TensorRT-LLMs/index.html
Shi Xiaowei 3c4ef52e61
Update GitHub pages to v0.18.2 (#3624)
Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
2025-04-16 18:17:04 +08:00

824 lines
50 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!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>Welcome to TensorRT-LLMs Documentation! &#8212; 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" />
<!-- 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 = 'index';</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="Overview" href="overview.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="" />
</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="#">
<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="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="#">
<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__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">LLM API Examples</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1 has-children"><a class="reference internal" href="llm-api-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="llm-api-examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_inference_async.html">Generate Text Asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_inference_async_streaming.html">Generate Text in Streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_logits_processor.html">Control generated text using logits post processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_quantization.html">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_inference_customize.html">Generate text with customization</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="llm-api-examples/customization.html">Common Customizations</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="llm-api-examples/llm_api_examples.html">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="llm-api-examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_inference_async.html">Generate Text Asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_inference_async_streaming.html">Generate Text in Streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_logits_processor.html">Control generated text using logits post processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_quantization.html">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_inference_customize.html">Generate text with customization</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm-api-examples/llm_auto_parallel.html">Automatic Parallelism with LLM</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/inference-request.html">Inference Request</a></li>
<li class="toctree-l1"><a class="reference internal" href="advanced/lora.html">Run gpt-2b + LoRA using GptManager / 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="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="blogs/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="blogs/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="blogs/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"><a class="reference internal" href="blogs/quantization-in-TRT-LLM.html">Speed up inference with SOTA quantization techniques in TRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="blogs/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>
<div id="searchbox"></div>
<article class="bd-article">
<section id="welcome-to-tensorrt-llm-s-documentation">
<h1>Welcome to TensorRT-LLMs Documentation!<a class="headerlink" href="#welcome-to-tensorrt-llm-s-documentation" title="Link to this heading">#</a></h1>
<div class="toctree-wrapper compound" id="getting-started">
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="overview.html">Overview</a><ul>
<li class="toctree-l2"><a class="reference internal" href="overview.html#about-tensorrt-llm">About TensorRT-LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="overview.html#what-can-you-do-with-tensorrt-llm">What Can You Do With TensorRT-LLM?</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="quick-start-guide.html">Quick Start Guide</a><ul>
<li class="toctree-l2"><a class="reference internal" href="quick-start-guide.html#prerequisites">Prerequisites</a></li>
<li class="toctree-l2"><a class="reference internal" href="quick-start-guide.html#llm-api">LLM API</a></li>
<li class="toctree-l2"><a class="reference internal" href="quick-start-guide.html#compile-the-model-into-a-tensorrt-engine">Compile the Model into a TensorRT Engine</a></li>
<li class="toctree-l2"><a class="reference internal" href="quick-start-guide.html#run-the-model">Run the Model</a></li>
<li class="toctree-l2"><a class="reference internal" href="quick-start-guide.html#deploy-with-triton-inference-server">Deploy with Triton Inference Server</a></li>
<li class="toctree-l2"><a class="reference internal" href="quick-start-guide.html#next-steps">Next Steps</a></li>
<li class="toctree-l2"><a class="reference internal" href="quick-start-guide.html#related-information">Related Information</a></li>
</ul>
</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><ul>
<li class="toctree-l2"><a class="reference internal" href="torch.html#quick-start">Quick Start</a></li>
<li class="toctree-l2"><a class="reference internal" href="torch.html#quantization">Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="torch.html#developer-guide">Developer Guide</a></li>
<li class="toctree-l2"><a class="reference internal" href="torch.html#key-components">Key Components</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="release-notes.html">Release Notes</a><ul>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-18-2">TensorRT-LLM Release 0.18.2</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-18-1">TensorRT-LLM Release 0.18.1</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-18-0">TensorRT-LLM Release 0.18.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-17-0">TensorRT-LLM Release 0.17.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-16-0">TensorRT-LLM Release 0.16.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-15-0">TensorRT-LLM Release 0.15.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-14-0">TensorRT-LLM Release 0.14.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-13-0">TensorRT-LLM Release 0.13.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-12-0">TensorRT-LLM Release 0.12.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-11-0">TensorRT-LLM Release 0.11.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-10-0">TensorRT-LLM Release 0.10.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-9-0">TensorRT-LLM Release 0.9.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-8-0">TensorRT-LLM Release 0.8.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-7-1">TensorRT-LLM Release 0.7.1</a></li>
</ul>
</li>
</ul>
</div>
<div class="toctree-wrapper compound" id="installation">
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Installation</span></p>
<ul>
<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><ul>
<li class="toctree-l2"><a class="reference internal" href="installation/build-from-source-linux.html#prerequisites">Prerequisites</a></li>
<li class="toctree-l2"><a class="reference internal" href="installation/build-from-source-linux.html#building-a-tensorrt-llm-docker-image">Building a TensorRT-LLM Docker Image</a></li>
<li class="toctree-l2"><a class="reference internal" href="installation/build-from-source-linux.html#building-the-python-bindings-for-the-c-runtime">Building the Python Bindings for the C++ Runtime</a></li>
<li class="toctree-l2"><a class="reference internal" href="installation/build-from-source-linux.html#linking-with-the-tensorrt-llm-c-runtime">Linking with the TensorRT-LLM C++ Runtime</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="installation/grace-hopper.html">Installing on Grace Hopper</a></li>
</ul>
</div>
<div class="toctree-wrapper compound">
</div>
<div class="toctree-wrapper compound">
</div>
<div class="toctree-wrapper compound">
</div>
<div class="toctree-wrapper compound">
</div>
<div class="toctree-wrapper compound">
</div>
<div class="toctree-wrapper compound" id="architecture">
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Architecture</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="architecture/overview.html">TensorRT-LLM Architecture</a><ul>
<li class="toctree-l2"><a class="reference internal" href="architecture/overview.html#model-weights">Model Weights</a></li>
</ul>
</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/core-concepts.html#compilation">Compilation</a><ul>
<li class="toctree-l2"><a class="reference internal" href="architecture/core-concepts.html#tensorrt-compiler">TensorRT Compiler</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/core-concepts.html#model-engine">Model Engine</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/core-concepts.html#weight-bindings">Weight Bindings</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/core-concepts.html#pattern-matching-and-fusion">Pattern-Matching and Fusion</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/core-concepts.html#plugins">Plugins</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="architecture/core-concepts.html#runtime">Runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="architecture/core-concepts.html#multi-gpu-and-multi-node-support">Multi-GPU and Multi-Node Support</a><ul>
<li class="toctree-l2"><a class="reference internal" href="architecture/core-concepts.html#examples">Examples</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="architecture/checkpoint.html">TensorRT-LLM Checkpoint</a><ul>
<li class="toctree-l2"><a class="reference internal" href="architecture/checkpoint.html#overview">Overview</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/checkpoint.html#prepare-the-tensorrt-llm-checkpoint">Prepare the TensorRT-LLM Checkpoint</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/checkpoint.html#build-checkpoint-into-tensorrt-engine">Build Checkpoint into TensorRT Engine</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/checkpoint.html#make-evaluation">Make Evaluation</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="architecture/workflow.html">TensorRT-LLM Build Workflow</a><ul>
<li class="toctree-l2"><a class="reference internal" href="architecture/workflow.html#overview">Overview</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/workflow.html#conversion-apis">Conversion APIs</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/workflow.html#quantization-apis">Quantization APIs</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/workflow.html#build-apis">Build APIs</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/workflow.html#cli-tools">CLI Tools</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="architecture/add-model.html">Adding a Model</a><ul>
<li class="toctree-l2"><a class="reference internal" href="architecture/add-model.html#step-1-write-modeling-part">Step 1. Write Modeling Part</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/add-model.html#step-2-implement-weight-conversion">Step 2. Implement Weight Conversion</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/add-model.html#step-3-register-new-model">Step 3. Register New Model</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/add-model.html#step-4-verify-new-model">Step 4. Verify New Model</a></li>
<li class="toctree-l2"><a class="reference internal" href="architecture/add-model.html#reference">Reference</a></li>
</ul>
</li>
</ul>
</div>
<div class="toctree-wrapper compound" id="advanced">
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Advanced</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="advanced/gpt-attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a><ul>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-attention.html#important-note">Important Note</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-attention.html#padded-and-packed-tensors">Padded and Packed Tensors</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-attention.html#context-and-generation-phases">Context and Generation Phases</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-attention.html#in-flight-batching">In-flight Batching</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-attention.html#chunked-context">Chunked Context</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-attention.html#kv-cache">KV Cache</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-attention.html#int8-fp8-kv-caches">INT8/FP8 KV Caches</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-attention.html#sliding-window-attention-cyclic-rolling-buffer-kv-cache">Sliding Window Attention, Cyclic (Rolling Buffer) KV Cache</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-attention.html#streamingllm">StreamingLLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-attention.html#beam-search">Beam-Search</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-attention.html#input-qkv-tensor">Input QKV tensor</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="advanced/gpt-runtime.html">C++ GPT Runtime</a><ul>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-runtime.html#overview">Overview</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-runtime.html#the-session">The Session</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-runtime.html#in-flight-batching-support">In-flight Batching Support</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/gpt-runtime.html#know-issues-and-future-changes">Know Issues and Future Changes</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="advanced/executor.html">Executor API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="advanced/executor.html#api">API</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/executor.html#c-executor-api-example">C++ Executor API Example</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/executor.html#python-bindings-for-the-executor-api">Python Bindings for the Executor API</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/executor.html#in-flight-batching-with-the-triton-inference-server">In-flight Batching with the Triton Inference Server</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="advanced/graph-rewriting.html">Graph Rewriting Module</a><ul>
<li class="toctree-l2"><a class="reference internal" href="advanced/graph-rewriting.html#when-to-use-graph-rewriting">When to Use Graph Rewriting?</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/graph-rewriting.html#graph-rewriting-apis">Graph Rewriting APIs</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/graph-rewriting.html#classical-workflow">Classical Workflow</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="advanced/inference-request.html">Inference Request</a></li>
<li class="toctree-l1"><a class="reference internal" href="advanced/inference-request.html#responses">Responses</a></li>
<li class="toctree-l1"><a class="reference internal" href="advanced/lora.html">Run gpt-2b + LoRA using GptManager / cpp runtime</a><ul>
<li class="toctree-l2"><a class="reference internal" href="advanced/lora.html#lora-tensor-format-details">LoRA tensor format details</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="advanced/expert-parallelism.html">Expert Parallelism in TensorRT-LLM</a><ul>
<li class="toctree-l2"><a class="reference internal" href="advanced/expert-parallelism.html#mixture-of-experts-moe">Mixture of Experts (MoE)</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/expert-parallelism.html#tensor-parallel-vs-expert-parallel">Tensor Parallel vs Expert Parallel</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/expert-parallelism.html#how-to-enable">How to Enable</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="advanced/kv-cache-reuse.html">KV cache reuse</a><ul>
<li class="toctree-l2"><a class="reference internal" href="advanced/kv-cache-reuse.html#how-to-enable-kv-cache-reuse">How to enable kv cache reuse</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/kv-cache-reuse.html#performance-expectations">Performance expectations</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/kv-cache-reuse.html#situations-that-can-prevent-kv-cache-reuse">Situations that can prevent kv cache reuse</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/kv-cache-reuse.html#offloading-to-host-memory">Offloading to host memory</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="advanced/speculative-decoding.html">Speculative Sampling</a><ul>
<li class="toctree-l2"><a class="reference internal" href="advanced/speculative-decoding.html#about-speculative-sampling">About Speculative Sampling</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/speculative-decoding.html#performance-improvements">Performance Improvements</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/speculative-decoding.html#draft-target-model">Draft-Target-Model</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/speculative-decoding.html#prompt-lookup-decoding">Prompt-Lookup-Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/speculative-decoding.html#medusa">Medusa</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/speculative-decoding.html#redrafter">ReDrafter</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/speculative-decoding.html#eagle">EAGLE</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/speculative-decoding.html#lookahead-decoding">Lookahead Decoding</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="advanced/disaggregated-service.html">Disaggregated-Service (experimental)</a><ul>
<li class="toctree-l2"><a class="reference internal" href="advanced/disaggregated-service.html#usage">Usage</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/disaggregated-service.html#example">Example</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/disaggregated-service.html#benchmarks">Benchmarks</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/disaggregated-service.html#troubleshooting-and-faq">Troubleshooting and FAQ</a></li>
</ul>
</li>
</ul>
</div>
<div class="toctree-wrapper compound" id="performance">
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Performance</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="performance/perf-overview.html">Overview</a><ul>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-overview.html#known-issues">Known Issues</a></li>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-overview.html#throughput-measurements">Throughput Measurements</a></li>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-overview.html#reproducing-benchmarked-results">Reproducing Benchmarked Results</a></li>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-overview.html#online-serving-measurements">Online Serving Measurements</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="performance/perf-benchmarking.html">Benchmarking</a><ul>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-benchmarking.html#throughput-benchmarking">Throughput Benchmarking</a></li>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-benchmarking.html#low-latency-benchmark">Low Latency Benchmark</a></li>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-benchmarking.html#summary">Summary</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="performance/performance-tuning-guide/index.html">Performance Tuning Guide</a><ul>
<li class="toctree-l2"><a class="reference internal" href="performance/performance-tuning-guide/index.html#prerequisite-knowledge">Prerequisite Knowledge</a></li>
<li class="toctree-l2"><a class="reference internal" href="performance/performance-tuning-guide/index.html#table-of-contents">Table of Contents</a></li>
<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>
</li>
<li class="toctree-l1"><a class="reference internal" href="performance/perf-analysis.html">Performance Analysis</a><ul>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-analysis.html#feature-descriptions">Feature Descriptions</a></li>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-analysis.html#usage">Usage</a></li>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-analysis.html#coordinating-with-nvidia-nsight-systems-launch">Coordinating with NVIDIA Nsight Systems Launch</a></li>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-analysis.html#examples">Examples</a></li>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-analysis.html#profiling-a-single-ifb-iteration-executing-on-a-single-rank-of-a-multi-gpu-model">Profiling a single IFB iteration executing on a single rank of a multi-GPU model</a></li>
</ul>
</li>
</ul>
</div>
<div class="toctree-wrapper compound" id="reference">
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Reference</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="reference/troubleshooting.html">Troubleshooting</a><ul>
<li class="toctree-l2"><a class="reference internal" href="reference/troubleshooting.html#installation-errors">Installation Errors</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/troubleshooting.html#debug-on-unit-tests">Debug on Unit Tests</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/troubleshooting.html#debug-on-e2e-models">Debug on E2E Models</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/troubleshooting.html#debug-execution-errors">Debug Execution Errors</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/troubleshooting.html#tips">Tips</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="reference/support-matrix.html">Support Matrix</a><ul>
<li class="toctree-l2"><a class="reference internal" href="reference/support-matrix.html#models">Models</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/support-matrix.html#hardware">Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/support-matrix.html#software">Software</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="reference/precision.html">Numerical Precision</a><ul>
<li class="toctree-l2"><a class="reference internal" href="reference/precision.html#fp32-fp16-and-bf16">FP32, FP16 and BF16</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/precision.html#quantization-and-dequantization-q-dq">Quantization and Dequantization (Q/DQ)</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/precision.html#int8-smoothquant-w8a8">INT8 SmoothQuant (W8A8)</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/precision.html#int4-and-int8-weight-only-w4a16-and-w8a16">INT4 and INT8 Weight-Only (W4A16 and W8A16)</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/precision.html#gptq-and-awq-w4a16">GPTQ and AWQ (W4A16)</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/precision.html#fp8-hopper">FP8 (Hopper)</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/precision.html#nvfp4-blackwell">NVFP4 (Blackwell)</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/precision.html#support-matrix">Support matrix</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/precision.html#technical-detail-the-quantmode-flags">Technical Detail: The <code class="docutils literal notranslate"><span class="pre">QuantMode</span></code> Flags</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="reference/memory.html">Memory Usage of TensorRT-LLM</a><ul>
<li class="toctree-l2"><a class="reference internal" href="reference/memory.html#understand-inference-time-gpu-memory-usage">Understand inference time GPU memory usage</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/memory.html#memory-pool">Memory pool</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/memory.html#known-issues">Known Issues</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/memory.html#faq">FAQ</a></li>
</ul>
</li>
</ul>
</div>
<div class="toctree-wrapper compound">
</div>
</section>
<section id="indices-and-tables">
<h1>Indices and tables<a class="headerlink" href="#indices-and-tables" title="Link to this heading">#</a></h1>
<ul class="simple">
<li><p><a class="reference internal" href="genindex.html"><span class="std std-ref">Index</span></a></p></li>
<li><p><a class="reference internal" href="py-modindex.html"><span class="std std-ref">Module Index</span></a></p></li>
<li><p><a class="reference internal" href="search.html"><span class="std std-ref">Search Page</span></a></p></li>
</ul>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="right-next"
href="overview.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Overview</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-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#">Welcome to TensorRT-LLMs Documentation!</a><ul class="visible nav section-nav flex-column">
</ul>
</li>
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#indices-and-tables">Indices and tables</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 © 2024, NVidia.
<br/>
</p>
</div>
</div>
</div>
</footer>
</body>
</html>