tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Built site for gh-pages

Browse Source
This commit is contained in:
Quarto GHA Workflow Runner
2025-09-16 18:58:53 +00:00
parent db626de56e
commit 421eea620c
209 changed files with 4822 additions and 3261 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
docs/sequence_parallelism.html
View File

@@ -2,7 +2,7 @@
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
<meta charset="utf-8">
<meta name="generator" content="quarto-1.7.34">
<meta name="generator" content="quarto-1.8.24">
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
@@ -68,14 +68,15 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<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/axe/axe-check.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-befe23ebd2f54d8af2c8a89d1a1611f1.css" rel="stylesheet" id="quarto-text-highlighting-styles">
<link href="../site_libs/quarto-html/quarto-syntax-highlighting-dark-b651517ce65839d647a86e2780455cfb.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">
<link href="../site_libs/bootstrap/bootstrap-f9d679a32da2b248d4ca48a0e58e089e.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,
@@ -125,7 +126,8 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
<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">
<img src="../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo light-content">
<img src="../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo dark-content">
</a>
</div>
<div class="quarto-navbar-tools tools-wide tools-end">
@@ -151,6 +153,10 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
<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="pt-lg-2 mt-2 text-left sidebar-header">
<a href="../index.html" class="sidebar-logo-link">
</a>
</div>
<div class="sidebar-menu-container">
<ul class="list-unstyled mt-1">
<li class="sidebar-item">
@@ -552,13 +558,13 @@ through a ring communication pattern.</p>
<section id="configuration" class="level2">
<h2 class="anchored" data-anchor-id="configuration">Configuration</h2>
<p>To enable sequence parallelism, add the following to your configuration file:</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="co"># Set to a divisor (&gt; 1) of the number of GPUs available</span></span>
<div class="code-copy-outer-scaffold"><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="co"># Set to a divisor (&gt; 1) of the number of GPUs available</span></span>
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">context_parallel_size</span><span class="kw">:</span><span class="at"> </span><span class="dv">4</span><span class="co"> # Split sequences across 4 GPUs</span></span>
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional; strides across the key dimension. Larger values use more memory but should make training faster.</span></span>
<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a><span class="fu">heads_k_stride</span><span class="kw">:</span><span class="at"> </span><span class="dv">1</span></span>
<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional; one of "varlen_llama3" or "batch_ring". Defaults to</span></span>
<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a><span class="co"># "varlen_llama3" when `sample_packing: true`, and "batch_ring" otherwise.</span></span>
<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a><span class="fu">ring_attn_func</span><span class="kw">:</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a><span class="fu">ring_attn_func</span><span class="kw">:</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>The <code>context_parallel_size</code> should be a divisor of the total number of GPUs. For example:</p>
<ul>
<li>With 8 GPUs, valid values would be 2, 4, or 8</li>
@@ -596,7 +602,7 @@ through a ring communication pattern.</p>
</section>
<section id="example" class="level2">
<h2 class="anchored" data-anchor-id="example">Example</h2>
<div class="sourceCode" id="cb2"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> meta-llama/Llama-3-8B-Instruct</span></span>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb2"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> meta-llama/Llama-3-8B-Instruct</span></span>
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="fu">sequence_len</span><span class="kw">:</span><span class="at"> </span><span class="dv">8192</span></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">...</span></span>
@@ -608,7 +614,7 @@ through a ring communication pattern.</p>
<span id="cb2-10"><a href="#cb2-10" aria-hidden="true" tabindex="-1"></a><span class="co"># "varlen_llama3" when `sample_packing: true`, and "batch_ring" otherwise.</span></span>
<span id="cb2-11"><a href="#cb2-11" aria-hidden="true" tabindex="-1"></a><span class="co">ring_attn_func:</span></span>
<span id="cb2-12"><a href="#cb2-12" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb2-13"><a href="#cb2-13" aria-hidden="true" tabindex="-1"></a><span class="co">...</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb2-13"><a href="#cb2-13" aria-hidden="true" tabindex="-1"></a><span class="co">...</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>This will train the Llama 3 8B model with 8K context length, with each sequence split
into 2 subsequences of length 4096 across 2 GPUs.</p>
</section>
@@ -688,13 +694,14 @@ into 2 subsequences of length 4096 across 2 GPUs.</p>
e.clearSelection();
}
const getTextToCopy = function(trigger) {
const codeEl = trigger.previousElementSibling.cloneNode(true);
for (const childEl of codeEl.children) {
if (isCodeAnnotation(childEl)) {
childEl.remove();
}
const outerScaffold = trigger.parentElement.cloneNode(true);
const codeEl = outerScaffold.querySelector('code');
for (const childEl of codeEl.children) {
if (isCodeAnnotation(childEl)) {
childEl.remove();
}
return codeEl.innerText;
}
return codeEl.innerText;
}
const clipboard = new window.ClipboardJS('.code-copy-button:not([data-in-quarto-modal])', {
text: getTextToCopy