kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
gh-pages
TensorRT-LLMs/examples/llm_mgmn_trtllm_serve.html
Kaiyu Xie 9c2249e7c4 Update GitHub pages in root to v1.2.0rc7
2026-01-08 05:44:03 +00:00

759 lines
42 KiB
HTML
Raw Permalink Blame History

This file contains invisible Unicode characters

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

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!DOCTYPE html>
<html lang="en" data-content_root="../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Run trtllm-serve with pytorch backend on Slurm &#8212; TensorRT LLM</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!--
this give us a css class that will be invisible only if js is disabled
-->
<noscript>
<style>
.pst-js-only { display: none !important; }
</style>
</noscript>
<!-- Loaded before other Sphinx assets -->
<link href="../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link href="../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../_static/styles/nvidia-sphinx-theme.css?v=933278ad" />
<link rel="stylesheet" type="text/css" href="../_static/copybutton.css?v=76b2166b" />
<link rel="stylesheet" type="text/css" href="../_static/autodoc_pydantic.css" />
<link rel="stylesheet" type="text/css" href="../_static/togglebutton.css?v=13237357" />
<link rel="stylesheet" type="text/css" href="../_static/config_selector.css?v=e17d8078" />
<link rel="stylesheet" type="text/css" href="../_static/custom.css?v=19d20f17" />
<!-- So that users can add custom icons -->
<script src="../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script>
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" />
<link rel="preload" as="script" href="../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" />
<script src="../_static/documentation_options.js?v=5929fcd5"></script>
<script src="../_static/doctools.js?v=9a2dae69"></script>
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../_static/copybutton.js?v=65e89d2a"></script>
<script src="../_static/config_selector.js?v=aaf6cd4a"></script>
<script>let toggleHintShow = 'Click to show';</script>
<script>let toggleHintHide = 'Click to hide';</script>
<script>let toggleOpenOnPrint = 'true';</script>
<script src="../_static/togglebutton.js?v=4a39c7ea"></script>
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
<script>DOCUMENTATION_OPTIONS.pagename = 'examples/llm_mgmn_trtllm_serve';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.2.0rc7';
DOCUMENTATION_OPTIONS.show_version_warning_banner =
false;
</script>
<link rel="icon" href="../_static/favicon.png"/>
<link rel="index" title="Index" href="../genindex.html" />
<link rel="search" title="Search" href="../search.html" />
<link rel="next" title="Online Serving Examples" href="trtllm_serve_examples.html" />
<link rel="prev" title="Run trtllm-bench with pytorch backend on Slurm" href="llm_mgmn_trtllm_bench.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="1.2.0rc7" />
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<dialog id="pst-search-dialog">
<form class="bd-search d-flex align-items-center"
action="../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form>
</dialog>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
<div class="bd-header__inner bd-page-width">
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
<span class="fa-solid fa-bars"></span>
</button>
<div class="col-lg-3 navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="../index.html">
<img src="../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT LLM - Home"/>
<img src="../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT LLM - Home"/>
<p class="title logo__title">TensorRT LLM</p>
</a></div>
</div>
<div class="col-lg-9 navbar-header-items">
<div class="me-auto navbar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-2"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-2"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-2"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-2">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="navbar-header-items__end">
<div class="navbar-item navbar-persistent--container">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="navbar-persistent--mobile">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
</div>
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<dialog id="pst-primary-sidebar-modal"></dialog>
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
<a class="navbar-brand logo" href="../index.html">
<img src="../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT LLM - Home"/>
<img src="../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT LLM - Home"/>
<p class="title logo__title">TensorRT LLM</p>
</a>
<div class="sidebar-header-items sidebar-primary__section">
<div class="sidebar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-3"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-3"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-3"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-3">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="sidebar-header-items__end">
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<nav class="bd-docs-nav bd-links"
aria-label="Table of Contents">
<p class="bd-links__title" role="heading" aria-level="1">Table of Contents</p>
<div class="bd-toc-item navbar-nav"><p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../quick-start-guide.html">Quick Start Guide</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../installation/index.html">Installation</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../installation/containers.html">Pre-built release container images on NGC</a></li>
<li class="toctree-l2"><a class="reference internal" href="../installation/linux.html">Installing on Linux via <code class="docutils literal notranslate"><span class="pre">pip</span></code></a></li>
<li class="toctree-l2"><a class="reference internal" href="../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Deployment Guide</span></p>
<ul class="current nav bd-sidenav">
<li class="toctree-l1 current active has-children"><a class="reference internal" href="llm_api_examples.html">LLM Examples</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="llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_async.html">Generate text asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_async_streaming.html">Generate text in streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_logits_processor.html">Control generated text using logits processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_sparse_attention.html">Sparse Attention</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_speculative_decoding.html">Speculative Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_kv_cache_connector.html">KV Cache Connector</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_kv_cache_offloading.html">KV Cache Offloading</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_runtime.html">Runtime Configuration Examples</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_sampling.html">Sampling Techniques Showcase</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_llm_distributed.html">Run LLM-API with pytorch backend on Slurm</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_trtllm_bench.html">Run trtllm-bench with pytorch backend on Slurm</a></li>
<li class="toctree-l2 current active"><a class="current reference internal" href="#">Run trtllm-serve with pytorch backend on Slurm</a></li>
</ul>
</details></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="trtllm_serve_examples.html">Online Serving Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="aiperf_client.html">Aiperf Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="aiperf_client_for_multimodal.html">Aiperf Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="curl_chat_client.html">Curl Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="curl_completion_client.html">Curl Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="curl_responses_client.html">Curl Responses Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
<li class="toctree-l2"><a class="reference internal" href="openai_chat_client.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="openai_chat_client_for_multimodal.html">OpenAI Chat Client for Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="openai_completion_client.html">OpenAI Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="openai_completion_client_for_lora.html">Openai Completion Client For Lora</a></li>
<li class="toctree-l2"><a class="reference internal" href="openai_completion_client_json_schema.html">OpenAI Completion Client with JSON Schema</a></li>
<li class="toctree-l2"><a class="reference internal" href="openai_responses_client.html">OpenAI Responses Client</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="dynamo_k8s_example.html">Dynamo K8s Example</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../deployment-guide/index.html">Model Recipes</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-deepseek-r1-on-trtllm.html">Deployment Guide for DeepSeek R1 on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-llama3.3-70b-on-trtllm.html">Deployment Guide for Llama3.3 70B on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-llama4-scout-on-trtllm.html">Deployment Guide for Llama4 Scout 17B on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-gpt-oss-on-trtllm.html">Deployment Guide for GPT-OSS on TensorRT-LLM - Blackwell Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-qwen3-on-trtllm.html">Deployment Guide for Qwen3 on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-qwen3-next-on-trtllm.html">Deployment Guide for Qwen3 Next on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-kimi-k2-thinking-on-trtllm.html">Deployment Guide for Kimi K2 Thinking on TensorRT LLM - Blackwell</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Models</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../models/supported-models.html">Supported Models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../models/adding-new-model.html">Adding a New Model</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">CLI Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-bench.html">trtllm-bench</a></li>
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-eval.html">trtllm-eval</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../commands/trtllm-serve/index.html">trtllm-serve</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../commands/trtllm-serve/trtllm-serve.html">trtllm-serve</a></li>
<li class="toctree-l2"><a class="reference internal" href="../commands/trtllm-serve/run-benchmark-with-trtllm-serve.html">Run benchmarking with <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code></a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">API Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../llm-api/index.html">LLM API Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="../llm-api/reference.html">API Reference</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Features</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../features/feature-combination-matrix.html">Feature Combination Matrix</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/disagg-serving.html">Disaggregated Serving</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/kvcache.html">KV Cache System</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/long-sequence.html">Long Sequences</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/lora.html">LoRA (Low-Rank Adaptation)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/multi-modality.html">Multimodal Support in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/overlap-scheduler.html">Overlap Scheduler</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/paged-attention-ifb-scheduler.html">Paged Attention, IFB, and Request Scheduling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/parallel-strategy.html">Parallelism in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/quantization.html">Quantization</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/sampling.html">Sampling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/additional-outputs.html">Additional Outputs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/guided-decoding.html">Guided Decoding</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/speculative-decoding.html">Speculative Decoding</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/checkpoint-loading.html">Checkpoint Loading</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/auto_deploy/auto-deploy.html">AutoDeploy (Beta)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/ray-orchestrator.html">Ray Orchestrator (Prototype)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/torch_compile_and_piecewise_cuda_graph.html">Torch Compile &amp; Piecewise CUDA Graph</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/helix.html">Helix Parallelism</a></li>
<li class="toctree-l1"><a class="reference internal" href="../features/kv-cache-connector.html">KV Cache Connector</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Developer Guide</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/overview.html">Architecture Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/perf-analysis.html">Performance Analysis</a></li>
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/perf-benchmarking.html">TensorRT LLM Benchmarking</a></li>
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/ci-overview.html">Continuous Integration Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/dev-containers.html">Using Dev Containers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/api-change.html">LLM API Change Guide</a></li>
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/kv-transfer.html">Introduction to KV Cache Transmission</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog10_ADP_Balance_Strategy.html">ADP Balance Strategy</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog11_GPT_OSS_Eagle3.html">Running GPT-OSS-120B with Eagle3 Speculative Decoding on GB200/B200 (TensorRT LLM)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.html">Combining Guided Decoding and Speculative Decoding: Making CPU and GPU Cooperate Seamlessly</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog13_Inference_Time_Compute_Implementation_in_TensorRT-LLM.html">Inference Time Compute Implementation in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog14_Scaling_Expert_Parallelism_in_TensorRT-LLM_part3.html">Scaling Expert Parallelism in TensorRT LLM (Part 3: Pushing the Performance Boundary)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html">Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html">DeepSeek R1 MTP Implementation and Optimization</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html">Optimizing DeepSeek R1 Throughput on NVIDIA Blackwell GPUs: A Deep Dive for Developers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html">Scaling Expert Parallelism in TensorRT LLM (Part 1: Design and Implementation of Large-scale EP)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html">Disaggregated Serving in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html">How to launch Llama4 Maverick + Eagle3 TensorRT LLM server</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html">N-Gram Speculative Decoding in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html">Scaling Expert Parallelism in TensorRT LLM (Part 2: Performance Status and Optimization)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html">Running a High Performance GPT-OSS-120B Inference Server with TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.html">How to get best performance on DeepSeek-R1 in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Quick Links</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/releases">Releases</a></li>
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM">Github Code</a></li>
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/issues?q=is%3Aissue%20state%3Aopen%20label%3Aroadmap">Roadmap</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Use TensorRT Engine</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../legacy/tensorrt_quickstart.html">LLM API with TensorRT Engine</a></li>
</ul>
</div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item">
<nav aria-label="Breadcrumb" class="d-print-none">
<ul class="bd-breadcrumbs">
<li class="breadcrumb-item breadcrumb-home">
<a href="../index.html" class="nav-link" aria-label="Home">
<i class="fa-solid fa-home"></i>
</a>
</li>
<li class="breadcrumb-item"><a href="llm_api_examples.html" class="nav-link">LLM Examples</a></li>
<li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">Run trtllm-serve with pytorch backend on Slurm</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="run-trtllm-serve-with-pytorch-backend-on-slurm">
<h1>Run trtllm-serve with pytorch backend on Slurm<a class="headerlink" href="#run-trtllm-serve-with-pytorch-backend-on-slurm" title="Link to this heading">#</a></h1>
<p>Source <a class="github reference external" href="https://github.com/NVIDIA/TensorRT-LLM/blob/a65b0d4efa23e6802f391c21de90750169ecf1ea/examples/llm-api/llm_mgmn_trtllm_serve.sh">NVIDIA/TensorRT-LLM</a>.</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="ch">#!/bin/bash</span>
<span class="linenos"> 2</span><span class="c1">#SBATCH -A &lt;account&gt;</span>
<span class="linenos"> 3</span><span class="c1">#SBATCH -p &lt;partition&gt;</span>
<span class="linenos"> 4</span><span class="c1">#SBATCH -t 01:00:00</span>
<span class="linenos"> 5</span><span class="c1">#SBATCH -N 2</span>
<span class="linenos"> 6</span><span class="c1">#SBATCH --ntasks-per-node=8</span>
<span class="linenos"> 7</span><span class="c1">#SBATCH -o logs/trtllm-serve.out</span>
<span class="linenos"> 8</span><span class="c1">#SBATCH -e logs/trtllm-serve.err</span>
<span class="linenos"> 9</span><span class="c1">#SBATCH -J trtllm-serve</span>
<span class="linenos">10</span>
<span class="linenos">11</span><span class="c1">##############################################################################</span>
<span class="linenos">12</span><span class="c1"># OVERVIEW:</span>
<span class="linenos">13</span><span class="c1"># This script launches trtllm-serve (OpenAI-compatible API server) on SLURM</span>
<span class="linenos">14</span><span class="c1"># with multi-node, multi-GPU support. The server will start on all allocated</span>
<span class="linenos">15</span><span class="c1"># nodes and serve the model with tensor parallelism.</span>
<span class="linenos">16</span><span class="c1">#</span>
<span class="linenos">17</span><span class="c1"># WHAT TO MODIFY:</span>
<span class="linenos">18</span><span class="c1"># 1. SLURM Parameters (lines 2-9):</span>
<span class="linenos">19</span><span class="c1"># - Replace &lt;account&gt; with your SLURM account name</span>
<span class="linenos">20</span><span class="c1"># - Replace &lt;partition&gt; with your SLURM partition name</span>
<span class="linenos">21</span><span class="c1"># - Adjust -N (number of nodes) based on your TP size</span>
<span class="linenos">22</span><span class="c1"># - Adjust --ntasks-per-node (GPUs per node) to match your setup</span>
<span class="linenos">23</span><span class="c1">#</span>
<span class="linenos">24</span><span class="c1"># 2. Environment Variables (set before running sbatch):</span>
<span class="linenos">25</span><span class="c1"># - CONTAINER_IMAGE: Docker image with TensorRT-LLM installed</span>
<span class="linenos">26</span><span class="c1"># - MOUNT_DIR: Host directory to mount in container</span>
<span class="linenos">27</span><span class="c1"># - MOUNT_DEST: Container mount destination path</span>
<span class="linenos">28</span><span class="c1"># - WORKDIR: Working directory inside container</span>
<span class="linenos">29</span><span class="c1"># - SOURCE_ROOT: Path to TensorRT-LLM source code</span>
<span class="linenos">30</span><span class="c1"># - PROLOGUE: Commands to run before main task (e.g., module loads)</span>
<span class="linenos">31</span><span class="c1"># - LOCAL_MODEL: Path to your pre-downloaded model directory</span>
<span class="linenos">32</span><span class="c1"># - ADDITIONAL_OPTIONS: (Optional) Extra trtllm-serve options</span>
<span class="linenos">33</span><span class="c1">#</span>
<span class="linenos">34</span><span class="c1"># 3. Server Configuration (lines 51-55):</span>
<span class="linenos">35</span><span class="c1"># - --tp_size 16: Adjust tensor parallelism to match your node/GPU setup</span>
<span class="linenos">36</span><span class="c1"># - --host 0.0.0.0: Server bind address (0.0.0.0 allows external access)</span>
<span class="linenos">37</span><span class="c1">#</span>
<span class="linenos">38</span><span class="c1"># EXAMPLE USAGE:</span>
<span class="linenos">39</span><span class="c1"># export CONTAINER_IMAGE=&quot;nvcr.io/nvidia/tensorrt_llm:latest&quot;</span>
<span class="linenos">40</span><span class="c1"># export LOCAL_MODEL=&quot;/path/to/llama-model&quot;</span>
<span class="linenos">41</span><span class="c1"># sbatch llm_mgmn_trtllm_serve.sh</span>
<span class="linenos">42</span><span class="c1">#</span>
<span class="linenos">43</span><span class="c1"># NOTE: After the server starts, you can send requests to it using curl or</span>
<span class="linenos">44</span><span class="c1"># the OpenAI Python client. Check the output logs for the server address.</span>
<span class="linenos">45</span><span class="c1">##############################################################################</span>
<span class="linenos">46</span>
<span class="linenos">47</span>
<span class="linenos">48</span><span class="c1"># NOTE, this feature is experimental and may not work on all systems.</span>
<span class="linenos">49</span><span class="c1"># The trtllm-llmapi-launch is a script that launches the LLM-API code on</span>
<span class="linenos">50</span><span class="c1"># Slurm-like systems, and can support multi-node and multi-GPU setups.</span>
<span class="linenos">51</span>
<span class="linenos">52</span><span class="c1"># IMPORTANT: Total MPI processes (nodes × ntasks-per-node) must equal tp_size.</span>
<span class="linenos">53</span><span class="c1"># e.g. For tensor_parallel_size=16, you may use 2 nodes with 8 gpus for</span>
<span class="linenos">54</span><span class="c1"># each, or 4 nodes with 4 gpus for each or other combinations.</span>
<span class="linenos">55</span>
<span class="linenos">56</span><span class="c1"># This docker image should have tensorrt_llm installed, or you need to install</span>
<span class="linenos">57</span><span class="c1"># it in the task.</span>
<span class="linenos">58</span>
<span class="linenos">59</span><span class="c1"># The following variables are expected to be set in the environment:</span>
<span class="linenos">60</span><span class="c1"># You can set them via --export in the srun/sbatch command.</span>
<span class="linenos">61</span><span class="c1"># CONTAINER_IMAGE: the docker image to use, you&#39;d better install tensorrt_llm in it, or install it in the task.</span>
<span class="linenos">62</span><span class="c1"># MOUNT_DIR: the directory to mount in the container</span>
<span class="linenos">63</span><span class="c1"># MOUNT_DEST: the destination directory in the container</span>
<span class="linenos">64</span><span class="c1"># WORKDIR: the working directory in the container</span>
<span class="linenos">65</span><span class="c1"># SOURCE_ROOT: the path to the TensorRT LLM source</span>
<span class="linenos">66</span><span class="c1"># PROLOGUE: the prologue to run before the script</span>
<span class="linenos">67</span><span class="c1"># LOCAL_MODEL: the local model directory to use, NOTE: downloading from HF is</span>
<span class="linenos">68</span><span class="c1"># not supported in Slurm mode, you need to download the model and put it in</span>
<span class="linenos">69</span><span class="c1"># the LOCAL_MODEL directory.</span>
<span class="linenos">70</span>
<span class="linenos">71</span><span class="nb">echo</span><span class="w"> </span><span class="s2">&quot;Starting trtllm-serve...&quot;</span>
<span class="linenos">72</span><span class="c1"># Just launch trtllm-serve job with trtllm-llmapi-launch command.</span>
<span class="linenos">73</span>srun<span class="w"> </span>-l<span class="w"> </span><span class="se">\</span>
<span class="linenos">74</span><span class="w"> </span>--container-image<span class="o">=</span><span class="si">${</span><span class="nv">CONTAINER_IMAGE</span><span class="si">}</span><span class="w"> </span><span class="se">\</span>
<span class="linenos">75</span><span class="w"> </span>--container-mounts<span class="o">=</span><span class="si">${</span><span class="nv">MOUNT_DIR</span><span class="si">}</span>:<span class="si">${</span><span class="nv">MOUNT_DEST</span><span class="si">}</span><span class="w"> </span><span class="se">\</span>
<span class="linenos">76</span><span class="w"> </span>--container-workdir<span class="o">=</span><span class="si">${</span><span class="nv">WORKDIR</span><span class="si">}</span><span class="w"> </span><span class="se">\</span>
<span class="linenos">77</span><span class="w"> </span>--export<span class="o">=</span>ALL,PYTHONPATH<span class="o">=</span><span class="si">${</span><span class="nv">SOURCE_ROOT</span><span class="si">}</span><span class="w"> </span><span class="se">\</span>
<span class="linenos">78</span><span class="w"> </span>--mpi<span class="o">=</span>pmix<span class="w"> </span><span class="se">\</span>
<span class="linenos">79</span><span class="w"> </span>bash<span class="w"> </span>-c<span class="w"> </span><span class="s2">&quot;</span>
<span class="linenos">80</span><span class="s2"> set -ex</span>
<span class="linenos">81</span><span class="s2"> </span><span class="nv">$PROLOGUE</span>
<span class="linenos">82</span><span class="s2"> export PATH=</span><span class="nv">$PATH</span><span class="s2">:~/.local/bin</span>
<span class="linenos">83</span>
<span class="linenos">84</span><span class="s2"> trtllm-llmapi-launch \</span>
<span class="linenos">85</span><span class="s2"> trtllm-serve </span><span class="nv">$LOCAL_MODEL</span><span class="s2"> \</span>
<span class="linenos">86</span><span class="s2"> --tp_size 16 \</span>
<span class="linenos">87</span><span class="s2"> --host 0.0.0.0 \</span>
<span class="linenos">88</span><span class="s2"> </span><span class="si">${</span><span class="nv">ADDITIONAL_OPTIONS</span><span class="si">}</span>
<span class="linenos">89</span><span class="s2"> &quot;</span>
</pre></div>
</div>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="llm_mgmn_trtllm_bench.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">Run trtllm-bench with pytorch backend on Slurm</p>
</div>
</a>
<a class="right-next"
href="trtllm_serve_examples.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Online Serving Examples</p>
</div>
<i class="fa-solid fa-angle-right"></i>
</a>
</div>
</footer>
</div>
<div class="bd-sidebar-secondary"></div>
</div>
<footer class="bd-footer-content">
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script defer src="../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf"></script>
<script defer src="../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf"></script>
<footer class="bd-footer">
<div class="bd-footer__inner bd-page-width">
<div class="footer-items__start">
<div class="footer-item">
<a class="footer-brand logo" href="https://www.nvidia.com">
<img src="../_static/nvidia-logo-horiz-rgb-1c-blk-for-screen.svg" class="logo__image only-light" alt="NVIDIA"/>
<img src="../_static/nvidia-logo-horiz-rgb-1c-wht-for-screen.svg" class="logo__image only-dark" alt="NVIDIA"/>
</a></div>
<div class="footer-item">
<div class="footer-links">
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/">Privacy Policy</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-center/">Your Privacy Choices</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/terms-of-service/">Terms of Service</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/accessibility/">Accessibility</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/company-policies/">Corporate Policies</a>
|
<a class="external" href="https://www.nvidia.com/en-us/product-security/">Product Security</a>
|
<a class="external" href="https://www.nvidia.com/en-us/contact/">Contact</a>
</div>
</div>
<div class="footer-item">
<p class="copyright">
Copyright © 2025, NVidia.
<br/>
</p>
</div>
<div class="footer-item">
<div class="extra_footer">
<p>Last updated on January 04, 2026.</p>
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/a65b0d4">a65b0d4</a>.</p>
</div></div>
</div>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink