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/1.1.0rc2/index.html
Kaiyu Xie c00f97e32e Update GitHub pages to v1.1.0rc2
2025-08-30 02:33:38 +00:00

1148 lines
84 KiB
HTML
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

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-LLM’s 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" />
<link rel="stylesheet" type="text/css" href="_static/autodoc_pydantic.css" />
<link rel="stylesheet" type="text/css" href="_static/togglebutton.css?v=13237357" />
<link rel="stylesheet" type="text/css" href="_static/custom.css?v=95073da6" />
<!-- 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>let toggleHintShow = 'Click to show';</script>
<script>let toggleHintHide = 'Click to hide';</script>
<script>let toggleOpenOnPrint = 'true';</script>
<script src="_static/togglebutton.js?v=4a39c7ea"></script>
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
<script>DOCUMENTATION_OPTIONS.pagename = 'index';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.1.0rc2';
DOCUMENTATION_OPTIONS.show_version_warning_banner =
false;
</script>
<link rel="icon" href="_static/favicon.png"/>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="next" title="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="1.1.0rc2" />
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<dialog id="pst-search-dialog">
<form class="bd-search d-flex align-items-center"
action="search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form>
</dialog>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
<div class="bd-header__inner bd-page-width">
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
<span class="fa-solid fa-bars"></span>
</button>
<div class="col-lg-3 navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="#">
<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="#">
<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/containers.html">Pre-built release container images on NGC</a></li>
<li class="toctree-l1"><a class="reference internal" href="installation/linux.html">Installing on Linux via <code class="docutils literal notranslate"><span class="pre">pip</span></code></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>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Deployment Guide</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama4-scout-on-trtllm.html">Quick Start Recipe for Llama4 Scout 17B on TensorRT-LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l1"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.html">Quick Start Recipe for DeepSeek R1 on TensorRT-LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l1"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama3.3-70b-on-trtllm.html">Quick Start Recipe for Llama3.3 70B on TensorRT-LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l1"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.html">Quick Start Recipe for GPT-OSS on TensorRT-LLM - Blackwell Hardware</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">LLM API Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="llm-api/reference.html">API Reference</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Examples</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1 has-children"><a class="reference internal" href="examples/index.html">LLM Examples Introduction</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="simple">
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="examples/customization.html">LLM Common Customizations</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="examples/llm_api_examples.html">LLM Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_inference_async.html">Generate text asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_inference_async_streaming.html">Generate text in streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_logits_processor.html">Control generated text using logits processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_speculative_decoding.html">Speculative Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_kv_cache_connector.html">KV Cache Connector</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_runtime.html">Runtime Configuration Examples</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_sampling.html">Sampling Techniques Showcase</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_mgmn_llm_distributed.html">Run LLM-API with pytorch backend on Slurm</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_mgmn_trtllm_bench.html">Run trtllm-bench with pytorch backend on Slurm</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/llm_mgmn_trtllm_serve.html">Run trtllm-serve with pytorch backend on Slurm</a></li>
</ul>
</details></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="examples/trtllm_serve_examples.html">Online Serving Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="examples/curl_chat_client.html">Curl Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/curl_completion_client.html">Curl Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/genai_perf_client.html">Genai Perf Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/genai_perf_client_for_multimodal.html">Genai Perf Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/openai_chat_client.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/openai_chat_client_for_multimodal.html">OpenAI Chat Client for Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/openai_completion_client.html">OpenAI Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/openai_completion_client_for_lora.html">Openai Completion Client For Lora</a></li>
<li class="toctree-l2"><a class="reference internal" href="examples/openai_completion_client_json_schema.html">OpenAI Completion Client with JSON Schema</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-bench.html">trtllm-bench</a></li>
<li class="toctree-l1"><a class="reference internal" href="commands/trtllm-build.html">trtllm-build</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="commands/trtllm-serve/index.html">trtllm-serve</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="commands/trtllm-serve/trtllm-serve.html">trtllm-serve</a></li>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-serve/run-benchmark-with-trtllm-serve.html">Run benchmarking with <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code></a></li>
</ul>
</details></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-management.html">KV Cache Management: Pools, Blocks, and Events</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 (Prototype)</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>
<li class="toctree-l1"><a class="reference internal" href="reference/ci-overview.html">Continuous Integration Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="reference/dev-containers.html">Using Dev Containers</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/blog10_ADP_Balance_Strategy.html">ADP Balance Strategy</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>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html">DeepSeek R1 MTP Implementation and Optimization</a></li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html">Optimizing DeepSeek R1 Throughput on NVIDIA Blackwell GPUs: A Deep Dive for Developers</a></li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html">Scaling Expert Parallelism in TensorRT-LLM (Part 1: Design and Implementation of Large-scale EP)</a></li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html">Disaggregated Serving in TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html">How to launch Llama4 Maverick + Eagle3 TensorRT-LLM server</a></li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html">N-Gram Speculative Decoding in TensorRT‑LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html">Scaling Expert Parallelism in TensorRT-LLM (Part 2: Performance Status and Optimization)</a></li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html">Running a High Performance GPT-OSS-120B Inference Server with TensorRT-LLM</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-LLM’s 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#installation">Installation</a></li>
<li class="toctree-l2"><a class="reference internal" href="quick-start-guide.html#launch-docker-on-a-node-with-nvidia-gpus-deployed">Launch Docker on a node with NVIDIA GPUs deployed.</a></li>
<li class="toctree-l2"><a class="reference internal" href="quick-start-guide.html#run-offline-inference-with-llm-api">Run Offline inference with LLM API</a></li>
<li class="toctree-l2"><a class="reference internal" href="quick-start-guide.html#deploy-online-serving-with-trtllm-serve">Deploy online serving with trtllm-serve</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#features">Features</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>
<li class="toctree-l2"><a class="reference internal" href="torch.html#known-issues">Known Issues</a></li>
<li class="toctree-l2"><a class="reference internal" href="torch.html#prototype-features">Prototype Features</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-0-21-0">TensorRT-LLM Release 0.21.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-20-0">TensorRT-LLM Release 0.20.0</a></li>
<li class="toctree-l2"><a class="reference internal" href="release-notes.html#tensorrt-llm-release-0-19-0">TensorRT-LLM Release 0.19.0</a></li>
<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/containers.html">Pre-built release container images on NGC</a></li>
<li class="toctree-l1"><a class="reference internal" href="installation/linux.html">Installing on Linux via <code class="docutils literal notranslate"><span class="pre">pip</span></code></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#build-tensorrt-llm">Build TensorRT-LLM</a></li>
</ul>
</li>
</ul>
</div>
<div class="toctree-wrapper compound" id="deployment-guide">
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Deployment Guide</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama4-scout-on-trtllm.html">Quick Start Recipe for Llama4 Scout 17B on TensorRT-LLM - Blackwell &amp; Hopper Hardware</a><ul>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama4-scout-on-trtllm.html#introduction">Introduction</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama4-scout-on-trtllm.html#access-licensing">Access &amp; Licensing</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama4-scout-on-trtllm.html#prerequisites">Prerequisites</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama4-scout-on-trtllm.html#models">Models</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama4-scout-on-trtllm.html#deployment-steps">Deployment Steps</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama4-scout-on-trtllm.html#testing-api-endpoint">Testing API Endpoint</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama4-scout-on-trtllm.html#benchmarking-performance">Benchmarking Performance</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.html">Quick Start Recipe for DeepSeek R1 on TensorRT-LLM - Blackwell &amp; Hopper Hardware</a><ul>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.html#introduction">Introduction</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.html#prerequisites">Prerequisites</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.html#models">Models</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.html#moe-backend-support-matrix">MoE Backend Support Matrix</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.html#deployment-steps">Deployment Steps</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.html#testing-api-endpoint">Testing API Endpoint</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.html#benchmarking-performance">Benchmarking Performance</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama3.3-70b-on-trtllm.html">Quick Start Recipe for Llama3.3 70B on TensorRT-LLM - Blackwell &amp; Hopper Hardware</a><ul>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama3.3-70b-on-trtllm.html#introduction">Introduction</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama3.3-70b-on-trtllm.html#access-licensing">Access &amp; Licensing</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama3.3-70b-on-trtllm.html#prerequisites">Prerequisites</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama3.3-70b-on-trtllm.html#models">Models</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama3.3-70b-on-trtllm.html#deployment-steps">Deployment Steps</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama3.3-70b-on-trtllm.html#testing-api-endpoint">Testing API Endpoint</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-llama3.3-70b-on-trtllm.html#benchmarking-performance">Benchmarking Performance</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.html">Quick Start Recipe for GPT-OSS on TensorRT-LLM - Blackwell Hardware</a><ul>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.html#introduction">Introduction</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.html#prerequisites">Prerequisites</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.html#models">Models</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.html#moe-backend-support-matrix">MoE Backend Support Matrix</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.html#deployment-steps">Deployment Steps</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.html#testing-api-endpoint">Testing API Endpoint</a></li>
<li class="toctree-l2"><a class="reference internal" href="deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.html#benchmarking-performance">Benchmarking Performance</a></li>
</ul>
</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" id="command-line-reference">
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="commands/trtllm-bench.html">trtllm-bench</a><ul>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-bench.html#trtllm-bench">trtllm-bench</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="commands/trtllm-bench.html#prepare-dataset-py">prepare_dataset.py</a><ul>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-bench.html#prepare-dataset">prepare_dataset</a></li>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-bench.html#dataset">dataset</a></li>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-bench.html#token-norm-dist">token_norm_dist</a></li>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-bench.html#token-unif-dist">token_unif_dist</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="commands/trtllm-build.html">trtllm-build</a><ul>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-build.html#tensorrt_llm.commands.build-parse_arguments-named-arguments">Named Arguments</a></li>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-build.html#tensorrt_llm.commands.build-parse_arguments-logits-arguments">Logits arguments</a></li>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-build.html#tensorrt_llm.commands.build-parse_arguments-lora-arguments">LoRA arguments</a></li>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-build.html#tensorrt_llm.commands.build-parse_arguments-speculative-decoding-arguments">Speculative decoding arguments</a></li>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-build.html#tensorrt_llm.commands.build-parse_arguments-auto-parallel-arguments">Auto parallel arguments</a></li>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-build.html#tensorrt_llm.commands.build-parse_arguments-plugin-config-arguments">Plugin config arguments</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="commands/trtllm-serve/index.html">trtllm-serve</a><ul>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-serve/trtllm-serve.html">trtllm-serve</a></li>
<li class="toctree-l2"><a class="reference internal" href="commands/trtllm-serve/run-benchmark-with-trtllm-serve.html">Run benchmarking with <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code></a></li>
</ul>
</li>
</ul>
</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>
</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/lora.html">Run gpt-2b + LoRA using Executor / 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-management.html">KV Cache Management: Pools, Blocks, and Events</a><ul>
<li class="toctree-l2"><a class="reference internal" href="advanced/kv-cache-management.html#hierarchy-pool-block-and-page">Hierarchy: Pool, Block, and Page</a></li>
<li class="toctree-l2"><a class="reference internal" href="advanced/kv-cache-management.html#events-in-kvcacheeventmanager">Events in <code class="docutils literal notranslate"><span class="pre">KVCacheEventManager</span></code></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#ngram">NGram</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 (Prototype)</a><ul>
<li class="toctree-l2"><a class="reference internal" href="advanced/disaggregated-service.html#environment-variables">Environment Variables</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#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>
</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#before-benchmarking">Before Benchmarking</a></li>
<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#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#coordinating-with-pytorch-profiler-pytorch-workflow-only">Coordinating with PyTorch profiler (PyTorch workflow only)</a></li>
<li class="toctree-l2"><a class="reference internal" href="performance/perf-analysis.html#examples">Examples</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-pytorch-backend">Models (PyTorch Backend)</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/support-matrix.html#models-tensorrt-backend">Models (TensorRT Backend)</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>
<li class="toctree-l1"><a class="reference internal" href="reference/ci-overview.html">Continuous Integration Overview</a><ul>
<li class="toctree-l2"><a class="reference internal" href="reference/ci-overview.html#table-of-contents">Table of Contents</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/ci-overview.html#ci-pipelines">CI pipelines</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/ci-overview.html#test-definitions">Test definitions</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/ci-overview.html#unit-tests">Unit tests</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/ci-overview.html#jenkins-stage-names">Jenkins stage names</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/ci-overview.html#finding-the-stage-for-a-test">Finding the stage for a test</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/ci-overview.html#waiving-tests">Waiving tests</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/ci-overview.html#triggering-ci-best-practices">Triggering CI Best Practices</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="reference/dev-containers.html">Using Dev Containers</a><ul>
<li class="toctree-l2"><a class="reference internal" href="reference/dev-containers.html#container-image-selection">Container image selection</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/dev-containers.html#volume-mounts">Volume Mounts</a></li>
<li class="toctree-l2"><a class="reference internal" href="reference/dev-containers.html#overriding-docker-compose-configuration">Overriding Docker Compose configuration</a></li>
</ul>
</li>
</ul>
</div>
<div class="toctree-wrapper compound">
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
<ul>
<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><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/H100vsA100.html#mlperf-on-h100-with-fp8">MLPerf on H100 with FP8</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/H100vsA100.html#what-is-h100-fp8">What is H100 FP8?</a></li>
</ul>
</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><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/H200launch.html#h200-vs-h100">H200 vs H100</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/H200launch.html#latest-hbm-memory">Latest HBM Memory</a></li>
</ul>
</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><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/Falcon180B-H200.html#falcon-180b-on-a-single-h200-with-int4-awq">Falcon-180B on a single H200 with INT4 AWQ</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/Falcon180B-H200.html#llama-70b-on-h200-up-to-6-7x-a100">Llama-70B on H200 up to 6.7x A100</a></li>
</ul>
</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><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/quantization-in-TRT-LLM.html#quantization-in-tensorrt-llm">Quantization in TensorRT-LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/quantization-in-TRT-LLM.html#benchmark">Benchmark</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/quantization-in-TRT-LLM.html#best-practices-to-choose-the-right-quantization-methods">Best practices to choose the right quantization methods</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/quantization-in-TRT-LLM.html#whats-coming-next">What’s coming next</a></li>
</ul>
</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><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/XQA-kernel.html#llama-70b-on-h200-up-to-2-4x-increased-throughput-with-xqa-within-same-latency-budget">Llama-70B on H200 up to 2.4x increased throughput with XQA within same latency budget</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog10_ADP_Balance_Strategy.html">ADP Balance Strategy</a><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog10_ADP_Balance_Strategy.html#table-of-contents">Table of Contents</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog10_ADP_Balance_Strategy.html#motivation-and-background">Motivation and Background</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog10_ADP_Balance_Strategy.html#theoretical-analysis-and-modeling">Theoretical Analysis and Modeling</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog10_ADP_Balance_Strategy.html#experiments">Experiments</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog10_ADP_Balance_Strategy.html#conclusion">Conclusion</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog10_ADP_Balance_Strategy.html#acknowledgement">Acknowledgement</a></li>
</ul>
</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><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html#table-of-contents">Table of Contents</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html#background">Background</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html#implementation-configuration">Implementation Configuration</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html#key-optimizations">Key Optimizations</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html#how-to-reproduce">How to reproduce</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html#future-works">Future Works</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html#acknowledgment">Acknowledgment</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html">DeepSeek R1 MTP Implementation and Optimization</a><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html#table-of-contents">Table of Contents</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html#mtp-for-inference">MTP for inference</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html#mtp-implementation-in-tensorrt-llm">MTP implementation in TensorRT-LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html#mtp-optimization-relaxed-acceptance">MTP optimization - Relaxed Acceptance</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html#evaluation">Evaluation</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html#future-works">Future Works</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html#acknowledgment">Acknowledgment</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html">Optimizing DeepSeek R1 Throughput on NVIDIA Blackwell GPUs: A Deep Dive for Developers</a><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html#table-of-contents">Table of Contents</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html#introduction">Introduction</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html#precision-strategy">Precision strategy</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html#parallel-strategy">Parallel strategy</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html#mla-layers-optimizations">MLA Layers Optimizations</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html#moe-layers-optimizations">MoE Layers Optimizations</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html#runtime-optimizations">Runtime Optimizations</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html#how-to-reproduce">How to reproduce</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html#future-works">Future Works</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html#acknowledgment">Acknowledgment</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html">Scaling Expert Parallelism in TensorRT-LLM (Part 1: Design and Implementation of Large-scale EP)</a><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html#table-of-contents">Table of Contents</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html#motivation-for-large-scale-ep">Motivation for large-scale EP</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html#high-level-design-introduction">High-level design introduction</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html#ep-communication-kernels">EP communication kernels</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html#ep-load-balancer">EP Load Balancer</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html#e2e-evaluation">E2E evaluation</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html#reproducing-steps">Reproducing steps</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html#expanded-thoughts">Expanded thoughts</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html#acknowledgement">Acknowledgement</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html">Disaggregated Serving in TensorRT-LLM</a><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html#motivation">Motivation</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html#id1">Disaggregated Serving in TensorRT-LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html#kv-cache-exchange">KV Cache Exchange</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html#performance-studies">Performance Studies</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html#future-work">Future Work</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html#acknowledgement">Acknowledgement</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html">How to launch Llama4 Maverick + Eagle3 TensorRT-LLM server</a><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html#prerequisites">Prerequisites</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html#download-artifacts">Download Artifacts</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html#launching-the-server">Launching the server</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html#troubleshooting-tips">Troubleshooting Tips</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html#performance-tuning">Performance Tuning</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html">N-Gram Speculative Decoding in TensorRT‑LLM</a><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html#highlights">Highlights</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html#table-of-contents">Table of Contents</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html#background-motivation">Background &amp; Motivation</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html#algorithm-complexity">Algorithm &amp; Complexity</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html#performance-study">Performance Study</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html#autoenablement-with-heuristic">Auto‑Enablement with Heuristic</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html">Scaling Expert Parallelism in TensorRT-LLM (Part 2: Performance Status and Optimization)</a><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html#table-of-contents">Table of Contents</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html#optimization-highlights">Optimization Highlights</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html#end-to-end-performance">End-to-End Performance</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html#future-work">Future Work</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html#acknowledgements">Acknowledgements</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html">Running a High Performance GPT-OSS-120B Inference Server with TensorRT-LLM</a><ul>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html#prerequisites">Prerequisites</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html#install-tensorrt-llm">Install TensorRT-LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html#performance-benchmarking-and-model-serving">Performance Benchmarking and Model Serving</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html#launch-the-tensorrt-llm-server">Launch the TensorRT-LLM Server</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html#h200-h100-only-using-openai-triton-kernels-for-moe">(H200/H100 Only) Using OpenAI Triton Kernels for MoE</a></li>
<li class="toctree-l2"><a class="reference internal" href="blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html#troubleshooting-tips">Troubleshooting Tips</a></li>
</ul>
</li>
</ul>
</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-LLM’s 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 © 2025, NVidia.
<br/>
</p>
</div>
<div class="footer-item">
<div class="extra_footer">
<p>Last updated on August 29, 2025.</p>
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/15ec2b8">15ec2b8</a>.</p>
</div></div>
</div>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink