kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
a79e2dc7fb
TensorRT-LLMs/0.20.0rc3/examples/customization.html
Kaiyu Xie e2085332db Update GitHub pages to v0.20.0rc3
2025-05-20 09:23:49 +00:00

796 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>LLM Common Customizations &#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" />
<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 = 'examples/customization';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '0.20.0rc3';
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="LLM Examples" href="llm_api_examples.html" />
<link rel="prev" title="Llm Mgmn Trtllm Serve" href="llm_mgmn_trtllm_serve.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="0.20.0rc3" />
</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="current nav bd-sidenav">
<li class="toctree-l1 has-children"><a class="reference internal" href="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_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_eagle_decoding.html">Generate Text Using Eagle Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_async.html">Generate Text Asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_logits_processor.html">Control generated text using logits processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_kv_events.html">Get KV Cache Events</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_quantization.html">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_async_streaming.html">Generate Text in Streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_customize.html">Generate text with customization</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
</ul>
</details></li>
<li class="toctree-l1 current active"><a class="current reference internal" href="#">LLM Common Customizations</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="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="llm_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_eagle_decoding.html">Generate Text Using Eagle Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_async.html">Generate Text Asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_logits_processor.html">Control generated text using logits processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_kv_events.html">Get KV Cache Events</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_quantization.html">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_async_streaming.html">Generate Text in Streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_customize.html">Generate text with customization</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
<li class="toctree-l2"><a class="reference internal" href="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="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="curl_chat_client.html">Curl Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="curl_completion_client.html">Curl Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
<li class="toctree-l2"><a class="reference internal" href="genai_perf_client.html">Genai Perf Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="genai_perf_client_for_multimodal.html">Genai Perf Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="openai_chat_client.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="openai_chat_client_for_multimodal.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="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="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>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html">Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs</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">LLM Common Customizations</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="llm-common-customizations">
<h1>LLM Common Customizations<a class="headerlink" href="#llm-common-customizations" title="Link to this heading">#</a></h1>
<section id="quantization">
<h2>Quantization<a class="headerlink" href="#quantization" title="Link to this heading">#</a></h2>
<p>TensorRT-LLM can quantize the Hugging Face model automatically. By setting the appropriate flags in the <code class="docutils literal notranslate"><span class="pre">LLM</span></code> instance. For example, to perform an Int4 AWQ quantization, the following code triggers the model quantization. Please refer to complete list of <a class="reference external" href="https://nvidia.github.io/TensorRT-LLM/_modules/tensorrt_llm/quantization/mode.html#QuantAlgo">supported flags</a> and acceptable values.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.llmapi</span><span class="w"> </span><span class="kn">import</span> <span class="n">QuantConfig</span><span class="p">,</span> <span class="n">QuantAlgo</span>
<span class="n">quant_config</span> <span class="o">=</span> <span class="n">QuantConfig</span><span class="p">(</span><span class="n">quant_algo</span><span class="o">=</span><span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A16_AWQ</span><span class="p">)</span>
<span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span><span class="o">&lt;</span><span class="n">model</span><span class="o">-</span><span class="nb">dir</span><span class="o">&gt;</span><span class="p">,</span> <span class="n">quant_config</span><span class="o">=</span><span class="n">quant_config</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="sampling">
<h2>Sampling<a class="headerlink" href="#sampling" title="Link to this heading">#</a></h2>
<p>SamplingParams can customize the sampling strategy to control LLM generated responses, such as beam search, temperature, and <a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/blob/main/tensorrt_llm/llmapi/utils.py#L55-L76">others</a>.</p>
<p>As an example, to enable beam search with a beam size of 4, set the <code class="docutils literal notranslate"><span class="pre">sampling_params</span></code> as follows:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.llmapi</span><span class="w"> </span><span class="kn">import</span> <span class="n">LLM</span><span class="p">,</span> <span class="n">SamplingParams</span><span class="p">,</span> <span class="n">BuildConfig</span>
<span class="n">build_config</span> <span class="o">=</span> <span class="n">BuildConfig</span><span class="p">()</span>
<span class="n">build_config</span><span class="o">.</span><span class="n">max_beam_width</span> <span class="o">=</span> <span class="mi">4</span>
<span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span><span class="o">&lt;</span><span class="n">llama_model_path</span><span class="o">&gt;</span><span class="p">,</span> <span class="n">build_config</span><span class="o">=</span><span class="n">build_config</span><span class="p">)</span>
<span class="c1"># Let the LLM object generate text with the default sampling strategy, or</span>
<span class="c1"># you can create a SamplingParams object as well with several fields set manually</span>
<span class="n">sampling_params</span> <span class="o">=</span> <span class="n">SamplingParams</span><span class="p">(</span><span class="n">beam_width</span><span class="o">=</span><span class="mi">4</span><span class="p">)</span> <span class="c1"># current limitation: beam_width should be equal to max_beam_width</span>
<span class="k">for</span> <span class="n">output</span> <span class="ow">in</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate</span><span class="p">(</span><span class="o">&lt;</span><span class="n">prompt</span><span class="o">&gt;</span><span class="p">,</span> <span class="n">sampling_params</span><span class="o">=</span><span class="n">sampling_params</span><span class="p">):</span>
<span class="nb">print</span><span class="p">(</span><span class="n">output</span><span class="p">)</span>
</pre></div>
</div>
<p><code class="docutils literal notranslate"><span class="pre">SamplingParams</span></code> manages and dispatches fields to C++ classes including:</p>
<ul class="simple">
<li><p><a class="reference external" href="https://nvidia.github.io/TensorRT-LLM/_cpp_gen/runtime.html#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE">SamplingConfig</a></p></li>
<li><p><a class="reference external" href="https://nvidia.github.io/TensorRT-LLM/_cpp_gen/executor.html#_CPPv4N12tensorrt_llm8executor12OutputConfigE">OutputConfig</a></p></li>
</ul>
<p>Refer to the <a class="reference external" href="https://nvidia.github.io/TensorRT-LLM/llm-api/index.html#tensorrt_llm.llmapi.SamplingParams">class documentation</a> for more details.</p>
</section>
<section id="build-configuration">
<h2>Build Configuration<a class="headerlink" href="#build-configuration" title="Link to this heading">#</a></h2>
<p>Apart from the arguments mentioned above, you can also customize the build configuration with the <code class="docutils literal notranslate"><span class="pre">build_config</span></code> class and other arguments borrowed from the trtllm-build CLI. These build configuration options provide flexibility in building engines for the target hardware and use cases. Refer to the following example:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span><span class="o">&lt;</span><span class="n">model</span><span class="o">-</span><span class="n">path</span><span class="o">&gt;</span><span class="p">,</span>
<span class="n">build_config</span><span class="o">=</span><span class="n">BuildConfig</span><span class="p">(</span>
<span class="n">max_num_tokens</span><span class="o">=</span><span class="mi">4096</span><span class="p">,</span>
<span class="n">max_batch_size</span><span class="o">=</span><span class="mi">128</span><span class="p">,</span>
<span class="n">max_beam_width</span><span class="o">=</span><span class="mi">4</span><span class="p">))</span>
</pre></div>
</div>
<p>Refer to the <a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/blob/main/tensorrt_llm/builder.py#L470-L501">buildconfig documentation</a> for more details.</p>
</section>
<section id="runtime-customization">
<h2>Runtime Customization<a class="headerlink" href="#runtime-customization" title="Link to this heading">#</a></h2>
<p>Similar to <code class="docutils literal notranslate"><span class="pre">build_config</span></code>, you can also customize the runtime configuration with the <code class="docutils literal notranslate"><span class="pre">runtime_config</span></code>, <code class="docutils literal notranslate"><span class="pre">peft_cache_config</span></code> or other <a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/blob/main/tensorrt_llm/llmapi/llm_utils.py#L186-L223">arguments</a> borrowed from the Executor APIs. These runtime configuration options provide additional flexibility with respect to KV cache management, GPU memory allocation and so on. Refer to the following example:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.llmapi</span><span class="w"> </span><span class="kn">import</span> <span class="n">LLM</span><span class="p">,</span> <span class="n">KvCacheConfig</span>
<span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span><span class="o">&lt;</span><span class="n">llama_model_path</span><span class="o">&gt;</span><span class="p">,</span>
<span class="n">kv_cache_config</span><span class="o">=</span><span class="n">KvCacheConfig</span><span class="p">(</span>
<span class="n">free_gpu_memory_fraction</span><span class="o">=</span><span class="mf">0.8</span><span class="p">))</span>
</pre></div>
</div>
</section>
<section id="tokenizer-customization">
<h2>Tokenizer Customization<a class="headerlink" href="#tokenizer-customization" title="Link to this heading">#</a></h2>
<p>By default, the LLM API uses transformers’ <code class="docutils literal notranslate"><span class="pre">AutoTokenizer</span></code>. You can override it with your own tokenizer by passing it when creating the LLM object. Refer to the following example:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span><span class="o">&lt;</span><span class="n">llama_model_path</span><span class="o">&gt;</span><span class="p">,</span> <span class="n">tokenizer</span><span class="o">=&lt;</span><span class="n">my_faster_one</span><span class="o">&gt;</span><span class="p">)</span>
</pre></div>
</div>
<p>The LLM() workflow should use your tokenizer instead.</p>
<p>It is also possible to input token IDs directly without <code class="docutils literal notranslate"><span class="pre">Tokenizers</span></code> with the following code. The code produces token IDs without text because the tokenizer is not used.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span><span class="o">&lt;</span><span class="n">llama_model_path</span><span class="o">&gt;</span><span class="p">)</span>
<span class="k">for</span> <span class="n">output</span> <span class="ow">in</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate</span><span class="p">([</span><span class="mi">32</span><span class="p">,</span> <span class="mi">12</span><span class="p">]):</span>
<span class="o">...</span>
</pre></div>
</div>
<section id="disable-tokenizer">
<h3>Disable Tokenizer<a class="headerlink" href="#disable-tokenizer" title="Link to this heading">#</a></h3>
<p>For performance considerations, you can disable the tokenizer by passing <code class="docutils literal notranslate"><span class="pre">skip_tokenizer_init=True</span></code> when creating <code class="docutils literal notranslate"><span class="pre">LLM</span></code>. In this case, <code class="docutils literal notranslate"><span class="pre">LLM.generate</span></code> and <code class="docutils literal notranslate"><span class="pre">LLM.generate_async</span></code> will expect prompt token ids as input. Refer to the following example:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span><span class="o">&lt;</span><span class="n">llama_model_path</span><span class="o">&gt;</span><span class="p">)</span>
<span class="k">for</span> <span class="n">output</span> <span class="ow">in</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate</span><span class="p">([[</span><span class="mi">32</span><span class="p">,</span> <span class="mi">12</span><span class="p">]],</span> <span class="n">skip_tokenizer_init</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="nb">print</span><span class="p">(</span><span class="n">output</span><span class="p">)</span>
</pre></div>
</div>
<p>You will get something like:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">RequestOutput</span><span class="p">(</span><span class="n">request_id</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">prompt</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">prompt_token_ids</span><span class="o">=</span><span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">15043</span><span class="p">,</span> <span class="mi">29892</span><span class="p">,</span> <span class="mi">590</span><span class="p">,</span> <span class="mi">1024</span><span class="p">,</span> <span class="mi">338</span><span class="p">],</span> <span class="n">outputs</span><span class="o">=</span><span class="p">[</span><span class="n">CompletionOutput</span><span class="p">(</span><span class="n">index</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">text</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">,</span> <span class="n">token_ids</span><span class="o">=</span><span class="p">[</span><span class="mi">518</span><span class="p">,</span> <span class="mi">10858</span><span class="p">,</span> <span class="mi">4408</span><span class="p">,</span> <span class="mi">29962</span><span class="p">,</span> <span class="mi">322</span><span class="p">,</span> <span class="mi">306</span><span class="p">,</span> <span class="mi">626</span><span class="p">,</span> <span class="mi">263</span><span class="p">,</span> <span class="mi">518</span><span class="p">,</span> <span class="mi">10858</span><span class="p">,</span> <span class="mi">20627</span><span class="p">,</span> <span class="mi">29962</span><span class="p">,</span> <span class="mi">472</span><span class="p">,</span> <span class="mi">518</span><span class="p">,</span> <span class="mi">10858</span><span class="p">,</span> <span class="mi">6938</span><span class="p">,</span> <span class="mi">1822</span><span class="p">,</span> <span class="mi">306</span><span class="p">,</span> <span class="mi">626</span><span class="p">,</span> <span class="mi">5007</span><span class="p">,</span> <span class="mi">304</span><span class="p">,</span> <span class="mi">4653</span><span class="p">,</span> <span class="mi">590</span><span class="p">,</span> <span class="mi">4066</span><span class="p">,</span> <span class="mi">297</span><span class="p">,</span> <span class="mi">278</span><span class="p">,</span> <span class="mi">518</span><span class="p">,</span> <span class="mi">11947</span><span class="p">,</span> <span class="mi">18527</span><span class="p">,</span> <span class="mi">29962</span><span class="p">,</span> <span class="mi">2602</span><span class="p">,</span> <span class="mi">472</span><span class="p">],</span> <span class="n">cumulative_logprob</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">logprobs</span><span class="o">=</span><span class="p">[])],</span> <span class="n">finished</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
</pre></div>
</div>
<p>Note that the <code class="docutils literal notranslate"><span class="pre">text</span></code> field in <code class="docutils literal notranslate"><span class="pre">CompletionOutput</span></code> is empty since the tokenizer is deactivated.</p>
</section>
</section>
<section id="generation">
<h2>Generation<a class="headerlink" href="#generation" title="Link to this heading">#</a></h2>
<section id="asyncio-based-generation">
<h3>Asyncio-Based Generation<a class="headerlink" href="#asyncio-based-generation" title="Link to this heading">#</a></h3>
<p>With the LLM API, you can also perform asynchronous generation with the <code class="docutils literal notranslate"><span class="pre">generate_async</span></code> method. Refer to the following example:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span><span class="n">model</span><span class="o">=&lt;</span><span class="n">llama_model_path</span><span class="o">&gt;</span><span class="p">)</span>
<span class="k">async</span> <span class="k">for</span> <span class="n">output</span> <span class="ow">in</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate_async</span><span class="p">(</span><span class="o">&lt;</span><span class="n">prompt</span><span class="o">&gt;</span><span class="p">,</span> <span class="n">streaming</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="nb">print</span><span class="p">(</span><span class="n">output</span><span class="p">)</span>
</pre></div>
</div>
<p>When the <code class="docutils literal notranslate"><span class="pre">streaming</span></code> flag is set to <code class="docutils literal notranslate"><span class="pre">True</span></code>, the <code class="docutils literal notranslate"><span class="pre">generate_async</span></code> method will return a generator that yields each token as soon as it is available. Otherwise, it returns a generator that wait for and yields only the final results.</p>
</section>
<section id="future-style-generation">
<h3>Future-Style Generation<a class="headerlink" href="#future-style-generation" title="Link to this heading">#</a></h3>
<p>The result of the <code class="docutils literal notranslate"><span class="pre">generate_async</span></code> method is a <a class="reference external" href="https://docs.python.org/3/library/asyncio-future.html#asyncio.Future">Future-like</a> object, it doesn’t block the thread unless the <code class="docutils literal notranslate"><span class="pre">.result()</span></code> is called.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># This will not block the main thread</span>
<span class="n">generation</span> <span class="o">=</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate_async</span><span class="p">(</span><span class="o">&lt;</span><span class="n">prompt</span><span class="o">&gt;</span><span class="p">)</span>
<span class="c1"># Do something else here</span>
<span class="c1"># call .result() to explicitly block the main thread and wait for the result when needed</span>
<span class="n">output</span> <span class="o">=</span> <span class="n">generation</span><span class="o">.</span><span class="n">result</span><span class="p">()</span>
</pre></div>
</div>
<p>The <code class="docutils literal notranslate"><span class="pre">.result()</span></code> method works like the <a class="reference external" href="https://docs.python.org/zh-cn/3/library/asyncio-future.html#asyncio.Future.result">result</a> method in the Python Future, you can specify a timeout to wait for the result.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">output</span> <span class="o">=</span> <span class="n">generation</span><span class="o">.</span><span class="n">result</span><span class="p">(</span><span class="n">timeout</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span>
</pre></div>
</div>
<p>There is an async version, where the <code class="docutils literal notranslate"><span class="pre">.aresult()</span></code> is used.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">generation</span> <span class="o">=</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate_async</span><span class="p">(</span><span class="o">&lt;</span><span class="n">prompt</span><span class="o">&gt;</span><span class="p">)</span>
<span class="n">output</span> <span class="o">=</span> <span class="k">await</span> <span class="n">generation</span><span class="o">.</span><span class="n">aresult</span><span class="p">()</span>
</pre></div>
</div>
</section>
</section>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="llm_mgmn_trtllm_serve.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">Llm Mgmn Trtllm Serve</p>
</div>
</a>
<a class="right-next"
href="llm_api_examples.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">LLM Examples</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">Quantization</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#sampling">Sampling</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#build-configuration">Build Configuration</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#runtime-customization">Runtime Customization</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#tokenizer-customization">Tokenizer Customization</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#disable-tokenizer">Disable Tokenizer</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#generation">Generation</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#asyncio-based-generation">Asyncio-Based Generation</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#future-style-generation">Future-Style Generation</a></li>
</ul>
</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>
Reference in New Issue View Git Blame Copy Permalink