mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
5e2cf02f46
update docs for 0.20.0rc2 Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
874 lines
43 KiB
HTML
874 lines
43 KiB
HTML
|
||
|
||
<!DOCTYPE html>
|
||
|
||
|
||
<html lang="en" data-content_root="../" >
|
||
|
||
<head>
|
||
<meta charset="utf-8" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||
|
||
<title>Speed up inference with SOTA quantization techniques in TRT-LLM — TensorRT-LLM</title>
|
||
|
||
|
||
|
||
<script data-cfasync="false">
|
||
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
|
||
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
|
||
</script>
|
||
<!--
|
||
this give us a css class that will be invisible only if js is disabled
|
||
-->
|
||
<noscript>
|
||
<style>
|
||
.pst-js-only { display: none !important; }
|
||
|
||
</style>
|
||
</noscript>
|
||
|
||
<!-- Loaded before other Sphinx assets -->
|
||
<link href="../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
|
||
<link href="../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
|
||
|
||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=8f2a1f02" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/styles/nvidia-sphinx-theme.css?v=df3ac72c" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/copybutton.css?v=76b2166b" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/autodoc_pydantic.css" />
|
||
|
||
<!-- So that users can add custom icons -->
|
||
<script src="../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script>
|
||
<!-- Pre-loaded scripts that we'll load fully later -->
|
||
<link rel="preload" as="script" href="../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" />
|
||
<link rel="preload" as="script" href="../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" />
|
||
|
||
<script src="../_static/documentation_options.js?v=5929fcd5"></script>
|
||
<script src="../_static/doctools.js?v=9a2dae69"></script>
|
||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||
<script src="../_static/clipboard.min.js?v=a7894cd8"></script>
|
||
<script src="../_static/copybutton.js?v=65e89d2a"></script>
|
||
<script>DOCUMENTATION_OPTIONS.pagename = 'blogs/quantization-in-TRT-LLM';</script>
|
||
<script>
|
||
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '0.20.0rc2';
|
||
DOCUMENTATION_OPTIONS.show_version_warning_banner =
|
||
false;
|
||
</script>
|
||
<link rel="icon" href="../_static/favicon.png"/>
|
||
<link rel="index" title="Index" href="../genindex.html" />
|
||
<link rel="search" title="Search" href="../search.html" />
|
||
<link rel="next" title="New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget" href="XQA-kernel.html" />
|
||
<link rel="prev" title="Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100" href="Falcon180B-H200.html" />
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
||
<meta name="docsearch:language" content="en"/>
|
||
<meta name="docsearch:version" content="0.20.0rc2" />
|
||
|
||
|
||
</head>
|
||
|
||
|
||
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
|
||
|
||
|
||
|
||
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
|
||
|
||
<div id="pst-scroll-pixel-helper"></div>
|
||
|
||
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
|
||
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
|
||
|
||
|
||
<dialog id="pst-search-dialog">
|
||
|
||
<form class="bd-search d-flex align-items-center"
|
||
action="../search.html"
|
||
method="get">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<input type="search"
|
||
class="form-control"
|
||
name="q"
|
||
placeholder="Search the docs ..."
|
||
aria-label="Search the docs ..."
|
||
autocomplete="off"
|
||
autocorrect="off"
|
||
autocapitalize="off"
|
||
spellcheck="false"/>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
|
||
</form>
|
||
</dialog>
|
||
|
||
<div class="pst-async-banner-revealer d-none">
|
||
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
|
||
</div>
|
||
|
||
|
||
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
|
||
<div class="bd-header__inner bd-page-width">
|
||
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
|
||
<span class="fa-solid fa-bars"></span>
|
||
</button>
|
||
|
||
|
||
<div class="col-lg-3 navbar-header-items__start">
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
|
||
|
||
|
||
<a class="navbar-brand logo" href="../index.html">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<img src="../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
|
||
<img src="../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
|
||
|
||
|
||
<p class="title logo__title">TensorRT-LLM</p>
|
||
|
||
</a></div>
|
||
|
||
</div>
|
||
|
||
<div class="col-lg-9 navbar-header-items">
|
||
|
||
<div class="me-auto navbar-header-items__center">
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
<div class="version-switcher__container dropdown pst-js-only">
|
||
<button id="pst-version-switcher-button-2"
|
||
type="button"
|
||
class="version-switcher__button btn btn-sm dropdown-toggle"
|
||
data-bs-toggle="dropdown"
|
||
aria-haspopup="listbox"
|
||
aria-controls="pst-version-switcher-list-2"
|
||
aria-label="Version switcher list"
|
||
>
|
||
Choose version <!-- this text may get changed later by javascript -->
|
||
<span class="caret"></span>
|
||
</button>
|
||
<div id="pst-version-switcher-list-2"
|
||
class="version-switcher__menu dropdown-menu list-group-flush py-0"
|
||
role="listbox" aria-labelledby="pst-version-switcher-button-2">
|
||
<!-- dropdown will be populated by javascript on page load -->
|
||
</div>
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="navbar-header-items__end">
|
||
|
||
<div class="navbar-item navbar-persistent--container">
|
||
|
||
|
||
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
</div>
|
||
|
||
|
||
<div class="navbar-item">
|
||
|
||
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
||
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
||
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
||
</button></div>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="navbar-persistent--mobile">
|
||
|
||
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
</div>
|
||
|
||
|
||
|
||
<button class="pst-navbar-icon sidebar-toggle secondary-toggle" aria-label="On this page">
|
||
<span class="fa-solid fa-outdent"></span>
|
||
</button>
|
||
|
||
</div>
|
||
|
||
</header>
|
||
|
||
|
||
<div class="bd-container">
|
||
<div class="bd-container__inner bd-page-width">
|
||
|
||
|
||
|
||
<dialog id="pst-primary-sidebar-modal"></dialog>
|
||
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<a class="navbar-brand logo" href="../index.html">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<img src="../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
|
||
<img src="../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
|
||
|
||
|
||
<p class="title logo__title">TensorRT-LLM</p>
|
||
|
||
</a>
|
||
|
||
|
||
|
||
<div class="sidebar-header-items sidebar-primary__section">
|
||
|
||
|
||
<div class="sidebar-header-items__center">
|
||
|
||
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
<div class="version-switcher__container dropdown pst-js-only">
|
||
<button id="pst-version-switcher-button-3"
|
||
type="button"
|
||
class="version-switcher__button btn btn-sm dropdown-toggle"
|
||
data-bs-toggle="dropdown"
|
||
aria-haspopup="listbox"
|
||
aria-controls="pst-version-switcher-list-3"
|
||
aria-label="Version switcher list"
|
||
>
|
||
Choose version <!-- this text may get changed later by javascript -->
|
||
<span class="caret"></span>
|
||
</button>
|
||
<div id="pst-version-switcher-list-3"
|
||
class="version-switcher__menu dropdown-menu list-group-flush py-0"
|
||
role="listbox" aria-labelledby="pst-version-switcher-button-3">
|
||
<!-- dropdown will be populated by javascript on page load -->
|
||
</div>
|
||
</div></div>
|
||
|
||
|
||
</div>
|
||
|
||
|
||
|
||
<div class="sidebar-header-items__end">
|
||
|
||
<div class="navbar-item">
|
||
|
||
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
||
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
||
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
||
</button></div>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
|
||
<div class="sidebar-primary-items__start sidebar-primary__section">
|
||
<div class="sidebar-primary-item">
|
||
|
||
|
||
|
||
<nav class="bd-docs-nav bd-links"
|
||
aria-label="Table of Contents">
|
||
<p class="bd-links__title" role="heading" aria-level="1">Table of Contents</p>
|
||
<div class="bd-toc-item navbar-nav"><p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../overview.html">Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../quick-start-guide.html">Quick Start Guide</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../key-features.html">Key Features</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../torch.html">PyTorch Backend</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../release-notes.html">Release Notes</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Installation</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../installation/linux.html">Installing on Linux</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../installation/grace-hopper.html">Installing on Grace Hopper</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">LLM API</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../llm-api/index.html">API Introduction</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../llm-api/reference.html">API Reference</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Examples</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../examples/index.html">LLM Examples Introduction</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_async.html">Generate Text Asynchronously</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_kv_events.html">Get KV Cache Events</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_customize.html">Generate text with customization</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_logits_processor.html">Control generated text using logits processor</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_quantization.html">Generation with Quantization</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference.html">Generate text</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_async_streaming.html">Generate Text in Streaming</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_eagle_decoding.html">Generate Text Using Eagle Decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
|
||
</ul>
|
||
</details></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../examples/customization.html">LLM Common Customizations</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../examples/llm_api_examples.html">LLM Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_async.html">Generate Text Asynchronously</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_kv_events.html">Get KV Cache Events</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_customize.html">Generate text with customization</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_logits_processor.html">Control generated text using logits processor</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_quantization.html">Generation with Quantization</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference.html">Generate text</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_async_streaming.html">Generate Text in Streaming</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_eagle_decoding.html">Generate Text Using Eagle Decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
|
||
</ul>
|
||
</details></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../examples/trtllm_serve_examples.html">Online Serving Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/curl_chat_client.html">Curl Chat Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/curl_completion_client.html">Curl Completion Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/genai_perf_client.html">Genai Perf Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_chat_client.html">OpenAI Chat Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_chat_client_for_multimodal.html">OpenAI Chat Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Model Definition API</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.layers.html">Layers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.functional.html">Functionals</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.models.html">Models</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.plugin.html">Plugin</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.quantization.html">Quantization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.runtime.html">Runtime</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">C++ API</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../_cpp_gen/executor.html">Executor</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../_cpp_gen/runtime.html">Runtime</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-build.html">trtllm-build</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-serve.html">trtllm-serve</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Architecture</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../architecture/overview.html">TensorRT-LLM Architecture</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../architecture/core-concepts.html">Model Definition</a></li>
|
||
|
||
|
||
|
||
<li class="toctree-l1"><a class="reference internal" href="../architecture/checkpoint.html">TensorRT-LLM Checkpoint</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../architecture/workflow.html">TensorRT-LLM Build Workflow</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../architecture/add-model.html">Adding a Model</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Advanced</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../advanced/gpt-attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../advanced/gpt-runtime.html">C++ GPT Runtime</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../advanced/executor.html">Executor API</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../advanced/graph-rewriting.html">Graph Rewriting Module</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../advanced/lora.html">Run gpt-2b + LoRA using Executor / cpp runtime</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../advanced/expert-parallelism.html">Expert Parallelism in TensorRT-LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../advanced/kv-cache-reuse.html">KV cache reuse</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../advanced/speculative-decoding.html">Speculative Sampling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../advanced/disaggregated-service.html">Disaggregated-Service (experimental)</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Performance</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../performance/perf-overview.html">Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../performance/perf-benchmarking.html">Benchmarking</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../performance/performance-tuning-guide/index.html">Performance Tuning Guide</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/benchmarking-default-performance.html">Benchmarking Default Performance</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/useful-build-time-flags.html">Useful Build-Time Flags</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.html">Tuning Max Batch Size and Max Num Tokens</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/deciding-model-sharding-strategy.html">Deciding Model Sharding Strategy</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/fp8-quantization.html">FP8 Quantization</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/useful-runtime-flags.html">Useful Runtime Options</a></li>
|
||
</ul>
|
||
</details></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../performance/perf-analysis.html">Performance Analysis</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../reference/troubleshooting.html">Troubleshooting</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../reference/support-matrix.html">Support Matrix</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../reference/precision.html">Numerical Precision</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../reference/memory.html">Memory Usage of TensorRT-LLM</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
|
||
<ul class="current nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="Falcon180B-H200.html">Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100</a></li>
|
||
<li class="toctree-l1 current active"><a class="current reference internal" href="#">Speed up inference with SOTA quantization techniques in TRT-LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
|
||
</ul>
|
||
</div>
|
||
</nav></div>
|
||
</div>
|
||
|
||
|
||
<div class="sidebar-primary-items__end sidebar-primary__section">
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
<main id="main-content" class="bd-main" role="main">
|
||
|
||
|
||
<div class="bd-content">
|
||
<div class="bd-article-container">
|
||
|
||
<div class="bd-header-article d-print-none">
|
||
<div class="header-article-items header-article__inner">
|
||
|
||
<div class="header-article-items__start">
|
||
|
||
<div class="header-article-item">
|
||
|
||
<nav aria-label="Breadcrumb" class="d-print-none">
|
||
<ul class="bd-breadcrumbs">
|
||
|
||
<li class="breadcrumb-item breadcrumb-home">
|
||
<a href="../index.html" class="nav-link" aria-label="Home">
|
||
<i class="fa-solid fa-home"></i>
|
||
</a>
|
||
</li>
|
||
<li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">Speed up inference with SOTA quantization techniques in TRT-LLM</span></li>
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<div id="searchbox"></div>
|
||
<article class="bd-article">
|
||
|
||
<section id="speed-up-inference-with-sota-quantization-techniques-in-trt-llm">
|
||
<h1>Speed up inference with SOTA quantization techniques in TRT-LLM<a class="headerlink" href="#speed-up-inference-with-sota-quantization-techniques-in-trt-llm" title="Link to this heading">#</a></h1>
|
||
<p>The deployment and inference speed of LLMs are often impeded by limitations in memory capacity, memory bandwidth, and computation power. Quantization emerges as a vital strategy to address these bottlenecks, involving representing weights and activations with lower-precision data types like <a class="reference external" href="https://www.nvidia.com/en-us/on-demand/session/gtcspring23-s52166/">FP8</a>.</p>
|
||
<p>In this blog, we provide an overview of the quantization features in TensorRT-LLM, share benchmark, and offer best practices of selecting the appropriate quantization methods tailored to your specific use case.</p>
|
||
<section id="quantization-in-tensorrt-llm">
|
||
<h2>Quantization in TensorRT-LLM<a class="headerlink" href="#quantization-in-tensorrt-llm" title="Link to this heading">#</a></h2>
|
||
<p>TensorRT-LLM offers a best-in-class unified quantization toolkit to significantly speedup DL/GenAI deployment on NVIDIA hardware, while maintaining model accuracy. This toolkit is designed with easy-of-use in mind. You can follow <a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/quantization">this user guide</a> to quantize <a class="reference internal" href="../reference/support-matrix.html#models"><span class="std std-ref">supported LLMs</span></a> with a few lines of codes. We currently focus on providing SOTA <strong>Post-Training Quantization (PTQ)</strong> and will soon expand to more model optimization techniques in the near future.</p>
|
||
</section>
|
||
<section id="benchmark">
|
||
<h2>Benchmark<a class="headerlink" href="#benchmark" title="Link to this heading">#</a></h2>
|
||
<section id="performance">
|
||
<h3>Performance<a class="headerlink" href="#performance" title="Link to this heading">#</a></h3>
|
||
<p>In the following benchmark, we highlight the acceleration of a few popular models at a small batch size without imposing latency constraints. It’s important to note that in scenarios where there’s a latency constraint in your application, TRT-LLM can achieve an even greater performance improvement. Using LLaMA-v2-7B as an example, when the first token latency is constrained to be under 500ms, quantization with FP8 and a batch size of 16 achieves a notable <strong>2.3x inference speedup</strong> compared to FP16 on a H100.</p>
|
||
<div class="pst-scrollable-table-container"><table class="table">
|
||
<thead>
|
||
<tr class="row-odd"><th class="head"><p>Model</p></th>
|
||
<th class="head text-center"><p>Batch Size</p></th>
|
||
<th class="head text-center"><p>Speedup (FP8 v.s. FP16)</p></th>
|
||
<th class="head text-center"><p>Speedup (INT8 SQ v.s. FP16)</p></th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr class="row-even"><td><p>GPT-J</p></td>
|
||
<td class="text-center"><p>1</p></td>
|
||
<td class="text-center"><p>1.40x</p></td>
|
||
<td class="text-center"><p>1.40x</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>GPT-J</p></td>
|
||
<td class="text-center"><p>8</p></td>
|
||
<td class="text-center"><p>1.44x</p></td>
|
||
<td class="text-center"><p>1.30x</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>LLaMA-v2-7B</p></td>
|
||
<td class="text-center"><p>1</p></td>
|
||
<td class="text-center"><p>1.51x</p></td>
|
||
<td class="text-center"><p>1.47x</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>LLaMA-v2-7B</p></td>
|
||
<td class="text-center"><p>8</p></td>
|
||
<td class="text-center"><p>1.40x</p></td>
|
||
<td class="text-center"><p>1.32x</p></td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</div>
|
||
<p>*The above benchmarks were run with Input Length=1024, Output Length=128, and TP=1 on H100 80GB.</p>
|
||
</section>
|
||
<section id="accuracy">
|
||
<h3>Accuracy<a class="headerlink" href="#accuracy" title="Link to this heading">#</a></h3>
|
||
<div class="pst-scrollable-table-container"><table class="table">
|
||
<thead>
|
||
<tr class="row-odd"><th class="head"><p>Model</p></th>
|
||
<th class="head text-center"><p>Quantization Methods</p></th>
|
||
<th class="head text-center"><p>MMLU Baseline (FP16)</p></th>
|
||
<th class="head text-center"><p>MMLU Post-quantization</p></th>
|
||
<th class="head text-center"><p>MMLU Loss</p></th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr class="row-even"><td><p>Falcon-180B</p></td>
|
||
<td class="text-center"><p>FP8</p></td>
|
||
<td class="text-center"><p>70.4</p></td>
|
||
<td class="text-center"><p>70.3</p></td>
|
||
<td class="text-center"><p>0.14%</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p></p></td>
|
||
<td class="text-center"><p>INT8-SQ</p></td>
|
||
<td class="text-center"><p>70.4</p></td>
|
||
<td class="text-center"><p>68.6</p></td>
|
||
<td class="text-center"><p>2.56%</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p></p></td>
|
||
<td class="text-center"><p>INT4-AWQ</p></td>
|
||
<td class="text-center"><p>70.4</p></td>
|
||
<td class="text-center"><p>69.8</p></td>
|
||
<td class="text-center"><p>0.85%</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>Falcon-40B</p></td>
|
||
<td class="text-center"><p>FP8</p></td>
|
||
<td class="text-center"><p>56.1</p></td>
|
||
<td class="text-center"><p>55.6</p></td>
|
||
<td class="text-center"><p>0.89%</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p></p></td>
|
||
<td class="text-center"><p>INT8-SQ</p></td>
|
||
<td class="text-center"><p>56.1</p></td>
|
||
<td class="text-center"><p>54.7</p></td>
|
||
<td class="text-center"><p>2.50%</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p></p></td>
|
||
<td class="text-center"><p>INT4-AWQ</p></td>
|
||
<td class="text-center"><p>56.1</p></td>
|
||
<td class="text-center"><p>55.5</p></td>
|
||
<td class="text-center"><p>1.07%</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>LLaMA-v2-70B</p></td>
|
||
<td class="text-center"><p>FP8</p></td>
|
||
<td class="text-center"><p>69.1</p></td>
|
||
<td class="text-center"><p>68.5</p></td>
|
||
<td class="text-center"><p>0.87%</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p></p></td>
|
||
<td class="text-center"><p>INT8-SQ</p></td>
|
||
<td class="text-center"><p>69.1</p></td>
|
||
<td class="text-center"><p>67.2</p></td>
|
||
<td class="text-center"><p>2.75%</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p></p></td>
|
||
<td class="text-center"><p>INT4-AWQ</p></td>
|
||
<td class="text-center"><p>69.1</p></td>
|
||
<td class="text-center"><p>68.4</p></td>
|
||
<td class="text-center"><p>1.01%</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>MPT-30B</p></td>
|
||
<td class="text-center"><p>FP8</p></td>
|
||
<td class="text-center"><p>47.5</p></td>
|
||
<td class="text-center"><p>47.4</p></td>
|
||
<td class="text-center"><p>0.21%</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p></p></td>
|
||
<td class="text-center"><p>INT8-SQ</p></td>
|
||
<td class="text-center"><p>47.5</p></td>
|
||
<td class="text-center"><p>46.8</p></td>
|
||
<td class="text-center"><p>1.47%</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p></p></td>
|
||
<td class="text-center"><p>INT4-AWQ</p></td>
|
||
<td class="text-center"><p>47.5</p></td>
|
||
<td class="text-center"><p>46.5</p></td>
|
||
<td class="text-center"><p>2.11%</p></td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</div>
|
||
</section>
|
||
</section>
|
||
<section id="best-practices-to-choose-the-right-quantization-methods">
|
||
<h2>Best practices to choose the right quantization methods<a class="headerlink" href="#best-practices-to-choose-the-right-quantization-methods" title="Link to this heading">#</a></h2>
|
||
<p>A quantization method comprises three primary components:</p>
|
||
<ol class="arabic simple">
|
||
<li><p>Weight precision format</p></li>
|
||
<li><p>Activation precision format</p></li>
|
||
<li><p>Calibration algorithms</p></li>
|
||
</ol>
|
||
<p>Typically, in the context of small-batch inference scenarios (batch size ≤ 4), the key consideration is memory bandwidth, making weight-only quantization methods the preferred choice. Conversely, for large-batch inference scenarios, such as serving scenarios (batch size ≥ 16), both memory bandwidth and computation density become crucial factors. Consequently, it’s recommended to opt for a quantization method that has both weight and activation quantized. For batch size ≥ 16, the choice of quantization method can be model specific. We suggest to prioritize using FP8 first, as we typically see it offers the best performance and accuracy. If the results do not meet your specific use case, you can further experiment with Int8 SmoothQuant (Int8 SQ) followed by AWQ and/or GPTQ.</p>
|
||
<p>Based on specific use cases, users might have different tolerances on accuracy impact and calibration time. The table below summarizes the tradeoffs* to consider when choosing a quantization method. You can also learn more about precision formats in our <a class="reference external" href="https://nvidia.github.io/TensorRT-LLM/reference/precision.html">documentation</a>.</p>
|
||
<div class="pst-scrollable-table-container"><table class="table">
|
||
<thead>
|
||
<tr class="row-odd"><th class="head text-left"><p>Quantization Methods</p></th>
|
||
<th class="head text-center"><p>Performance Improvement (batch size <= 4)</p></th>
|
||
<th class="head text-center"><p>Performance Improvement (batch size >= 16)</p></th>
|
||
<th class="head text-center"><p>Accuracy Impact</p></th>
|
||
<th class="head text-center"><p>Calibration Time**</p></th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr class="row-even"><td class="text-left"><p>FP8 (W8A8)</p></td>
|
||
<td class="text-center"><p>Medium</p></td>
|
||
<td class="text-center"><p>Medium</p></td>
|
||
<td class="text-center"><p>Very Low</p></td>
|
||
<td class="text-center"><p>Minutes</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td class="text-left"><p>Int8 SQ (W8A8)</p></td>
|
||
<td class="text-center"><p>Medium</p></td>
|
||
<td class="text-center"><p>Medium</p></td>
|
||
<td class="text-center"><p>Medium</p></td>
|
||
<td class="text-center"><p>Minutes</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td class="text-left"><p>Int8 weight-only (W8A16)</p></td>
|
||
<td class="text-center"><p>Medium</p></td>
|
||
<td class="text-center"><p>Low</p></td>
|
||
<td class="text-center"><p>Low</p></td>
|
||
<td class="text-center"><p>Not Required</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td class="text-left"><p>Int4 weight-only (W4A16)</p></td>
|
||
<td class="text-center"><p>High</p></td>
|
||
<td class="text-center"><p>Low</p></td>
|
||
<td class="text-center"><p>High</p></td>
|
||
<td class="text-center"><p>Not Required</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td class="text-left"><p>Int4 AWQ (W4A16)</p></td>
|
||
<td class="text-center"><p>High</p></td>
|
||
<td class="text-center"><p>Low</p></td>
|
||
<td class="text-center"><p>Low</p></td>
|
||
<td class="text-center"><p>Tens of Minutes</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td class="text-left"><p>Int4 GPTQ</p></td>
|
||
<td class="text-center"><p>High</p></td>
|
||
<td class="text-center"><p>Low</p></td>
|
||
<td class="text-center"><p>Low</p></td>
|
||
<td class="text-center"><p>Tens of Minutes</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td class="text-left"><p>Int4-FP8 AWQ (W4A8)</p></td>
|
||
<td class="text-center"><p>High</p></td>
|
||
<td class="text-center"><p>Medium</p></td>
|
||
<td class="text-center"><p>Low</p></td>
|
||
<td class="text-center"><p>Tens of Minutes</p></td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</div>
|
||
<p>* The performance and impact are measured on 10+ popular LLMs. We’ll follow up with more data points.
|
||
** Calibration time is subject to the actual model size.</p>
|
||
<p>We note that TensorRT-LLM also offers INT8 and FP8 quantization for KV cache. KV cache differs from normal activation because it occupies non-negligible persistent memory under scenarios like large batch sizes or long context lengths. If you’re using KV cache on Hopper & Ada GPUs, We recommend using FP8 KV cache over Int8 because the former has a lower accuracy impact than the latter in most tested cases. When switching from FP16 KV cache to FP8 KV cache, it also enables you to run 2-3x larger batch size on H100 machine for models like GPT-J which further brings about 1.5x performance benefit.</p>
|
||
</section>
|
||
<section id="whats-coming-next">
|
||
<h2>What’s coming next<a class="headerlink" href="#whats-coming-next" title="Link to this heading">#</a></h2>
|
||
<p>TensorRT-LLM continues to make improvements on our quantization features, such as Int4-FP8 AWQ (W4A8) public examples and more model supports. Please stay tuned for our upcoming releases.</p>
|
||
</section>
|
||
</section>
|
||
|
||
|
||
</article>
|
||
|
||
|
||
|
||
|
||
|
||
<footer class="prev-next-footer d-print-none">
|
||
|
||
<div class="prev-next-area">
|
||
<a class="left-prev"
|
||
href="Falcon180B-H200.html"
|
||
title="previous page">
|
||
<i class="fa-solid fa-angle-left"></i>
|
||
<div class="prev-next-info">
|
||
<p class="prev-next-subtitle">previous</p>
|
||
<p class="prev-next-title">Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100</p>
|
||
</div>
|
||
</a>
|
||
<a class="right-next"
|
||
href="XQA-kernel.html"
|
||
title="next page">
|
||
<div class="prev-next-info">
|
||
<p class="prev-next-subtitle">next</p>
|
||
<p class="prev-next-title">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</p>
|
||
</div>
|
||
<i class="fa-solid fa-angle-right"></i>
|
||
</a>
|
||
</div>
|
||
</footer>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
|
||
|
||
<dialog id="pst-secondary-sidebar-modal"></dialog>
|
||
<div id="pst-secondary-sidebar" class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
|
||
|
||
|
||
<div class="sidebar-secondary-item">
|
||
<div
|
||
id="pst-page-navigation-heading-2"
|
||
class="page-toc tocsection onthispage">
|
||
<i class="fa-solid fa-list"></i> On this page
|
||
</div>
|
||
<nav class="bd-toc-nav page-toc" aria-labelledby="pst-page-navigation-heading-2">
|
||
<ul class="visible nav section-nav flex-column">
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#quantization-in-tensorrt-llm">Quantization in TensorRT-LLM</a></li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#benchmark">Benchmark</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#performance">Performance</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#accuracy">Accuracy</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#best-practices-to-choose-the-right-quantization-methods">Best practices to choose the right quantization methods</a></li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#whats-coming-next">What’s coming next</a></li>
|
||
</ul>
|
||
</nav></div>
|
||
|
||
</div></div>
|
||
|
||
|
||
|
||
</div>
|
||
<footer class="bd-footer-content">
|
||
|
||
</footer>
|
||
|
||
</main>
|
||
</div>
|
||
</div>
|
||
|
||
<!-- Scripts loaded after <body> so the DOM is not blocked -->
|
||
<script defer src="../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf"></script>
|
||
<script defer src="../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf"></script>
|
||
|
||
<footer class="bd-footer">
|
||
<div class="bd-footer__inner bd-page-width">
|
||
|
||
<div class="footer-items__start">
|
||
|
||
<div class="footer-item">
|
||
<a class="footer-brand logo" href="https://www.nvidia.com">
|
||
<img src="../_static/nvidia-logo-horiz-rgb-1c-blk-for-screen.svg" class="logo__image only-light" alt="NVIDIA"/>
|
||
<img src="../_static/nvidia-logo-horiz-rgb-1c-wht-for-screen.svg" class="logo__image only-dark" alt="NVIDIA"/>
|
||
</a></div>
|
||
|
||
<div class="footer-item">
|
||
|
||
<div class="footer-links">
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/">Privacy Policy</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-center/">Manage My Privacy</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/preferences/start/">Do Not Sell or Share My Data</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/terms-of-service/">Terms of Service</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/accessibility/">Accessibility</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/company-policies/">Corporate Policies</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/product-security/">Product Security</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/contact/">Contact</a>
|
||
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
<div class="footer-item">
|
||
|
||
|
||
|
||
|
||
<p class="copyright">
|
||
|
||
Copyright © 2025, NVidia.
|
||
<br/>
|
||
|
||
</p>
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
</footer>
|
||
</body>
|
||
</html> |