mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-10-22 17:49:13 +08:00
ovowei
306 lines
15 KiB
HTML
306 lines
15 KiB
HTML
<!DOCTYPE HTML>
|
|
<html lang="zh-CN" class="light sidebar-visible" dir="ltr">
|
|
<head>
|
|
<!-- Book generated using mdBook -->
|
|
<meta charset="UTF-8">
|
|
<title>Use FP8 GPU Kernel - Ktransformers</title>
|
|
|
|
|
|
<!-- Custom HTML head -->
|
|
|
|
<meta name="description" content="">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
<meta name="theme-color" content="#ffffff">
|
|
|
|
<link rel="icon" href="../favicon.svg">
|
|
<link rel="shortcut icon" href="../favicon.png">
|
|
<link rel="stylesheet" href="../css/variables.css">
|
|
<link rel="stylesheet" href="../css/general.css">
|
|
<link rel="stylesheet" href="../css/chrome.css">
|
|
<link rel="stylesheet" href="../css/print.css" media="print">
|
|
|
|
<!-- Fonts -->
|
|
<link rel="stylesheet" href="../FontAwesome/css/font-awesome.css">
|
|
<link rel="stylesheet" href="../fonts/fonts.css">
|
|
|
|
<!-- Highlight.js Stylesheets -->
|
|
<link rel="stylesheet" id="highlight-css" href="../highlight.css">
|
|
<link rel="stylesheet" id="tomorrow-night-css" href="../tomorrow-night.css">
|
|
<link rel="stylesheet" id="ayu-highlight-css" href="../ayu-highlight.css">
|
|
|
|
<!-- Custom theme stylesheets -->
|
|
|
|
|
|
<!-- Provide site root and default themes to javascript -->
|
|
<script>
|
|
const path_to_root = "../";
|
|
const default_light_theme = "light";
|
|
const default_dark_theme = "navy";
|
|
window.path_to_searchindex_js = "../searchindex.js";
|
|
</script>
|
|
<!-- Start loading toc.js asap -->
|
|
<script src="../toc.js"></script>
|
|
</head>
|
|
<body>
|
|
<div id="mdbook-help-container">
|
|
<div id="mdbook-help-popup">
|
|
<h2 class="mdbook-help-title">Keyboard shortcuts</h2>
|
|
<div>
|
|
<p>Press <kbd>←</kbd> or <kbd>→</kbd> to navigate between chapters</p>
|
|
<p>Press <kbd>S</kbd> or <kbd>/</kbd> to search in the book</p>
|
|
<p>Press <kbd>?</kbd> to show this help</p>
|
|
<p>Press <kbd>Esc</kbd> to hide this help</p>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div id="body-container">
|
|
<!-- Work around some values being stored in localStorage wrapped in quotes -->
|
|
<script>
|
|
try {
|
|
let theme = localStorage.getItem('mdbook-theme');
|
|
let sidebar = localStorage.getItem('mdbook-sidebar');
|
|
|
|
if (theme.startsWith('"') && theme.endsWith('"')) {
|
|
localStorage.setItem('mdbook-theme', theme.slice(1, theme.length - 1));
|
|
}
|
|
|
|
if (sidebar.startsWith('"') && sidebar.endsWith('"')) {
|
|
localStorage.setItem('mdbook-sidebar', sidebar.slice(1, sidebar.length - 1));
|
|
}
|
|
} catch (e) { }
|
|
</script>
|
|
|
|
<!-- Set the theme before any content is loaded, prevents flash -->
|
|
<script>
|
|
const default_theme = window.matchMedia("(prefers-color-scheme: dark)").matches ? default_dark_theme : default_light_theme;
|
|
let theme;
|
|
try { theme = localStorage.getItem('mdbook-theme'); } catch(e) { }
|
|
if (theme === null || theme === undefined) { theme = default_theme; }
|
|
const html = document.documentElement;
|
|
html.classList.remove('light')
|
|
html.classList.add(theme);
|
|
html.classList.add("js");
|
|
</script>
|
|
|
|
<input type="checkbox" id="sidebar-toggle-anchor" class="hidden">
|
|
|
|
<!-- Hide / unhide sidebar before it is displayed -->
|
|
<script>
|
|
let sidebar = null;
|
|
const sidebar_toggle = document.getElementById("sidebar-toggle-anchor");
|
|
if (document.body.clientWidth >= 1080) {
|
|
try { sidebar = localStorage.getItem('mdbook-sidebar'); } catch(e) { }
|
|
sidebar = sidebar || 'visible';
|
|
} else {
|
|
sidebar = 'hidden';
|
|
sidebar_toggle.checked = false;
|
|
}
|
|
if (sidebar === 'visible') {
|
|
sidebar_toggle.checked = true;
|
|
} else {
|
|
html.classList.remove('sidebar-visible');
|
|
}
|
|
</script>
|
|
|
|
<nav id="sidebar" class="sidebar" aria-label="Table of contents">
|
|
<!-- populated by js -->
|
|
<mdbook-sidebar-scrollbox class="sidebar-scrollbox"></mdbook-sidebar-scrollbox>
|
|
<noscript>
|
|
<iframe class="sidebar-iframe-outer" src="../toc.html"></iframe>
|
|
</noscript>
|
|
<div id="sidebar-resize-handle" class="sidebar-resize-handle">
|
|
<div class="sidebar-resize-indicator"></div>
|
|
</div>
|
|
</nav>
|
|
|
|
<div id="page-wrapper" class="page-wrapper">
|
|
|
|
<div class="page">
|
|
<div id="menu-bar-hover-placeholder"></div>
|
|
<div id="menu-bar" class="menu-bar sticky">
|
|
<div class="left-buttons">
|
|
<label id="sidebar-toggle" class="icon-button" for="sidebar-toggle-anchor" title="Toggle Table of Contents" aria-label="Toggle Table of Contents" aria-controls="sidebar">
|
|
<i class="fa fa-bars"></i>
|
|
</label>
|
|
<button id="theme-toggle" class="icon-button" type="button" title="Change theme" aria-label="Change theme" aria-haspopup="true" aria-expanded="false" aria-controls="theme-list">
|
|
<i class="fa fa-paint-brush"></i>
|
|
</button>
|
|
<ul id="theme-list" class="theme-popup" aria-label="Themes" role="menu">
|
|
<li role="none"><button role="menuitem" class="theme" id="default_theme">Auto</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="light">Light</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="rust">Rust</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="coal">Coal</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="navy">Navy</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="ayu">Ayu</button></li>
|
|
</ul>
|
|
<button id="search-toggle" class="icon-button" type="button" title="Search (`/`)" aria-label="Toggle Searchbar" aria-expanded="false" aria-keyshortcuts="/ s" aria-controls="searchbar">
|
|
<i class="fa fa-search"></i>
|
|
</button>
|
|
</div>
|
|
|
|
<h1 class="menu-title">Ktransformers</h1>
|
|
|
|
<div class="right-buttons">
|
|
<a href="../print.html" title="Print this book" aria-label="Print this book">
|
|
<i id="print-button" class="fa fa-print"></i>
|
|
</a>
|
|
<a href="https://github.com/kvcache-ai/ktransformers" title="Git repository" aria-label="Git repository">
|
|
<i id="git-repository-button" class="fa fa-github"></i>
|
|
</a>
|
|
<a href="https://github.com/kvcache-ai/ktransformers/edit/main/doc/en/fp8_kernel.md" title="Suggest an edit" aria-label="Suggest an edit" rel="edit">
|
|
<i id="git-edit-button" class="fa fa-edit"></i>
|
|
</a>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
<div id="search-wrapper" class="hidden">
|
|
<form id="searchbar-outer" class="searchbar-outer">
|
|
<div class="search-wrapper">
|
|
<input type="search" id="searchbar" name="searchbar" placeholder="Search this book ..." aria-controls="searchresults-outer" aria-describedby="searchresults-header">
|
|
<div class="spinner-wrapper">
|
|
<i class="fa fa-spinner fa-spin"></i>
|
|
</div>
|
|
</div>
|
|
</form>
|
|
<div id="searchresults-outer" class="searchresults-outer hidden">
|
|
<div id="searchresults-header" class="searchresults-header"></div>
|
|
<ul id="searchresults">
|
|
</ul>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Apply ARIA attributes after the sidebar and the sidebar toggle button are added to the DOM -->
|
|
<script>
|
|
document.getElementById('sidebar-toggle').setAttribute('aria-expanded', sidebar === 'visible');
|
|
document.getElementById('sidebar').setAttribute('aria-hidden', sidebar !== 'visible');
|
|
Array.from(document.querySelectorAll('#sidebar a')).forEach(function(link) {
|
|
link.setAttribute('tabIndex', sidebar === 'visible' ? 0 : -1);
|
|
});
|
|
</script>
|
|
|
|
<div id="content" class="content">
|
|
<main>
|
|
<h1 id="fp8-linear-kernel-for-deepseek-v3r1"><a class="header" href="#fp8-linear-kernel-for-deepseek-v3r1">FP8 Linear Kernel for DeepSeek-V3/R1</a></h1>
|
|
<h2 id="overview"><a class="header" href="#overview">Overview</a></h2>
|
|
<p>The DeepSeek-AI team provides FP8 safetensors for DeepSeek-R1/V3 models. We achieve performance optimization through the following works:</p>
|
|
<ul>
|
|
<li><strong>FP8 GPU Kernel Integration</strong>: FP8 linear layer acceleration kernels integrated in KTransformers</li>
|
|
<li><strong>Hybrid Quantization Architecture</strong>:
|
|
<ul>
|
|
<li>Attention and Shared-Expert modules use FP8 precision (enhances computational accuracy)</li>
|
|
<li>Experts modules retain GGML quantization (GGUF format, reside in CPU to save GPU memory)</li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
<p>So those who are persuing the best performance can use the FP8 linear kernel for DeepSeek-V3/R1.</p>
|
|
<h2 id="key-features"><a class="header" href="#key-features">Key Features</a></h2>
|
|
<p>✅ Hybrid Precision Architecture (FP8 + GGML)<br>
|
|
✅ Memory Optimization (~19GB VRAM usage)</p>
|
|
<h2 id="quick-start"><a class="header" href="#quick-start">Quick Start</a></h2>
|
|
<h3 id="using-pre-merged-weights"><a class="header" href="#using-pre-merged-weights">Using Pre-Merged Weights</a></h3>
|
|
<p>Pre-merged weights are available on Hugging Face:<br>
|
|
<a href="https://huggingface.co/KVCache-ai/DeepSeek-V3">KVCache-ai/DeepSeek-V3-GGML-FP8-Hybrid</a><br>
|
|
<a href="https://huggingface.co/KVCache-ai/DeepSeek-R1">KVCache-ai/DeepSeek-R1-GGML-FP8-Hybrid</a></p>
|
|
<blockquote>
|
|
<p>Please confirm the weights are fully uploaded before downloading. The large file size may extend Hugging Face upload time.</p>
|
|
</blockquote>
|
|
<p>Download Pre-Merged Weights</p>
|
|
<pre><code class="language-shell">pip install -U huggingface_hub
|
|
|
|
# Optional: Use HF Mirror for faster downloads in special area.
|
|
# export HF_ENDPOINT=https://hf-mirror.com
|
|
|
|
huggingface-cli download --resume-download KVCache-ai/DeepSeek-V3-GGML-FP8-Hybrid --local-dir <local_dir>
|
|
</code></pre>
|
|
<h3 id="using-merge-scripts"><a class="header" href="#using-merge-scripts">Using merge scripts</a></h3>
|
|
<p>If you got local DeepSeek-R1/V3 fp8 safetensors and gguf weights(eg.q4km), you can merge them using the following scripts.</p>
|
|
<pre><code class="language-shell">python merge_tensors/merge_safetensor_gguf.py \
|
|
--safetensor_path <fp8_safetensor_path> \
|
|
--gguf_path <gguf_folder_path> \
|
|
--output_path <merged_output_path>
|
|
</code></pre>
|
|
<ul>
|
|
<li><code>--safetensor_path</code>: input path of safetensor file(<a href="https://huggingface.co/deepseek-ai/DeepSeek-V3/tree/main">Download</a>).</li>
|
|
<li><code>--gguf_path</code>: input path of gguf folder (<a href="https://huggingface.co/unsloth/DeepSeek-V3-GGUF/tree/main/DeepSeek-V3-Q4_K_M">Download</a>).</li>
|
|
<li><code>--output_path</code>: output path of merged file.</li>
|
|
</ul>
|
|
<h3 id="execution-notes"><a class="header" href="#execution-notes">Execution Notes</a></h3>
|
|
<p>Launch local_chat.py with custom quantized experts</p>
|
|
<pre><code class="language-shell">python ktransformers/local_chat.py \
|
|
--model_path deepseek-ai/DeepSeek-V3 \
|
|
--gguf_path <merged_weights_folder> \
|
|
--optimize_config_path ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat-fp8-linear-ggml-experts.yaml \
|
|
--cpu_infer <cpu_cores + 1>
|
|
</code></pre>
|
|
<h2 id="notes"><a class="header" href="#notes">Notes</a></h2>
|
|
<p>⚠️ Hardware Requirements<br></p>
|
|
<ul>
|
|
<li>Recommended minimum 19GB available VRAM for FP8 kernel.</li>
|
|
<li>Requires GPU with FP8 support (e.g., 4090)</li>
|
|
</ul>
|
|
<p>⏳ First-Run Optimization
|
|
JIT compilation causes longer initial execution (subsequent runs retain optimized speed).</p>
|
|
<p>🔄 Temporary Interface<br>
|
|
Current weight loading implementation is provisional - will be refined in future versions</p>
|
|
<p>📁 Path Specification<br>
|
|
Despite hybrid quantization, merged weights are stored as .safetensors - pass the containing folder path to <code>--gguf_path</code></p>
|
|
|
|
</main>
|
|
|
|
<nav class="nav-wrapper" aria-label="Page navigation">
|
|
<!-- Mobile navigation buttons -->
|
|
<a rel="prev" href="../en/multi-gpu-tutorial.html" class="mobile-nav-chapters previous" title="Previous chapter" aria-label="Previous chapter" aria-keyshortcuts="Left">
|
|
<i class="fa fa-angle-left"></i>
|
|
</a>
|
|
|
|
<a rel="next prefetch" href="../en/ROCm.html" class="mobile-nav-chapters next" title="Next chapter" aria-label="Next chapter" aria-keyshortcuts="Right">
|
|
<i class="fa fa-angle-right"></i>
|
|
</a>
|
|
|
|
<div style="clear: both"></div>
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
|
|
<nav class="nav-wide-wrapper" aria-label="Page navigation">
|
|
<a rel="prev" href="../en/multi-gpu-tutorial.html" class="nav-chapters previous" title="Previous chapter" aria-label="Previous chapter" aria-keyshortcuts="Left">
|
|
<i class="fa fa-angle-left"></i>
|
|
</a>
|
|
|
|
<a rel="next prefetch" href="../en/ROCm.html" class="nav-chapters next" title="Next chapter" aria-label="Next chapter" aria-keyshortcuts="Right">
|
|
<i class="fa fa-angle-right"></i>
|
|
</a>
|
|
</nav>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<script>
|
|
window.playground_copyable = true;
|
|
</script>
|
|
|
|
<script src="../ace.js"></script>
|
|
<script src="../mode-rust.js"></script>
|
|
<script src="../editor.js"></script>
|
|
<script src="../theme-dawn.js"></script>
|
|
<script src="../theme-tomorrow_night.js"></script>
|
|
|
|
<script src="../elasticlunr.min.js"></script>
|
|
<script src="../mark.min.js"></script>
|
|
<script src="../searcher.js"></script>
|
|
|
|
<script src="../clipboard.min.js"></script>
|
|
<script src="../highlight.js"></script>
|
|
<script src="../book.js"></script>
|
|
|
|
<!-- Custom JS scripts -->
|
|
|
|
|
|
|
|
</div>
|
|
</body>
|
|
</html>
|