mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-13 22:18:36 +08:00
| .. | ||
| README.html | ||
<!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>Disaggregated Inference Benchmark Scripts — TensorRT-LLM</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!--
this give us a css class that will be invisible only if js is disabled
-->
<noscript>
<style>
.pst-js-only { display: none !important; }
</style>
</noscript>
<!-- Loaded before other Sphinx assets -->
<link href="../../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link href="../../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="../../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../../_static/styles/nvidia-sphinx-theme.css?v=df3ac72c" />
<link rel="stylesheet" type="text/css" href="../../_static/copybutton.css?v=76b2166b" />
<link rel="stylesheet" type="text/css" href="../../_static/autodoc_pydantic.css" />
<link rel="stylesheet" type="text/css" href="../../_static/togglebutton.css?v=13237357" />
<!-- So that users can add custom icons -->
<script src="../../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script>
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" />
<link rel="preload" as="script" href="../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" />
<script src="../../_static/documentation_options.js?v=5929fcd5"></script>
<script src="../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../../_static/copybutton.js?v=65e89d2a"></script>
<script>let toggleHintShow = 'Click to show';</script>
<script>let toggleHintHide = 'Click to hide';</script>
<script>let toggleOpenOnPrint = 'true';</script>
<script src="../../_static/togglebutton.js?v=4a39c7ea"></script>
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
<script>DOCUMENTATION_OPTIONS.pagename = 'scripts/disaggregated/README';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.0.0rc4';
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" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="1.0.0rc4" />
</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/containers.html">Pre-built release container images on NGC</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../installation/linux.html">Installing on Linux via <code class="docutils literal notranslate"><span class="pre">pip</span></code></a></li>
<li class="toctree-l1"><a class="reference internal" href="../../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">LLM API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../llm-api/index.html">LLM API Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../llm-api/reference.html">API Reference</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Examples</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1 has-children"><a class="reference internal" href="../../examples/index.html">LLM Examples Introduction</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="simple">
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../examples/customization.html">LLM Common Customizations</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../examples/llm_api_examples.html">LLM Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_inference_async.html">Generate text asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_inference_async_streaming.html">Generate text in streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_logits_processor.html">Control generated text using logits processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_speculative_decoding.html">Speculative Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_runtime.html">Runtime Configuration Examples</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_sampling.html">Sampling Techniques Showcase</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_mgmn_llm_distributed.html">Run LLM-API with pytorch backend on Slurm</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_mgmn_trtllm_bench.html">Run trtllm-bench with pytorch backend on Slurm</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/llm_mgmn_trtllm_serve.html">Run trtllm-serve with pytorch backend on Slurm</a></li>
</ul>
</details></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../examples/trtllm_serve_examples.html">Online Serving Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../examples/curl_chat_client.html">Curl Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/curl_completion_client.html">Curl Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/genai_perf_client.html">Genai Perf Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/genai_perf_client_for_multimodal.html">Genai Perf Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/openai_chat_client.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/openai_chat_client_for_multimodal.html">OpenAI Chat Client for Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../examples/openai_completion_client_for_lora.html">Openai Completion Client For Lora</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Model Definition API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../python-api/tensorrt_llm.layers.html">Layers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../python-api/tensorrt_llm.functional.html">Functionals</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../python-api/tensorrt_llm.models.html">Models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../python-api/tensorrt_llm.plugin.html">Plugin</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../python-api/tensorrt_llm.quantization.html">Quantization</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../python-api/tensorrt_llm.runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">C++ API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../_cpp_gen/executor.html">Executor</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../_cpp_gen/runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../commands/trtllm-bench.html">trtllm-bench</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../commands/trtllm-build.html">trtllm-build</a></li>
<li class="toctree-l1"><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="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../performance/perf-overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../performance/perf-benchmarking.html">Benchmarking</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../performance/performance-tuning-guide/index.html">Performance Tuning Guide</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../performance/performance-tuning-guide/benchmarking-default-performance.html">Benchmarking Default Performance</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../performance/performance-tuning-guide/useful-build-time-flags.html">Useful Build-Time Flags</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.html">Tuning Max Batch Size and Max Num Tokens</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../performance/performance-tuning-guide/deciding-model-sharding-strategy.html">Deciding Model Sharding Strategy</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../performance/performance-tuning-guide/fp8-quantization.html">FP8 Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../performance/performance-tuning-guide/useful-runtime-flags.html">Useful Runtime Options</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../performance/perf-analysis.html">Performance Analysis</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../reference/troubleshooting.html">Troubleshooting</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../reference/support-matrix.html">Support Matrix</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../reference/precision.html">Numerical Precision</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../reference/memory.html">Memory Usage of TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../reference/ci-overview.html">Continuous Integration Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../reference/dev-containers.html">Using Dev Containers</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../blogs/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../blogs/H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../blogs/Falcon180B-H200.html">Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../blogs/quantization-in-TRT-LLM.html">Speed up inference with SOTA quantization techniques in TRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../blogs/XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../blogs/tech_blog/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 active" aria-current="page"><span class="ellipsis">Disaggregated Inference Benchmark Scripts</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="disaggregated-inference-benchmark-scripts">
<h1>Disaggregated Inference Benchmark Scripts<a class="headerlink" href="#disaggregated-inference-benchmark-scripts" title="Link to this heading">#</a></h1>
<p>This directory contains scripts to run disaggregated inference benchmarks using TensorRT-LLM and SLURM.</p>
<section id="overview">
<h2>Overview<a class="headerlink" href="#overview" title="Link to this heading">#</a></h2>
<p>The benchmarking process is orchestrated through a set of shell scripts and a Python script that work together:</p>
<ol class="arabic simple">
<li><p><code class="docutils literal notranslate"><span class="pre">submit.sh</span></code>: The main entry point for submitting benchmark jobs to SLURM. It runs a parameter sweep by calling <code class="docutils literal notranslate"><span class="pre">sbatch</span></code> with different configurations.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">disaggr_torch.slurm</span></code>: The SLURM script that sets up and runs a single benchmark experiment. It launches a container, generates a configuration file, starts the server and workers, and runs the benchmark client.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">gen_yaml.py</span></code>: A Python script that generates the <code class="docutils literal notranslate"><span class="pre">config.yaml</span></code> file needed by <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code>. It determines the server and worker configuration based on SLURM environment variables and script arguments.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">start_worker.sh</span></code>: A shell script responsible for starting a <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span> <span class="pre">disaggregated_mpi_worker</span></code> on each allocated machine.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">run_benchmark.sh</span></code>: A shell script that waits for the server to be healthy and then runs the actual benchmark client (<code class="docutils literal notranslate"><span class="pre">run_benchmark.py</span></code>, not included in this directory).</p></li>
</ol>
</section>
<section id="file-descriptions">
<h2>File Descriptions<a class="headerlink" href="#file-descriptions" title="Link to this heading">#</a></h2>
<section id="submit-sh">
<h3><code class="docutils literal notranslate"><span class="pre">submit.sh</span></code><a class="headerlink" href="#submit-sh" title="Link to this heading">#</a></h3>
<p>This script is used to submit multiple SLURM jobs for running benchmarks with different parameters. It iterates through various configurations and uses <code class="docutils literal notranslate"><span class="pre">sbatch</span></code> to submit <code class="docutils literal notranslate"><span class="pre">disaggr_torch.slurm</span></code> for each one.</p>
<p><strong>Usage:</strong></p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>./submit.sh
</pre></div>
</div>
<p>You can modify the loops in this script to change the parameter space for the benchmark sweep.</p>
</section>
<section id="disaggr-torch-slurm">
<h3><code class="docutils literal notranslate"><span class="pre">disaggr_torch.slurm</span></code><a class="headerlink" href="#disaggr-torch-slurm" title="Link to this heading">#</a></h3>
<p>This is the core SLURM script for a single benchmark run. It is not meant to be run directly, but rather submitted via <code class="docutils literal notranslate"><span class="pre">sbatch</span></code> (e.g., by <code class="docutils literal notranslate"><span class="pre">submit.sh</span></code>).</p>
<p>It takes the following arguments in order:</p>
<ol class="arabic simple">
<li><p><code class="docutils literal notranslate"><span class="pre">num_ctx_servers</span></code>: Number of context servers.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">ctx_tp_size</span></code>: Tensor parallel size for context servers.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">ctx_batch_size</span></code>: Max batch size for context servers.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">ctx_max_num_tokens</span></code>: Max number of tokens for context servers.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">ctx_enable_attention_dp</span></code>: <code class="docutils literal notranslate"><span class="pre">true</span></code> or <code class="docutils literal notranslate"><span class="pre">false</span></code> to enable attention DP for context servers.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">num_gen_servers</span></code>: Number of generation servers.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">gen_tp_size</span></code>: Tensor parallel size for generation servers.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">gen_batch_size</span></code>: Max batch size for generation servers.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">gen_max_num_tokens</span></code>: Max number of tokens for generation servers.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">gen_enable_attention_dp</span></code>: <code class="docutils literal notranslate"><span class="pre">true</span></code> or <code class="docutils literal notranslate"><span class="pre">false</span></code> to enable attention DP for generation servers.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">gen_gpu_memory_fraction</span></code>: GPU memory fraction for generation servers.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">concurrency_list</span></code>: A space-separated list of concurrencies to test (e.g., “1 2 4 8”).</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">sub_file</span></code>: A subdirectory name for logs.</p></li>
</ol>
</section>
<section id="gen-yaml-py">
<h3><code class="docutils literal notranslate"><span class="pre">gen_yaml.py</span></code><a class="headerlink" href="#gen-yaml-py" title="Link to this heading">#</a></h3>
<p>This Python script generates the <code class="docutils literal notranslate"><span class="pre">config.yaml</span></code> file that configures the <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code> application. It reads SLURM environment variables (<code class="docutils literal notranslate"><span class="pre">SLURM_JOB_NODELIST</span></code>, <code class="docutils literal notranslate"><span class="pre">SLURM_TASKS_PER_NODE</span></code>) to distribute workers across nodes.</p>
<p><strong>Usage:</strong></p>
<p>The script is called from within <code class="docutils literal notranslate"><span class="pre">disaggr_torch.slurm</span></code>. It takes numerous arguments to define the model, parallelism, and server configurations.</p>
</section>
<section id="start-worker-sh">
<h3><code class="docutils literal notranslate"><span class="pre">start_worker.sh</span></code><a class="headerlink" href="#start-worker-sh" title="Link to this heading">#</a></h3>
<p>This script starts a <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span> <span class="pre">disaggregated_mpi_worker</span></code>. It is launched by <code class="docutils literal notranslate"><span class="pre">srun</span></code> from the <code class="docutils literal notranslate"><span class="pre">disaggr_torch.slurm</span></code> script on all allocated nodes.</p>
<p><strong>Arguments:</strong></p>
<ol class="arabic simple">
<li><p><code class="docutils literal notranslate"><span class="pre">config_file</span></code>: Path to the <code class="docutils literal notranslate"><span class="pre">config.yaml</span></code> file.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">enable_pdl</span></code>: <code class="docutils literal notranslate"><span class="pre">true</span></code> or <code class="docutils literal notranslate"><span class="pre">false</span></code>.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">ctx_gpus</span></code>: Number of GPUs used for the context phase.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">work_dir</span></code>: (Optional) Directory to store nsys profiling output.</p></li>
</ol>
</section>
<section id="run-benchmark-sh">
<h3><code class="docutils literal notranslate"><span class="pre">run_benchmark.sh</span></code><a class="headerlink" href="#run-benchmark-sh" title="Link to this heading">#</a></h3>
<p>This script orchestrates the execution of the benchmark client. It waits for the <code class="docutils literal notranslate"><span class="pre">config.yaml</span></code> to be created and for the server’s <code class="docutils literal notranslate"><span class="pre">/health</span></code> endpoint to respond, then it runs the benchmark.</p>
<p><strong>Arguments:</strong></p>
<ol class="arabic simple">
<li><p><code class="docutils literal notranslate"><span class="pre">isl</span></code>: Input sequence length.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">osl</span></code>: Output sequence length.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">multi_round</span></code>: Number of rounds for the benchmark.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">model_name</span></code>: Name of the model being benchmarked.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">concurrency_list</span></code>: Space-separated list of concurrencies.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">streaming</span></code>: <code class="docutils literal notranslate"><span class="pre">true</span></code> or <code class="docutils literal notranslate"><span class="pre">false</span></code>.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">log_path</span></code>: Path to the log directory.</p></li>
</ol>
</section>
</section>
<section id="workflow">
<h2>Workflow<a class="headerlink" href="#workflow" title="Link to this heading">#</a></h2>
<ol class="arabic simple">
<li><p>The user runs <code class="docutils literal notranslate"><span class="pre">./submit.sh</span></code>.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">submit.sh</span></code> submits one or more jobs to SLURM by calling <code class="docutils literal notranslate"><span class="pre">sbatch</span> <span class="pre">disaggr_torch.slurm</span></code> with different parameters.</p></li>
<li><p>For each job, SLURM allocates resources and runs <code class="docutils literal notranslate"><span class="pre">disaggr_torch.slurm</span></code>.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">disaggr_torch.slurm</span></code> runs <code class="docutils literal notranslate"><span class="pre">gen_yaml.py</span></code> to create a <code class="docutils literal notranslate"><span class="pre">config.yaml</span></code>.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">disaggr_torch.slurm</span></code> uses <code class="docutils literal notranslate"><span class="pre">srun</span></code> to launch <code class="docutils literal notranslate"><span class="pre">start_worker.sh</span></code> on all nodes, starting the MPI workers.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">disaggr_torch.slurm</span></code> starts the main <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code> process.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">disaggr_torch.slurm</span></code> runs <code class="docutils literal notranslate"><span class="pre">run_benchmark.sh</span></code> which waits for the server to be ready.</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">run_benchmark.sh</span></code> executes the benchmark for each concurrency level specified.</p></li>
<li><p>After the benchmark, <code class="docutils literal notranslate"><span class="pre">run_benchmark.sh</span></code> and <code class="docutils literal notranslate"><span class="pre">disaggr_torch.slurm</span></code> attempt to kill the server and worker processes.</p></li>
<li><p>Logs for each run are stored in a subdirectory specified by the <code class="docutils literal notranslate"><span class="pre">sub_file</span></code> parameter.</p></li>
</ol>
</section>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
</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="#overview">Overview</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#file-descriptions">File Descriptions</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#submit-sh"><code class="docutils literal notranslate"><span class="pre">submit.sh</span></code></a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#disaggr-torch-slurm"><code class="docutils literal notranslate"><span class="pre">disaggr_torch.slurm</span></code></a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#gen-yaml-py"><code class="docutils literal notranslate"><span class="pre">gen_yaml.py</span></code></a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#start-worker-sh"><code class="docutils literal notranslate"><span class="pre">start_worker.sh</span></code></a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#run-benchmark-sh"><code class="docutils literal notranslate"><span class="pre">run_benchmark.sh</span></code></a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#workflow">Workflow</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 July 19, 2025.</p>
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/69e9f6d">69e9f6d</a>.</p>
</div></div>
</div>
</div>
</footer>
</body>
</html>