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
abcebb8ffa
TensorRT-LLMs/performance/performance-tuning-guide/useful-runtime-flags.html
Kaiyu Xie abcebb8ffa Update GitHub pages in root to v0.21.0rc2
2025-06-18 05:57:03 +00:00

880 lines
55 KiB
HTML
Raw Blame History

<!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>Useful Runtime Options &#8212; TensorRT-LLM</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!--
this give us a css class that will be invisible only if js is disabled
-->
<noscript>
<style>
.pst-js-only { display: none !important; }
</style>
</noscript>
<!-- Loaded before other Sphinx assets -->
<link href="../../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link href="../../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="../../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../../_static/styles/nvidia-sphinx-theme.css?v=df3ac72c" />
<link rel="stylesheet" type="text/css" href="../../_static/copybutton.css?v=76b2166b" />
<link rel="stylesheet" type="text/css" href="../../_static/autodoc_pydantic.css" />
<!-- So that users can add custom icons -->
<script src="../../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script>
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" />
<link rel="preload" as="script" href="../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" />
<script src="../../_static/documentation_options.js?v=5929fcd5"></script>
<script src="../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../../_static/copybutton.js?v=65e89d2a"></script>
<script>DOCUMENTATION_OPTIONS.pagename = 'performance/performance-tuning-guide/useful-runtime-flags';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '0.21.0rc2';
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="Performance Analysis" href="../perf-analysis.html" />
<link rel="prev" title="FP8 Quantization" href="fp8-quantization.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="0.21.0rc2" />
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<dialog id="pst-search-dialog">
<form class="bd-search d-flex align-items-center"
action="../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form>
</dialog>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
<div class="bd-header__inner bd-page-width">
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
<span class="fa-solid fa-bars"></span>
</button>
<div class="col-lg-3 navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="../../index.html">
<img src="../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
<img src="../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
<p class="title logo__title">TensorRT-LLM</p>
</a></div>
</div>
<div class="col-lg-9 navbar-header-items">
<div class="me-auto navbar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-2"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-2"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-2"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-2">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="navbar-header-items__end">
<div class="navbar-item navbar-persistent--container">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="navbar-persistent--mobile">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
<button class="pst-navbar-icon sidebar-toggle secondary-toggle" aria-label="On this page">
<span class="fa-solid fa-outdent"></span>
</button>
</div>
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<dialog id="pst-primary-sidebar-modal"></dialog>
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
<a class="navbar-brand logo" href="../../index.html">
<img src="../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
<img src="../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
<p class="title logo__title">TensorRT-LLM</p>
</a>
<div class="sidebar-header-items sidebar-primary__section">
<div class="sidebar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-3"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-3"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-3"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-3">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="sidebar-header-items__end">
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<nav class="bd-docs-nav bd-links"
aria-label="Table of Contents">
<p class="bd-links__title" role="heading" aria-level="1">Table of Contents</p>
<div class="bd-toc-item navbar-nav"><p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../quick-start-guide.html">Quick Start Guide</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../key-features.html">Key Features</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../torch.html">PyTorch Backend</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../release-notes.html">Release Notes</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Installation</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../installation/linux.html">Installing on Linux</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../installation/grace-hopper.html">Installing on Grace Hopper</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">LLM API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../llm-api/index.html">API Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../llm-api/reference.html">API Reference</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Examples</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1 has-children"><a class="reference internal" href="../../examples/index.html">LLM Examples Introduction</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_medusa_decoding.html">Generate Text Using Medusa Decoding</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_eagle_decoding.html">Generate Text Using Eagle Decoding</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_distributed.html">Distributed LLM Generation</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_eagle2_decoding.html">Generate Text Using Eagle2 Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_inference_kv_events.html">Get KV Cache Events</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_quantization.html">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_inference_async_streaming.html">Generate Text in Streaming</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_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_inference_customize.html">Generate text with customization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../examples/customization.html">LLM Common Customizations</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../examples/llm_api_examples.html">LLM Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_medusa_decoding.html">Generate Text Using Medusa Decoding</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_eagle_decoding.html">Generate Text Using Eagle Decoding</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_distributed.html">Distributed LLM Generation</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_eagle2_decoding.html">Generate Text Using Eagle2 Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_inference_kv_events.html">Get KV Cache Events</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_quantization.html">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_inference_async_streaming.html">Generate Text in Streaming</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_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_inference_customize.html">Generate text with customization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
</ul>
</details></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../examples/trtllm_serve_examples.html">Online Serving Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../examples/curl_chat_client.html">Curl Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/curl_completion_client.html">Curl Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/genai_perf_client.html">Genai Perf Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/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</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Model Definition API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../python-api/tensorrt_llm.layers.html">Layers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../python-api/tensorrt_llm.functional.html">Functionals</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../python-api/tensorrt_llm.models.html">Models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../python-api/tensorrt_llm.plugin.html">Plugin</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../python-api/tensorrt_llm.quantization.html">Quantization</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../python-api/tensorrt_llm.runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">C++ API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../_cpp_gen/executor.html">Executor</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../_cpp_gen/runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../commands/trtllm-build.html">trtllm-build</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../commands/trtllm-serve.html">trtllm-serve</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Architecture</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../architecture/overview.html">TensorRT-LLM Architecture</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../architecture/core-concepts.html">Model Definition</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../architecture/checkpoint.html">TensorRT-LLM Checkpoint</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../architecture/workflow.html">TensorRT-LLM Build Workflow</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../architecture/add-model.html">Adding a Model</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Advanced</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../advanced/gpt-attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../advanced/gpt-runtime.html">C++ GPT Runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../advanced/executor.html">Executor API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../advanced/graph-rewriting.html">Graph Rewriting Module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../advanced/lora.html">Run gpt-2b + LoRA using Executor / cpp runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../advanced/expert-parallelism.html">Expert Parallelism in TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../advanced/kv-cache-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 (experimental)</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Performance</span></p>
<ul class="current nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../perf-overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../perf-benchmarking.html">Benchmarking</a></li>
<li class="toctree-l1 current active has-children"><a class="reference internal" href="index.html">Performance Tuning Guide</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="benchmarking-default-performance.html">Benchmarking Default Performance</a></li>
<li class="toctree-l2"><a class="reference internal" href="useful-build-time-flags.html">Useful Build-Time Flags</a></li>
<li class="toctree-l2"><a class="reference internal" href="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="deciding-model-sharding-strategy.html">Deciding Model Sharding Strategy</a></li>
<li class="toctree-l2"><a class="reference internal" href="fp8-quantization.html">FP8 Quantization</a></li>
<li class="toctree-l2 current active"><a class="current reference internal" href="#">Useful Runtime Options</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../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>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../blogs/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../blogs/H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../blogs/Falcon180B-H200.html">Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../blogs/quantization-in-TRT-LLM.html">Speed up inference with SOTA quantization techniques in TRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../blogs/XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html">Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs</a></li>
<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>
</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"><a href="index.html" class="nav-link">Performance Tuning Guide</a></li>
<li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">Useful Runtime Options</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="useful-runtime-options">
<span id="useful-runtime-flags"></span><h1>Useful Runtime Options<a class="headerlink" href="#useful-runtime-options" title="Link to this heading">#</a></h1>
<p>This part summarizes the runtime configuration knobs that can be tweaked to
enhance the performance of already built engines. As compared to previous examples where
the LLM-API was used to build and save an engine but not to process any requests,
runtime knobs would be specified when you are using the LLM-API to actually run inference
like in the <a class="reference internal" href="benchmarking-default-performance.html#before-you-begin-tensorrt-llm-llm-api"><span class="std std-ref">LLM-API end-to-end example</span></a></p>
<section id="capacity-scheduler-policy">
<h2>Capacity Scheduler Policy<a class="headerlink" href="#capacity-scheduler-policy" title="Link to this heading">#</a></h2>
<p>TensorRT-LLM currently supports three batch scheduler policies: <code class="docutils literal notranslate"><span class="pre">GUARANTEED_NO_EVICT</span></code> (default),
<code class="docutils literal notranslate"><span class="pre">MAX_UTILIZATION</span></code> and <code class="docutils literal notranslate"><span class="pre">STATIC_BATCH</span></code>.</p>
<p>The scheduling policy can be set to <code class="docutils literal notranslate"><span class="pre">MAX_UTILIZATION</span></code> to pack as many
requests as possible at each iteration of the forward loop, when in-flight
sequence batching is enabled. It maximizes the utilization of the GPUs by
aggressively scheduling requests at the risk of having to pause requests if the
KV cache size limit is reached.</p>
<p>For a more conservative approach with respect to the KV cache limitations in
terms of memory allocation, <code class="docutils literal notranslate"><span class="pre">CapacitySchedulerPolicy</span></code> should be set to
<code class="docutils literal notranslate"><span class="pre">GUARANTEED_NO_EVICT</span></code> to guarantee that a started request is never paused.</p>
<p>If the goal is to maximizes the throughput, users should try <code class="docutils literal notranslate"><span class="pre">MAX_UTILIZATION</span></code>.
However, they need to keep in mind that it may have a negative impact on
latency if requests have to be paused.</p>
<p><code class="docutils literal notranslate"><span class="pre">STATIC_BATCH</span></code> is a legacy mode and is not recommended for production usage.</p>
<p>To switch the capacity scheduler policy from the default of <code class="docutils literal notranslate"><span class="pre">GUARANTEED_NO_EVICT</span></code> to <code class="docutils literal notranslate"><span class="pre">MAX_UTILIZATION</span></code>
you would modify the <a class="reference internal" href="benchmarking-default-performance.html#before-you-begin-tensorrt-llm-llm-api"><span class="std std-ref">LLM-API end-to-end example</span></a> to be:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm</span><span class="w"> </span><span class="kn">import</span> <span class="n">LLM</span><span class="p">,</span> <span class="n">SamplingParams</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.bindings.executor</span><span class="w"> </span><span class="kn">import</span> <span class="n">SchedulerConfig</span><span class="p">,</span> <span class="n">CapacitySchedulerPolicy</span>
<span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
<span class="n">prompts</span> <span class="o">=</span> <span class="p">[</span>
<span class="s2">&quot;Hello, I am&quot;</span><span class="p">,</span>
<span class="s2">&quot;The president of the United States is&quot;</span><span class="p">,</span>
<span class="s2">&quot;The capital of France is&quot;</span><span class="p">,</span>
<span class="s2">&quot;The future of AI is&quot;</span><span class="p">,</span>
<span class="p">]</span>
<span class="n">sampling_params</span> <span class="o">=</span> <span class="n">SamplingParams</span><span class="p">(</span><span class="n">temperature</span><span class="o">=</span><span class="mf">0.8</span><span class="p">,</span> <span class="n">top_p</span><span class="o">=</span><span class="mf">0.95</span><span class="p">)</span>
<span class="n">scheduler_config</span> <span class="o">=</span> <span class="n">SchedulerConfig</span><span class="p">(</span>
<span class="n">capacity_scheduler_policy</span><span class="o">=</span><span class="n">CapacitySchedulerPolicy</span><span class="o">.</span><span class="n">MAX_UTILIZATION</span>
<span class="p">)</span>
<span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span>
<span class="n">model</span><span class="o">=</span><span class="s2">&quot;meta-llama/Llama-3.3-70B-Instruct&quot;</span><span class="p">,</span>
<span class="n">tensor_parallel_size</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span>
<span class="n">scheduler_config</span><span class="o">=</span><span class="n">scheduler_config</span>
<span class="p">)</span>
<span class="n">outputs</span> <span class="o">=</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate</span><span class="p">(</span><span class="n">prompts</span><span class="p">,</span> <span class="n">sampling_params</span><span class="p">)</span>
<span class="c1"># Print the outputs.</span>
<span class="k">for</span> <span class="n">output</span> <span class="ow">in</span> <span class="n">outputs</span><span class="p">:</span>
<span class="n">prompt</span> <span class="o">=</span> <span class="n">output</span><span class="o">.</span><span class="n">prompt</span>
<span class="n">generated_text</span> <span class="o">=</span> <span class="n">output</span><span class="o">.</span><span class="n">outputs</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">text</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Prompt: </span><span class="si">{</span><span class="n">prompt</span><span class="si">!r}</span><span class="s2">, Generated text: </span><span class="si">{</span><span class="n">generated_text</span><span class="si">!r}</span><span class="s2">&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">&#39;__main__&#39;</span><span class="p">:</span>
<span class="n">main</span><span class="p">()</span>
</pre></div>
</div>
</section>
<section id="context-chunking-policy">
<h2>Context Chunking Policy<a class="headerlink" href="#context-chunking-policy" title="Link to this heading">#</a></h2>
<p>As discussed <a class="reference internal" href="tuning-max-batch-size-and-max-num-tokens.html#revisiting-paged-context-attention-and-context-chunking"><span class="std std-ref">previously</span></a> context chunking will increase the chance of batch processing between
the context and the generation phase, thereby balancing the calculation amount
of each iteration and typically increasing throughput.</p>
<p>TensorRT-LLM currently supports two context chunking policies: <code class="docutils literal notranslate"><span class="pre">FIRST_COME_FIRST_SERVED</span></code> (default) which would prioritize scheduling all the context chunks of a request that comes in first,
and <code class="docutils literal notranslate"><span class="pre">EQUAL_PROGRESS</span></code> which schedules context chunks from all requests before scheduling the next chunk of any request.</p>
<p><code class="docutils literal notranslate"><span class="pre">FIRST_COME_FIRST_SERVED</span></code> should achieve overall better performance, while
<code class="docutils literal notranslate"><span class="pre">EQUAL_PROGRESS</span></code> can be helpful in theory to make sure time to first token (TTFT)
for most requests are relatively similar.</p>
<p>To switch the context chunking policy from the default of <code class="docutils literal notranslate"><span class="pre">FIRST_COME_FIRST_SERVED</span></code> to <code class="docutils literal notranslate"><span class="pre">EQUAL_PROGRESS</span></code>
you would modify the <a class="reference internal" href="benchmarking-default-performance.html#before-you-begin-tensorrt-llm-llm-api"><span class="std std-ref">LLM-API end-to-end example</span></a> to be:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm</span><span class="w"> </span><span class="kn">import</span> <span class="n">LLM</span><span class="p">,</span> <span class="n">SamplingParams</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.bindings.executor</span><span class="w"> </span><span class="kn">import</span> <span class="n">SchedulerConfig</span><span class="p">,</span> <span class="n">ContextChunkingPolicy</span>
<span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
<span class="n">prompts</span> <span class="o">=</span> <span class="p">[</span>
<span class="s2">&quot;Hello, I am&quot;</span><span class="p">,</span>
<span class="s2">&quot;The president of the United States is&quot;</span><span class="p">,</span>
<span class="s2">&quot;The capital of France is&quot;</span><span class="p">,</span>
<span class="s2">&quot;The future of AI is&quot;</span><span class="p">,</span>
<span class="p">]</span>
<span class="n">sampling_params</span> <span class="o">=</span> <span class="n">SamplingParams</span><span class="p">(</span><span class="n">temperature</span><span class="o">=</span><span class="mf">0.8</span><span class="p">,</span> <span class="n">top_p</span><span class="o">=</span><span class="mf">0.95</span><span class="p">)</span>
<span class="n">scheduler_config</span> <span class="o">=</span> <span class="n">SchedulerConfig</span><span class="p">(</span>
<span class="n">context_chunking_policy</span><span class="o">=</span><span class="n">ContextChunkingPolicy</span><span class="o">.</span><span class="n">EQUAL_PROGRESS</span>
<span class="p">)</span>
<span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span>
<span class="n">model</span><span class="o">=</span><span class="s2">&quot;meta-llama/Llama-3.3-70B-Instruct&quot;</span><span class="p">,</span>
<span class="n">tensor_parallel_size</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span>
<span class="n">scheduler_config</span><span class="o">=</span><span class="n">scheduler_config</span>
<span class="p">)</span>
<span class="n">outputs</span> <span class="o">=</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate</span><span class="p">(</span><span class="n">prompts</span><span class="p">,</span> <span class="n">sampling_params</span><span class="p">)</span>
<span class="c1"># Print the outputs.</span>
<span class="k">for</span> <span class="n">output</span> <span class="ow">in</span> <span class="n">outputs</span><span class="p">:</span>
<span class="n">prompt</span> <span class="o">=</span> <span class="n">output</span><span class="o">.</span><span class="n">prompt</span>
<span class="n">generated_text</span> <span class="o">=</span> <span class="n">output</span><span class="o">.</span><span class="n">outputs</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">text</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Prompt: </span><span class="si">{</span><span class="n">prompt</span><span class="si">!r}</span><span class="s2">, Generated text: </span><span class="si">{</span><span class="n">generated_text</span><span class="si">!r}</span><span class="s2">&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">&#39;__main__&#39;</span><span class="p">:</span>
<span class="n">main</span><span class="p">()</span>
</pre></div>
</div>
</section>
<section id="max-tokens-in-paged-kv-cache-and-kv-cache-free-gpu-memory-fraction">
<h2>Max Tokens in Paged KV Cache and KV Cache Free GPU Memory Fraction<a class="headerlink" href="#max-tokens-in-paged-kv-cache-and-kv-cache-free-gpu-memory-fraction" title="Link to this heading">#</a></h2>
<p>The <code class="docutils literal notranslate"><span class="pre">max_tokens_in_paged_kv_cache</span></code> and <code class="docutils literal notranslate"><span class="pre">kv_cache_free_gpu_mem_fraction</span></code>
parameters can be used to control the maximum number of tokens handled by the
KV cache manager. Setting them properly helps better control the amount of
available memory for the KV cache manager during inference. Keeping in mind
that increasing the amount of memory available to the KV cache manager tends to
translate to a higher achievable throughput.</p>
<p>The <code class="docutils literal notranslate"><span class="pre">max_tokens_in_paged_kv_cache</span></code> flag directly sets the maximum number of
tokens in the KV cache manager. When left unset, that value will be computed
based on the <code class="docutils literal notranslate"><span class="pre">kv_cache_free_gpu_mem_fraction</span></code> setting.</p>
<p>The <code class="docutils literal notranslate"><span class="pre">kv_cache_free_gpu_mem_fraction</span></code> is a floating-point number between <code class="docutils literal notranslate"><span class="pre">0.0</span></code>
and <code class="docutils literal notranslate"><span class="pre">1.0</span></code> that indicates the maximum fraction of GPU memory (after loading the
model) that will be used for the KV cache. The default value is <code class="docutils literal notranslate"><span class="pre">0.90</span></code> and
means that 90% of the free GPU memory will be used to save tokens in the KV
cache. Based on that value, TensorRT-LLM can determine the maximum number of
tokens in the KV cache manager.</p>
<p>When both parameters are set, the maximum number of tokens in the KV cache
manager will be set to the smaller value between <code class="docutils literal notranslate"><span class="pre">max_tokens_in_paged_kv_cache</span></code>
and the value computed from the amount of memory available for the KV cache.</p>
<p>Unless users clearly know the maximum number of tokens in the KV cache needed
by the model, it is recommended to leave <code class="docutils literal notranslate"><span class="pre">max_tokens_in_paged_kv_cache</span></code> unset.
For <code class="docutils literal notranslate"><span class="pre">kv_cache_free_gpu_mem_fraction</span></code>, if no other programs are executed on the
same GPU, it is recommended to test with a as high value as <code class="docutils literal notranslate"><span class="pre">0.95</span></code> to target a
high throughput. Note that the <code class="docutils literal notranslate"><span class="pre">kv_cache_free_gpu_mem_fraction</span></code> parameter
cannot be set to <code class="docutils literal notranslate"><span class="pre">1.0</span></code> because some amount of memory has to be reserved for
inputs and outputs.</p>
<p>To set <code class="docutils literal notranslate"><span class="pre">kv_cache_free_gpu_mem_fraction</span></code> you would modify the <a class="reference internal" href="benchmarking-default-performance.html#before-you-begin-tensorrt-llm-llm-api"><span class="std std-ref">LLM-API end-to-end example</span></a> to be:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm</span><span class="w"> </span><span class="kn">import</span> <span class="n">LLM</span><span class="p">,</span> <span class="n">SamplingParams</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.bindings.executor</span><span class="w"> </span><span class="kn">import</span> <span class="n">KvCacheConfig</span>
<span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
<span class="n">prompts</span> <span class="o">=</span> <span class="p">[</span>
<span class="s2">&quot;Hello, I am&quot;</span><span class="p">,</span>
<span class="s2">&quot;The president of the United States is&quot;</span><span class="p">,</span>
<span class="s2">&quot;The capital of France is&quot;</span><span class="p">,</span>
<span class="s2">&quot;The future of AI is&quot;</span><span class="p">,</span>
<span class="p">]</span>
<span class="n">sampling_params</span> <span class="o">=</span> <span class="n">SamplingParams</span><span class="p">(</span><span class="n">temperature</span><span class="o">=</span><span class="mf">0.8</span><span class="p">,</span> <span class="n">top_p</span><span class="o">=</span><span class="mf">0.95</span><span class="p">)</span>
<span class="n">kv_cache_config</span> <span class="o">=</span> <span class="n">KvCacheConfig</span><span class="p">(</span><span class="n">free_gpu_memory_fraction</span><span class="o">=</span><span class="mf">0.95</span><span class="p">)</span>
<span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span>
<span class="n">model</span><span class="o">=</span><span class="s2">&quot;meta-llama/Llama-3.3-70B-Instruct&quot;</span><span class="p">,</span>
<span class="n">tensor_parallel_size</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span>
<span class="n">kv_cache_config</span><span class="o">=</span><span class="n">kv_cache_config</span>
<span class="p">)</span>
<span class="n">outputs</span> <span class="o">=</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate</span><span class="p">(</span><span class="n">prompts</span><span class="p">,</span> <span class="n">sampling_params</span><span class="p">)</span>
<span class="c1"># Print the outputs.</span>
<span class="k">for</span> <span class="n">output</span> <span class="ow">in</span> <span class="n">outputs</span><span class="p">:</span>
<span class="n">prompt</span> <span class="o">=</span> <span class="n">output</span><span class="o">.</span><span class="n">prompt</span>
<span class="n">generated_text</span> <span class="o">=</span> <span class="n">output</span><span class="o">.</span><span class="n">outputs</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">text</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Prompt: </span><span class="si">{</span><span class="n">prompt</span><span class="si">!r}</span><span class="s2">, Generated text: </span><span class="si">{</span><span class="n">generated_text</span><span class="si">!r}</span><span class="s2">&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">&#39;__main__&#39;</span><span class="p">:</span>
<span class="n">main</span><span class="p">()</span>
</pre></div>
</div>
<p>If you wanted to set <code class="docutils literal notranslate"><span class="pre">max_tokens_in_paged_kv_cache</span></code> instead, you would replace <code class="docutils literal notranslate"><span class="pre">free_gpu_memory_fraction</span></code> with <code class="docutils literal notranslate"><span class="pre">max_tokens</span></code> and specify the number.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span> <span class="n">kv_cache_config</span> <span class="o">=</span> <span class="n">KvCacheConfig</span><span class="p">(</span><span class="n">max_tokens</span><span class="o">=&lt;</span><span class="n">number</span> <span class="n">of</span> <span class="n">tokens</span><span class="o">&gt;</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="maximum-attention-window-size">
<h2>Maximum Attention Window Size<a class="headerlink" href="#maximum-attention-window-size" title="Link to this heading">#</a></h2>
<p>The <code class="docutils literal notranslate"><span class="pre">max_attention_window_size</span></code> flag sets the maximum number of tokens that are
attended to in order to generate one token when using techniques like sliding window
attention. See this
<a class="reference internal" href="../../advanced/gpt-attention.html#sliding-window-attention-cyclic-rolling-buffer-kv-cache"><span class="std std-ref">Document</span></a>
for more details. It defaults to the maximum sequence length
(<code class="docutils literal notranslate"><span class="pre">max_seq_len</span></code> when building the engine), which means
that the feature is disabled by default.</p>
<p>When set to a smaller value than <code class="docutils literal notranslate"><span class="pre">max_seq_len</span></code> (during
engine build), only the KV cache of the last <code class="docutils literal notranslate"><span class="pre">max_attention_window_size</span></code> tokens
will be stored. If the input sequence length at runtime exceeds the
<code class="docutils literal notranslate"><span class="pre">max_attention_window_size</span></code> value, the accuracy may start dropping, but the
runtime performance will be better (due to the reduction in terms of
computations and GPU memory allocation). Users can modify that value to
increase runtime performance at the expense of reduced accuracy.</p>
<p>Just like <a class="reference internal" href="#max-tokens-in-paged-kv-cache-and-kv-cache-free-gpu-memory-fraction"><span class="std std-ref"><code class="docutils literal notranslate"><span class="pre">kv_cache_free_gpu_mem_fraction</span></code></span></a>, <code class="docutils literal notranslate"><span class="pre">max_attention_window_size</span></code> can be specified in the LLM-API
via <code class="docutils literal notranslate"><span class="pre">KVCacheConfig</span></code>. To specify <code class="docutils literal notranslate"><span class="pre">max_attention_window_size</span></code> you would instantiate <code class="docutils literal notranslate"><span class="pre">KVCacheConfig</span></code> like so</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span> <span class="n">kv_cache_config</span> <span class="o">=</span> <span class="n">KvCacheConfig</span><span class="p">(</span><span class="n">max_attention_window</span><span class="o">=&lt;</span><span class="n">number</span> <span class="n">of</span> <span class="n">tokens</span><span class="o">&gt;</span><span class="p">)</span>
</pre></div>
</div>
</section>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="fp8-quantization.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">FP8 Quantization</p>
</div>
</a>
<a class="right-next"
href="../perf-analysis.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Performance Analysis</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="#capacity-scheduler-policy">Capacity Scheduler Policy</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#context-chunking-policy">Context Chunking Policy</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#max-tokens-in-paged-kv-cache-and-kv-cache-free-gpu-memory-fraction">Max Tokens in Paged KV Cache and KV Cache Free GPU Memory Fraction</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#maximum-attention-window-size">Maximum Attention Window Size</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 June 16, 2025.</p>
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/8445416">8445416</a>.</p>
</div></div>
</div>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink