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
gh-pages
TensorRT-LLMs/developer-guide/perf-analysis.html
Kaiyu Xie 9c2249e7c4 Update GitHub pages in root to v1.2.0rc7
2026-01-08 05:44:03 +00:00

889 lines
53 KiB
HTML
Raw Permalink 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>Performance Analysis &#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=933278ad" />
<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/config_selector.css?v=e17d8078" />
<link rel="stylesheet" type="text/css" href="../_static/custom.css?v=19d20f17" />
<!-- 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 src="../_static/config_selector.js?v=aaf6cd4a"></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 = 'developer-guide/perf-analysis';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.2.0rc7';
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="TensorRT LLM Benchmarking" href="perf-benchmarking.html" />
<link rel="prev" title="Architecture 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="1.2.0rc7" />
</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 has-children"><a class="reference internal" href="../installation/index.html">Installation</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="../installation/containers.html">Pre-built release container images on NGC</a></li>
<li class="toctree-l2"><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-l2"><a class="reference internal" href="../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
</ul>
</details></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 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_sparse_attention.html">Sparse Attention</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_kv_cache_offloading.html">KV Cache Offloading</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/aiperf_client.html">Aiperf Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/aiperf_client_for_multimodal.html">Aiperf Client For Multimodal</a></li>
<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/curl_responses_client.html">Curl Responses 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/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>
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_responses_client.html">OpenAI Responses Client</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../examples/dynamo_k8s_example.html">Dynamo K8s Example</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../deployment-guide/index.html">Model Recipes</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="../deployment-guide/deployment-guide-for-deepseek-r1-on-trtllm.html">Deployment Guide for DeepSeek R1 on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-llama3.3-70b-on-trtllm.html">Deployment Guide for Llama3.3 70B on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-llama4-scout-on-trtllm.html">Deployment Guide for Llama4 Scout 17B on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-gpt-oss-on-trtllm.html">Deployment Guide for GPT-OSS on TensorRT-LLM - Blackwell Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-qwen3-on-trtllm.html">Deployment Guide for Qwen3 on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-qwen3-next-on-trtllm.html">Deployment Guide for Qwen3 Next on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-kimi-k2-thinking-on-trtllm.html">Deployment Guide for Kimi K2 Thinking on TensorRT LLM - Blackwell</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Models</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../models/supported-models.html">Supported Models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../models/adding-new-model.html">Adding a New Model</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">CLI 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-eval.html">trtllm-eval</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">API Reference</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">Features</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../features/feature-combination-matrix.html">Feature Combination Matrix</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/disagg-serving.html">Disaggregated Serving</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/kvcache.html">KV Cache System</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/long-sequence.html">Long Sequences</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/lora.html">LoRA (Low-Rank Adaptation)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/multi-modality.html">Multimodal Support in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/overlap-scheduler.html">Overlap Scheduler</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/paged-attention-ifb-scheduler.html">Paged Attention, IFB, and Request Scheduling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/parallel-strategy.html">Parallelism in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/quantization.html">Quantization</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/sampling.html">Sampling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/additional-outputs.html">Additional Outputs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/guided-decoding.html">Guided Decoding</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/speculative-decoding.html">Speculative Decoding</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/checkpoint-loading.html">Checkpoint Loading</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/auto_deploy/auto-deploy.html">AutoDeploy (Beta)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/ray-orchestrator.html">Ray Orchestrator (Prototype)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/torch_compile_and_piecewise_cuda_graph.html">Torch Compile &amp; Piecewise CUDA Graph</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/helix.html">Helix Parallelism</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/kv-cache-connector.html">KV Cache Connector</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Developer Guide</span></p>
<ul class="current nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="overview.html">Architecture Overview</a></li>
<li class="toctree-l1 current active"><a class="current reference internal" href="#">Performance Analysis</a></li>
<li class="toctree-l1"><a class="reference internal" href="perf-benchmarking.html">TensorRT LLM Benchmarking</a></li>
<li class="toctree-l1"><a class="reference internal" href="ci-overview.html">Continuous Integration Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="dev-containers.html">Using Dev Containers</a></li>
<li class="toctree-l1"><a class="reference internal" href="api-change.html">LLM API Change Guide</a></li>
<li class="toctree-l1"><a class="reference internal" href="kv-transfer.html">Introduction to KV Cache Transmission</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/tech_blog/blog10_ADP_Balance_Strategy.html">ADP Balance Strategy</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog11_GPT_OSS_Eagle3.html">Running GPT-OSS-120B with Eagle3 Speculative Decoding on GB200/B200 (TensorRT LLM)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.html">Combining Guided Decoding and Speculative Decoding: Making CPU and GPU Cooperate Seamlessly</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog13_Inference_Time_Compute_Implementation_in_TensorRT-LLM.html">Inference Time Compute Implementation in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog14_Scaling_Expert_Parallelism_in_TensorRT-LLM_part3.html">Scaling Expert Parallelism in TensorRT LLM (Part 3: Pushing the Performance Boundary)</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>
<li class="toctree-l1"><a class="reference internal" href="../blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.html">How to get best performance on DeepSeek-R1 in TensorRT LLM</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/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/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Quick Links</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/releases">Releases</a></li>
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM">Github Code</a></li>
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/issues?q=is%3Aissue%20state%3Aopen%20label%3Aroadmap">Roadmap</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Use TensorRT Engine</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../legacy/tensorrt_quickstart.html">LLM API with TensorRT Engine</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">Performance Analysis</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section class="tex2jax_ignore mathjax_ignore" id="performance-analysis">
<span id="perf-analysis"></span><h1>Performance Analysis<a class="headerlink" href="#performance-analysis" title="Link to this heading">#</a></h1>
<p>NVIDIA Nsight Systems reports at the application level are highly informative. Metric sampling capabilities have increased over generations and provide a clean middle-ground between timing analysis and kernel-level deep dives with NVIDIA Nsight Compute.</p>
<p>Given the potential long runtimes of Large Languages Models (LLMs) and the diversity of workloads a model may experience during a single inference pass or binary execution, NVIDIA has added features to TensorRT LLM to get the most out of Nsight Systems capabilities. This document outlines those features as well as provides examples of how to best utilize them to understand your application.</p>
<section id="feature-descriptions">
<h2>Feature Descriptions<a class="headerlink" href="#feature-descriptions" title="Link to this heading">#</a></h2>
<p>The main functionality:</p>
<ul class="simple">
<li><p>Relies on toggling the CUDA profiler runtime API on and off.</p></li>
<li><p>(PyTorch workflow only) Toggling the PyTorch profiler on and off.</p></li>
<li><p>Provides a means to understand which regions a user may want to focus on.</p></li>
</ul>
<p>Toggling the CUDA profiler runtime API on and off:</p>
<ul class="simple">
<li><p>Allows users to know specifically what the profiled region corresponds to.</p></li>
<li><p>Results in smaller files to post-process (for metric extraction or similar).</p></li>
</ul>
<p>(PyTorch workflow only) Toggling the PyTorch profiler on and off:</p>
<ul class="simple">
<li><p>Help users to analysis the performance breakdown in the model.</p></li>
<li><p>Results in smaller files to post-process (for metric extraction or similar).</p></li>
</ul>
</section>
<section id="coordinating-with-nvidia-nsight-systems-launch">
<h2>Coordinating with NVIDIA Nsight Systems Launch<a class="headerlink" href="#coordinating-with-nvidia-nsight-systems-launch" title="Link to this heading">#</a></h2>
<p>Consult the Nsight Systems User Guide for full overview of options.</p>
<p>On the PyTorch workflow, basic NVTX markers are by default provided. On the C++/TensorRT workflow, append <code class="docutils literal notranslate"><span class="pre">--nvtx</span></code> when calling <code class="docutils literal notranslate"><span class="pre">scripts/build_wheel.py</span></code> script to compile, and clean build the code.</p>
<section id="only-collect-specific-iterations">
<h3>Only collect specific iterations<a class="headerlink" href="#only-collect-specific-iterations" title="Link to this heading">#</a></h3>
<p>To reduce the Nsight Systems profile size, and ensure that only specific iterations are collected, set environment variable <code class="docutils literal notranslate"><span class="pre">TLLM_PROFILE_START_STOP=A-B</span></code>, and append <code class="docutils literal notranslate"><span class="pre">-c</span> <span class="pre">cudaProfilerApi</span></code> to <code class="docutils literal notranslate"><span class="pre">nsys</span> <span class="pre">profile</span></code> command.</p>
</section>
<section id="enable-more-nvtx-markers-for-debugging">
<h3>Enable more NVTX markers for debugging<a class="headerlink" href="#enable-more-nvtx-markers-for-debugging" title="Link to this heading">#</a></h3>
<p>Set environment variable <code class="docutils literal notranslate"><span class="pre">TLLM_NVTX_DEBUG=1</span></code>.</p>
</section>
<section id="enable-garbage-collection-gc-nvtx-markers">
<h3>Enable garbage collection (GC) NVTX markers<a class="headerlink" href="#enable-garbage-collection-gc-nvtx-markers" title="Link to this heading">#</a></h3>
<p>Set environment variable <code class="docutils literal notranslate"><span class="pre">TLLM_PROFILE_RECORD_GC=1</span></code>.</p>
</section>
<section id="enable-gil-information-in-nvtx-markers">
<h3>Enable GIL information in NVTX markers<a class="headerlink" href="#enable-gil-information-in-nvtx-markers" title="Link to this heading">#</a></h3>
<p>Append “python-gil” to Nsys “-t” option.</p>
</section>
</section>
<section id="coordinating-with-pytorch-profiler-pytorch-workflow-only">
<h2>Coordinating with PyTorch profiler (PyTorch workflow only)<a class="headerlink" href="#coordinating-with-pytorch-profiler-pytorch-workflow-only" title="Link to this heading">#</a></h2>
<section id="collect-pytorch-profiler-results">
<h3>Collect PyTorch profiler results<a class="headerlink" href="#collect-pytorch-profiler-results" title="Link to this heading">#</a></h3>
<ol class="arabic simple">
<li><p>Set environment variable <code class="docutils literal notranslate"><span class="pre">TLLM_PROFILE_START_STOP=A-B</span></code> to specify the range of the iterations to be collected.</p></li>
<li><p>Set environment variable <code class="docutils literal notranslate"><span class="pre">TLLM_TORCH_PROFILE_TRACE=&lt;path&gt;</span></code>, and the results will be saved to <code class="docutils literal notranslate"><span class="pre">&lt;path&gt;</span></code>.</p></li>
</ol>
</section>
<section id="visualize-the-pytorch-profiler-results">
<h3>Visualize the PyTorch profiler results<a class="headerlink" href="#visualize-the-pytorch-profiler-results" title="Link to this heading">#</a></h3>
<p>Use <a class="reference internal" href="#chrome://tracing/"><span class="xref myst">chrome://tracing/</span></a> to inspect the saved profile.</p>
</section>
</section>
<section id="examples">
<h2>Examples<a class="headerlink" href="#examples" title="Link to this heading">#</a></h2>
<p>Consult the Nsight Systems User Guide for full overview of MPI-related options.</p>
<section id="profiling-specific-iterations-on-a-trtllm-bench-trtllm-serve-run">
<h3>Profiling specific iterations on a <code class="docutils literal notranslate"><span class="pre">trtllm-bench</span></code>/<code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code> run<a class="headerlink" href="#profiling-specific-iterations-on-a-trtllm-bench-trtllm-serve-run" title="Link to this heading">#</a></h3>
<p>Say we want to profile iterations 100 to 150 on a <code class="docutils literal notranslate"><span class="pre">trtllm-bench</span></code>/<code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code> run, we want to collect as much information as possible for debugging, such as GIL, debugging NVTX markers, etc:</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="ch">#!/bin/bash</span>
<span class="c1"># Prepare dataset for the benchmark</span>
trtllm-bench<span class="w"> </span>--model<span class="w"> </span><span class="si">${</span><span class="nv">MODEL_PATH</span><span class="si">}</span><span class="w"> </span><span class="se">\</span>
<span class="w"> </span>prepare-dataset<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>--output<span class="w"> </span>dataset.txt<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>token-norm-dist<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>--num-requests<span class="o">=</span><span class="si">${</span><span class="nv">NUM_SAMPLES</span><span class="si">}</span><span class="w"> </span><span class="se">\</span>
<span class="w"> </span>--input-mean<span class="o">=</span><span class="m">1000</span><span class="w"> </span>--output-mean<span class="o">=</span><span class="m">1000</span><span class="w"> </span>--input-stdev<span class="o">=</span><span class="m">0</span><span class="w"> </span>--output-stdev<span class="o">=</span><span class="m">0</span>
<span class="c1"># Benchmark and profile</span>
<span class="nv">TLLM_PROFILE_START_STOP</span><span class="o">=</span><span class="m">100</span>-150<span class="w"> </span>nsys<span class="w"> </span>profile<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>-o<span class="w"> </span>trace<span class="w"> </span>-f<span class="w"> </span><span class="nb">true</span><span class="w"> </span><span class="se">\</span>
<span class="w"> </span>-t<span class="w"> </span><span class="s1">&#39;cuda,nvtx,python-gil&#39;</span><span class="w"> </span>-c<span class="w"> </span>cudaProfilerApi<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>--cuda-graph-trace<span class="w"> </span>node<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>-e<span class="w"> </span><span class="nv">TLLM_PROFILE_RECORD_GC</span><span class="o">=</span><span class="m">1</span>,TLLM_LLMAPI_ENABLE_NVTX<span class="o">=</span><span class="m">1</span>,TLLM_TORCH_PROFILE_TRACE<span class="o">=</span>trace.json<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>--trace-fork-before-exec<span class="o">=</span><span class="nb">true</span><span class="w"> </span><span class="se">\</span>
<span class="w"> </span>trtllm-bench<span class="w"> </span><span class="se">\ </span><span class="c1"># or trtllm-serve command</span>
<span class="w"> </span>--model<span class="w"> </span>deepseek-ai/DeepSeek-V3<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>--model_path<span class="w"> </span><span class="si">${</span><span class="nv">MODEL_PATH</span><span class="si">}</span><span class="w"> </span><span class="se">\</span>
<span class="w"> </span>throughput<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>--dataset<span class="w"> </span>/tmp/dataset.txt<span class="w"> </span>--warmup<span class="w"> </span><span class="m">0</span><span class="w"> </span><span class="se">\</span>
<span class="w"> </span>--backend<span class="w"> </span>pytorch<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>--streaming
</pre></div>
</div>
<p>The Nsight Systems reports will be saved to <code class="docutils literal notranslate"><span class="pre">trace.nsys-rep</span></code>. Use NVIDIA Nsight Systems application to open it.</p>
<p>The PyTorch profiler results will be saved to <code class="docutils literal notranslate"><span class="pre">trace.json</span></code>. Use <a class="reference internal" href="#chrome://tracing/"><span class="xref myst">chrome://tracing/</span></a> to inspect the saved profile.</p>
</section>
</section>
<section id="moe-expert-load-balance-analysis-perfect-router">
<h2>MoE Expert Load Balance Analysis (Perfect Router)<a class="headerlink" href="#moe-expert-load-balance-analysis-perfect-router" title="Link to this heading">#</a></h2>
<p>For Mixture-of-Experts (MoE) models, performance can vary significantly based on how tokens are routed to experts. Uneven expert load distribution can cause some GPUs to be overloaded while others are underutilized, leading to suboptimal throughput.</p>
<p>TensorRT-LLM provides the <code class="docutils literal notranslate"><span class="pre">ENABLE_PERFECT_ROUTER</span></code> environment variable to help analyze and isolate expert load balancing issues from kernel performance.</p>
<section id="what-it-does">
<h3>What It Does<a class="headerlink" href="#what-it-does" title="Link to this heading">#</a></h3>
<p>When enabled, this feature <strong>bypasses the learned router</strong> and replaces it with pre-computed, perfectly load-balanced routing logits. This creates an idealized scenario where tokens are distributed evenly across all experts and GPUs.</p>
<p>Key behaviors:</p>
<ul class="simple">
<li><p>The learned gate/router is still computed (to maintain realistic timing)</p></li>
<li><p>The gate output is <strong>discarded</strong> and replaced with ideal balanced logits</p></li>
<li><p>Logits are pre-computed and cached for common batch sizes to minimize overhead</p></li>
<li><p>Works with all MoE backends (CUTLASS, TRTLLM, TRITON)</p></li>
</ul>
<div class="admonition warning">
<p class="admonition-title">Warning</p>
<p>This feature is for <strong>performance analysis only</strong>. It produces <strong>incorrect model outputs</strong> because the learned router decisions are discarded. Never use this in production inference.</p>
</div>
</section>
<section id="when-to-use-it">
<h3>When to Use It<a class="headerlink" href="#when-to-use-it" title="Link to this heading">#</a></h3>
<p>Use <code class="docutils literal notranslate"><span class="pre">ENABLE_PERFECT_ROUTER</span></code> when you want to:</p>
<ol class="arabic simple">
<li><p><strong>Establish performance upper bounds</strong>: Measure the theoretical best-case MoE throughput when expert loads are perfectly balanced.</p></li>
<li><p><strong>Isolate routing bottlenecks</strong>: Compare performance with vs. without perfect routing to determine if the learned router is causing load imbalance issues.</p></li>
<li><p><strong>Test different load balancing strategies</strong>: Validate that MoE kernels and communication patterns behave correctly with balanced loads before implementing custom routing logic.</p></li>
<li><p><strong>Benchmark kernel efficiency</strong>: Remove routing variability to get consistent, reproducible kernel performance measurements.</p></li>
</ol>
</section>
<section id="how-to-enable">
<h3>How to Enable<a class="headerlink" href="#how-to-enable" title="Link to this heading">#</a></h3>
<p>Set the environment variable before running your workload. This works with both <code class="docutils literal notranslate"><span class="pre">trtllm-bench</span></code> and <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code>:</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="nb">export</span><span class="w"> </span><span class="nv">ENABLE_PERFECT_ROUTER</span><span class="o">=</span><span class="m">1</span>
</pre></div>
</div>
</section>
<section id="example-workflow">
<h3>Example Workflow<a class="headerlink" href="#example-workflow" title="Link to this heading">#</a></h3>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Step 1: Benchmark with normal (learned) routing</span>
trtllm-bench<span class="w"> </span>...
<span class="c1"># or</span>
trtllm-serve<span class="w"> </span>...
<span class="c1"># Step 2: Benchmark with perfect routing (upper bound)</span>
<span class="nv">ENABLE_PERFECT_ROUTER</span><span class="o">=</span><span class="m">1</span><span class="w"> </span>trtllm-bench<span class="w"> </span>...
<span class="c1"># or</span>
<span class="nv">ENABLE_PERFECT_ROUTER</span><span class="o">=</span><span class="m">1</span><span class="w"> </span>trtllm-serve<span class="w"> </span>...
<span class="c1"># Step 3: Compare the throughput numbers</span>
<span class="c1"># If perfect router shows &gt;10% improvement, routing imbalance is significant</span>
</pre></div>
</div>
</section>
<section id="interpreting-results">
<h3>Interpreting Results<a class="headerlink" href="#interpreting-results" title="Link to this heading">#</a></h3>
<div class="pst-scrollable-table-container"><table class="table">
<thead>
<tr class="row-odd"><th class="head"><p>Scenario</p></th>
<th class="head"><p>Interpretation</p></th>
</tr>
</thead>
<tbody>
<tr class="row-even"><td><p>Similar performance with/without perfect router</p></td>
<td><p>Router load balancing is not a bottleneck; focus optimization efforts elsewhere</p></td>
</tr>
<tr class="row-odd"><td><p>Significant improvement with perfect router</p></td>
<td><p>The learned router is causing load imbalance; consider router optimization or load balancing strategies</p></td>
</tr>
</tbody>
</table>
</div>
</section>
<section id="supported-models">
<h3>Supported Models<a class="headerlink" href="#supported-models" title="Link to this heading">#</a></h3>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>This feature currently requires model-specific integration. The plumbing to support perfect routing must be added to each MoE model implementation. If you need this feature for a model that doesn’t yet support it, you will need to add the integration following the pattern used in existing implementations.</p>
</div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>The perfect router logits are specifically designed for <code class="docutils literal notranslate"><span class="pre">RenormalizeMoeRoutingMethod</span></code> (TopK first, then Softmax). Models using other routing methods such as <code class="docutils literal notranslate"><span class="pre">DefaultMoeRoutingMethod</span></code> or <code class="docutils literal notranslate"><span class="pre">DeepSeekV3MoeRoutingMethod</span></code> would require adapting the logit generation logic to match their routing behavior.</p>
</div>
<p>Currently supported:</p>
<ul class="simple">
<li><p>GPT-OSS (uses <code class="docutils literal notranslate"><span class="pre">RenormalizeMoeRoutingMethod</span></code>)</p></li>
</ul>
</section>
</section>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="overview.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">Architecture Overview</p>
</div>
</a>
<a class="right-next"
href="perf-benchmarking.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">TensorRT LLM Benchmarking</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="#feature-descriptions">Feature Descriptions</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#coordinating-with-nvidia-nsight-systems-launch">Coordinating with NVIDIA Nsight Systems Launch</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#only-collect-specific-iterations">Only collect specific iterations</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#enable-more-nvtx-markers-for-debugging">Enable more NVTX markers for debugging</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#enable-garbage-collection-gc-nvtx-markers">Enable garbage collection (GC) NVTX markers</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#enable-gil-information-in-nvtx-markers">Enable GIL information in NVTX markers</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#coordinating-with-pytorch-profiler-pytorch-workflow-only">Coordinating with PyTorch profiler (PyTorch workflow only)</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#collect-pytorch-profiler-results">Collect PyTorch profiler results</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#visualize-the-pytorch-profiler-results">Visualize the PyTorch profiler results</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#examples">Examples</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#profiling-specific-iterations-on-a-trtllm-bench-trtllm-serve-run">Profiling specific iterations on a <code class="docutils literal notranslate"><span class="pre">trtllm-bench</span></code>/<code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code> run</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#moe-expert-load-balance-analysis-perfect-router">MoE Expert Load Balance Analysis (Perfect Router)</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#what-it-does">What It Does</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#when-to-use-it">When to Use It</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#how-to-enable">How to Enable</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#example-workflow">Example Workflow</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#interpreting-results">Interpreting Results</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#supported-models">Supported Models</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/">Your Privacy Choices</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 January 04, 2026.</p>
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/a65b0d4">a65b0d4</a>.</p>
</div></div>
</div>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink