tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 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

45
docs/mixed_precision.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">
@@ -67,14 +67,15 @@ 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,
@@ -124,7 +125,8 @@ 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">
@@ -150,6 +152,10 @@ 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">
@@ -560,7 +566,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
</section>
<section id="sec-fp16-config" class="level3" data-number="1.2">
<h3 data-number="1.2" class="anchored" data-anchor-id="sec-fp16-config"><span class="header-section-number">1.2</span> Configuration</h3>
<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">fp16</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>
<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="fu">fp16</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
</section>
<section id="sec-fp16-considerations" class="level3" data-number="1.3">
<h3 data-number="1.3" class="anchored" data-anchor-id="sec-fp16-considerations"><span class="header-section-number">1.3</span> FP16 Considerations</h3>
@@ -580,14 +586,14 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
</section>
<section id="sec-bf16-config" class="level3" data-number="2.2">
<h3 data-number="2.2" class="anchored" data-anchor-id="sec-bf16-config"><span class="header-section-number">2.2</span> Configuration</h3>
<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="co"># Automatic BF16 detection (recommended)</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="co"># Automatic BF16 detection (recommended)</span></span>
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="fu">bf16</span><span class="kw">:</span><span class="at"> auto</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"># Or explicitly enable</span></span>
<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a><span class="fu">bf16</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></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"># For evaluation with BF16</span></span>
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a><span class="fu">bf16</span><span class="kw">:</span><span class="at"> full</span><span class="co"> # Equivalent to bf16_full_eval in the HF trainer</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a><span class="fu">bf16</span><span class="kw">:</span><span class="at"> full</span><span class="co"> # Equivalent to bf16_full_eval in the HF trainer</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
</section>
</section>
<section id="sec-fp8" class="level2" data-number="3">
@@ -620,14 +626,14 @@ Note
<section id="sec-fp8-config" class="level3" data-number="3.3">
<h3 data-number="3.3" class="anchored" data-anchor-id="sec-fp8-config"><span class="header-section-number">3.3</span> Configuration</h3>
<p>Add to your YAML 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="co"># Enable FP8 mixed precision</span></span>
<div class="code-copy-outer-scaffold"><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="co"># Enable FP8 mixed precision</span></span>
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a><span class="fu">fp8</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional: Enable FP8 for FSDP all-gather operations</span></span>
<span id="cb3-5"><a href="#cb3-5" aria-hidden="true" tabindex="-1"></a><span class="fu">fp8_enable_fsdp_float8_all_gather</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
<span id="cb3-6"><a href="#cb3-6" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a><span class="co"># Enable torch.compile (almost always necessary for FP8 speedups)</span></span>
<span id="cb3-8"><a href="#cb3-8" aria-hidden="true" tabindex="-1"></a><span class="fu">torch_compile</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>
<span id="cb3-8"><a href="#cb3-8" aria-hidden="true" tabindex="-1"></a><span class="fu">torch_compile</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<div class="callout callout-style-default callout-important callout-titled">
<div class="callout-header d-flex align-content-center">
<div class="callout-icon-container">
@@ -646,7 +652,7 @@ Important
<section id="sec-fp8-advanced" class="level3" data-number="3.4">
<h3 data-number="3.4" class="anchored" data-anchor-id="sec-fp8-advanced"><span class="header-section-number">3.4</span> Advanced FP8 Configs</h3>
<p>For <a href="../docs/multi-gpu.html#sec-fsdp">FSDP</a> (Fully Sharded Data Parallel) training:</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">fp8</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
<div class="code-copy-outer-scaffold"><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">fp8</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a><span class="fu">fp8_enable_fsdp_float8_all_gather</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
<span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb4-4"><a href="#cb4-4" aria-hidden="true" tabindex="-1"></a><span class="fu">torch_compile</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
@@ -659,7 +665,7 @@ Important
<span id="cb4-11"><a href="#cb4-11" 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="cb4-12"><a href="#cb4-12" 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"> LlamaDecoderLayer</span></span>
<span id="cb4-13"><a href="#cb4-13" 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="cb4-14"><a href="#cb4-14" 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>
<span id="cb4-14"><a href="#cb4-14" 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></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
</section>
</section>
<section id="sec-best-practices" class="level2" data-number="4">
@@ -765,13 +771,14 @@ Important
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
@@ -1164,7 +1171,7 @@ Important
}
});
</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="cb5" data-shortcodes="false"><pre class="sourceCode markdown code-with-copy"><code class="sourceCode markdown"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="co">---</span></span>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb5" data-shortcodes="false"><pre class="sourceCode markdown code-with-copy"><code class="sourceCode markdown"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="co">---</span></span>
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a><span class="an">title:</span><span class="co"> "Mixed Precision Training"</span></span>
<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a><span class="an">format:</span></span>
<span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a><span class="co"> html:</span></span>
@@ -1312,7 +1319,7 @@ Important
<span id="cb5-146"><a href="#cb5-146" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb5-147"><a href="#cb5-147" aria-hidden="true" tabindex="-1"></a>See <span class="in">`examples/llama-3/3b-fp8-fsdp2.yaml`</span> for an optimized example config. Enabling FP8 mixed precision + FP8 all-gather training results in ~10% faster iterations per second vs. BF16 for a relatively small (3B param) model</span>
<span id="cb5-148"><a href="#cb5-148" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb5-149"><a href="#cb5-149" aria-hidden="true" tabindex="-1"></a>For more information on multi-GPU training, see our <span class="co">[</span><span class="ot">Multi-GPU guide</span><span class="co">](multi-gpu.qmd)</span>.</span></code><button title="Copy to Clipboard" class="code-copy-button" data-in-quarto-modal=""><i class="bi"></i></button></pre></div>
<span id="cb5-149"><a href="#cb5-149" aria-hidden="true" tabindex="-1"></a>For more information on multi-GPU training, see our <span class="co">[</span><span class="ot">Multi-GPU guide</span><span class="co">](multi-gpu.qmd)</span>.</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button" data-in-quarto-modal=""><i class="bi"></i></button></div>
</div></div></div></div></div>
</div> <!-- /content -->