</span>
|
||
<span id="cb6-80"><a href="#cb6-80" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-81"><a href="#cb6-81" aria-hidden="true" tabindex="-1"></a>:::</span>
|
||
<span id="cb6-82"><a href="#cb6-82" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-83"><a href="#cb6-83" aria-hidden="true" tabindex="-1"></a><span class="fu">### Migrating from FSDP1 to FSDP2 {#sec-migrate-fsdp1-fsdp2}</span></span>
|
||
<span id="cb6-84"><a href="#cb6-84" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-85"><a href="#cb6-85" aria-hidden="true" tabindex="-1"></a>To migrate your config from FSDP1 to FSDP2, you must use the <span class="in">`fsdp_version`</span> top-level config field to specify the FSDP version, and</span>
|
||
<span id="cb6-86"><a href="#cb6-86" aria-hidden="true" tabindex="-1"></a>also follow the config field mapping below to update field names.</span>
|
||
<span id="cb6-87"><a href="#cb6-87" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-88"><a href="#cb6-88" aria-hidden="true" tabindex="-1"></a><span class="fu">#### Config mapping</span></span>
|
||
<span id="cb6-89"><a href="#cb6-89" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-90"><a href="#cb6-90" aria-hidden="true" tabindex="-1"></a>FSDP1 | FSDP2</span>
|
||
<span id="cb6-91"><a href="#cb6-91" aria-hidden="true" tabindex="-1"></a>-------- | --------</span>
|
||
<span id="cb6-92"><a href="#cb6-92" aria-hidden="true" tabindex="-1"></a>fsdp_sharding_strategy | reshard_after_forward</span>
|
||
<span id="cb6-93"><a href="#cb6-93" aria-hidden="true" tabindex="-1"></a>fsdp_backward_prefetch_policy | **REMOVED**</span>
|
||
<span id="cb6-94"><a href="#cb6-94" aria-hidden="true" tabindex="-1"></a>fsdp_backward_prefetch | **REMOVED**</span>
|
||
<span id="cb6-95"><a href="#cb6-95" aria-hidden="true" tabindex="-1"></a>fsdp_forward_prefetch | **REMOVED**</span>
|
||
<span id="cb6-96"><a href="#cb6-96" aria-hidden="true" tabindex="-1"></a>fsdp_sync_module_states | **REMOVED**</span>
|
||
<span id="cb6-97"><a href="#cb6-97" aria-hidden="true" tabindex="-1"></a>fsdp_cpu_ram_efficient_loading | cpu_ram_efficient_loading</span>
|
||
<span id="cb6-98"><a href="#cb6-98" aria-hidden="true" tabindex="-1"></a>fsdp_state_dict_type | state_dict_type</span>
|
||
<span id="cb6-99"><a href="#cb6-99" aria-hidden="true" tabindex="-1"></a>fsdp_use_orig_params | **REMOVED**</span>
|
||
<span id="cb6-100"><a href="#cb6-100" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-101"><a href="#cb6-101" aria-hidden="true" tabindex="-1"></a>For more details, please see the migration guide in the <span class="co">[</span><span class="ot">torchtitan repo</span><span class="co">](https://github.com/pytorch/torchtitan/blob/main/docs/fsdp.md)</span>. In Axolotl,</span>
|
||
<span id="cb6-102"><a href="#cb6-102" aria-hidden="true" tabindex="-1"></a>if you were using the following FSDP1 config:</span>
|
||
<span id="cb6-103"><a href="#cb6-103" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-104"><a href="#cb6-104" aria-hidden="true" tabindex="-1"></a><span class="in">```{.yaml}</span></span>
|
||
<span id="cb6-105"><a href="#cb6-105" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_version</span><span class="kw">:</span><span class="at"> </span><span class="dv">1</span></span>
|
||
<span id="cb6-106"><a href="#cb6-106" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</span><span class="kw">:</span></span>
|
||
<span id="cb6-107"><a href="#cb6-107" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_offload_params</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
|
||
<span id="cb6-108"><a href="#cb6-108" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_cpu_ram_efficient_loading</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||
<span id="cb6-109"><a href="#cb6-109" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_auto_wrap_policy</span><span class="kw">:</span><span class="at"> TRANSFORMER_BASED_WRAP</span></span>
|
||
<span id="cb6-110"><a href="#cb6-110" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_transformer_layer_cls_to_wrap</span><span class="kw">:</span><span class="at"> Qwen3DecoderLayer</span></span>
|
||
<span id="cb6-111"><a href="#cb6-111" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_state_dict_type</span><span class="kw">:</span><span class="at"> FULL_STATE_DICT</span></span>
|
||
<span id="cb6-112"><a href="#cb6-112" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_sharding_strategy</span><span class="kw">:</span><span class="at"> FULL_SHARD</span></span>
|
||
<span id="cb6-113"><a href="#cb6-113" aria-hidden="true" tabindex="-1"></a><span class="in">```</span></span>
|
||
<span id="cb6-114"><a href="#cb6-114" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-115"><a href="#cb6-115" aria-hidden="true" tabindex="-1"></a>You can migrate to the following FSDP2 config:</span>
|
||
<span id="cb6-116"><a href="#cb6-116" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-117"><a href="#cb6-117" aria-hidden="true" tabindex="-1"></a><span class="in">```{.yaml}</span></span>
|
||
<span id="cb6-118"><a href="#cb6-118" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_version</span><span class="kw">:</span><span class="at"> </span><span class="dv">2</span></span>
|
||
<span id="cb6-119"><a href="#cb6-119" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</span><span class="kw">:</span></span>
|
||
<span id="cb6-120"><a href="#cb6-120" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">offload_params</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
|
||
<span id="cb6-121"><a href="#cb6-121" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">cpu_ram_efficient_loading</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||
<span id="cb6-122"><a href="#cb6-122" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">auto_wrap_policy</span><span class="kw">:</span><span class="at"> TRANSFORMER_BASED_WRAP</span></span>
|
||
<span id="cb6-123"><a href="#cb6-123" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">transformer_layer_cls_to_wrap</span><span class="kw">:</span><span class="at"> Qwen3DecoderLayer</span></span>
|
||
<span id="cb6-124"><a href="#cb6-124" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">state_dict_type</span><span class="kw">:</span><span class="at"> FULL_STATE_DICT</span></span>
|
||
<span id="cb6-125"><a href="#cb6-125" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">reshard_after_forward</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||
<span id="cb6-126"><a href="#cb6-126" aria-hidden="true" tabindex="-1"></a><span class="in">```</span></span>
|
||
<span id="cb6-127"><a href="#cb6-127" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-128"><a href="#cb6-128" aria-hidden="true" tabindex="-1"></a><span class="fu">### FSDP1 (deprecated) {#sec-fsdp-config}</span></span>
|
||
<span id="cb6-129"><a href="#cb6-129" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-130"><a href="#cb6-130" aria-hidden="true" tabindex="-1"></a>::: {.callout-note}</span>
|
||
<span id="cb6-131"><a href="#cb6-131" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-132"><a href="#cb6-132" aria-hidden="true" tabindex="-1"></a>Using <span class="in">`fsdp`</span> to configure FSDP is deprecated and will be removed in an upcoming release of Axolotl. Please use <span class="in">`fsdp_config`</span> as above instead.</span>
|
||
<span id="cb6-133"><a href="#cb6-133" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-134"><a href="#cb6-134" aria-hidden="true" tabindex="-1"></a>:::</span>
|
||
<span id="cb6-135"><a href="#cb6-135" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-136"><a href="#cb6-136" aria-hidden="true" tabindex="-1"></a><span class="in">```{.yaml}</span></span>
|
||
<span id="cb6-137"><a href="#cb6-137" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp</span><span class="kw">:</span></span>
|
||
<span id="cb6-138"><a href="#cb6-138" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span>full_shard</span>
|
||
<span id="cb6-139"><a href="#cb6-139" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span>auto_wrap</span>
|
||
<span id="cb6-140"><a href="#cb6-140" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</span><span class="kw">:</span></span>
|
||
<span id="cb6-141"><a href="#cb6-141" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_offload_params</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
|
||
<span id="cb6-142"><a href="#cb6-142" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_state_dict_type</span><span class="kw">:</span><span class="at"> FULL_STATE_DICT</span></span>
|
||
<span id="cb6-143"><a href="#cb6-143" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">fsdp_transformer_layer_cls_to_wrap</span><span class="kw">:</span><span class="at"> LlamaDecoderLayer</span></span>
|
||
<span id="cb6-144"><a href="#cb6-144" aria-hidden="true" tabindex="-1"></a><span class="in">```</span></span>
|
||
<span id="cb6-145"><a href="#cb6-145" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-146"><a href="#cb6-146" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-147"><a href="#cb6-147" aria-hidden="true" tabindex="-1"></a><span class="fu">## Sequence parallelism {#sec-sequence-parallelism}</span></span>
|
||
<span id="cb6-148"><a href="#cb6-148" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-149"><a href="#cb6-149" aria-hidden="true" tabindex="-1"></a>We support sequence parallelism (SP) via the</span>
|
||
<span id="cb6-150"><a href="#cb6-150" aria-hidden="true" tabindex="-1"></a><span class="co">[</span><span class="ot">ring-flash-attention</span><span class="co">](https://github.com/zhuzilin/ring-flash-attention)</span> project. This</span>
|
||
<span id="cb6-151"><a href="#cb6-151" aria-hidden="true" tabindex="-1"></a>allows one to split up sequences across GPUs, which is useful in the event that a</span>
|
||
<span id="cb6-152"><a href="#cb6-152" aria-hidden="true" tabindex="-1"></a>single sequence causes OOM errors during model training.</span>
|
||
<span id="cb6-153"><a href="#cb6-153" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-154"><a href="#cb6-154" aria-hidden="true" tabindex="-1"></a>See our <span class="co">[</span><span class="ot">dedicated guide</span><span class="co">](sequence_parallelism.qmd)</span> for more information.</span>
|
||
<span id="cb6-155"><a href="#cb6-155" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-156"><a href="#cb6-156" aria-hidden="true" tabindex="-1"></a><span class="fu">### FSDP + QLoRA {#sec-fsdp-qlora}</span></span>
|
||
<span id="cb6-157"><a href="#cb6-157" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-158"><a href="#cb6-158" aria-hidden="true" tabindex="-1"></a>For combining FSDP with QLoRA, see our <span class="co">[</span><span class="ot">dedicated guide</span><span class="co">](fsdp_qlora.qmd)</span>.</span>
|
||
<span id="cb6-159"><a href="#cb6-159" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-160"><a href="#cb6-160" aria-hidden="true" tabindex="-1"></a><span class="fu">## Performance Optimization {#sec-performance}</span></span>
|
||
<span id="cb6-161"><a href="#cb6-161" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-162"><a href="#cb6-162" aria-hidden="true" tabindex="-1"></a><span class="fu">### Liger Kernel Integration {#sec-liger}</span></span>
|
||
<span id="cb6-163"><a href="#cb6-163" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-164"><a href="#cb6-164" aria-hidden="true" tabindex="-1"></a>Please see <span class="co">[</span><span class="ot">docs</span><span class="co">](custom_integrations.qmd#liger)</span> for more info.</span>
|
||
<span id="cb6-165"><a href="#cb6-165" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-166"><a href="#cb6-166" aria-hidden="true" tabindex="-1"></a><span class="fu">## Troubleshooting {#sec-troubleshooting}</span></span>
|
||
<span id="cb6-167"><a href="#cb6-167" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-168"><a href="#cb6-168" aria-hidden="true" tabindex="-1"></a><span class="fu">### NCCL Issues {#sec-nccl}</span></span>
|
||
<span id="cb6-169"><a href="#cb6-169" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-170"><a href="#cb6-170" aria-hidden="true" tabindex="-1"></a>For NCCL-related problems, see our <span class="co">[</span><span class="ot">NCCL troubleshooting guide</span><span class="co">](nccl.qmd)</span>.</span>
|
||
<span id="cb6-171"><a href="#cb6-171" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-172"><a href="#cb6-172" aria-hidden="true" tabindex="-1"></a><span class="fu">### Common Problems {#sec-common-problems}</span></span>
|
||
<span id="cb6-173"><a href="#cb6-173" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-174"><a href="#cb6-174" aria-hidden="true" tabindex="-1"></a>::: {.panel-tabset}</span>
|
||
<span id="cb6-175"><a href="#cb6-175" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-176"><a href="#cb6-176" aria-hidden="true" tabindex="-1"></a><span class="fu">## Memory Issues</span></span>
|
||
<span id="cb6-177"><a href="#cb6-177" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-178"><a href="#cb6-178" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>Reduce <span class="in">`micro_batch_size`</span></span>
|
||
<span id="cb6-179"><a href="#cb6-179" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>Reduce <span class="in">`eval_batch_size`</span></span>
|
||
<span id="cb6-180"><a href="#cb6-180" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>Adjust <span class="in">`gradient_accumulation_steps`</span></span>
|
||
<span id="cb6-181"><a href="#cb6-181" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>Consider using a higher ZeRO stage</span>
|
||
<span id="cb6-182"><a href="#cb6-182" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-183"><a href="#cb6-183" aria-hidden="true" tabindex="-1"></a><span class="fu">## Training Instability</span></span>
|
||
<span id="cb6-184"><a href="#cb6-184" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-185"><a href="#cb6-185" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>Start with DeepSpeed ZeRO-2</span>
|
||
<span id="cb6-186"><a href="#cb6-186" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>Monitor loss values</span>
|
||
<span id="cb6-187"><a href="#cb6-187" aria-hidden="true" tabindex="-1"></a><span class="ss">- </span>Check learning rates</span>
|
||
<span id="cb6-188"><a href="#cb6-188" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-189"><a href="#cb6-189" aria-hidden="true" tabindex="-1"></a>:::</span>
|
||
<span id="cb6-190"><a href="#cb6-190" aria-hidden="true" tabindex="-1"></a></span>
|
||
<span id="cb6-191"><a href="#cb6-191" aria-hidden="true" tabindex="-1"></a>For more detailed troubleshooting, see our <span class="co">[</span><span class="ot">debugging guide</span><span class="co">](debugging.qmd)</span>.</span></code><button title="Copy to Clipboard" class="code-copy-button" data-in-quarto-modal=""><i class="bi"></i></button></pre></div>
|
||
</div></div></div></div></div>
|
||
</div> <!-- /content -->
|
||
|
||
|
||
|
||
|
||
</body></html> |