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
259faa6ee7
TensorRT-LLMs/features/guided-decoding.html
Kaiyu Xie 259faa6ee7 Update GitHub pages in root to v1.2.0rc6
2025-12-23 02:41:11 +00:00

1252 lines
95 KiB
HTML
Raw Blame History

This file contains invisible Unicode characters

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

<!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>Guided Decoding &#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/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>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 = 'features/guided-decoding';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.2.0rc6';
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="Speculative Decoding" href="speculative-decoding.html" />
<link rel="prev" title="Additional Outputs" href="additional-outputs.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="1.2.0rc6" />
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<dialog id="pst-search-dialog">
<form class="bd-search d-flex align-items-center"
action="../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form>
</dialog>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
<div class="bd-header__inner bd-page-width">
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
<span class="fa-solid fa-bars"></span>
</button>
<div class="col-lg-3 navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="../index.html">
<img src="../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT LLM - Home"/>
<img src="../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT LLM - Home"/>
<p class="title logo__title">TensorRT LLM</p>
</a></div>
</div>
<div class="col-lg-9 navbar-header-items">
<div class="me-auto navbar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-2"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-2"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-2"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-2">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="navbar-header-items__end">
<div class="navbar-item navbar-persistent--container">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="navbar-persistent--mobile">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
<button class="pst-navbar-icon sidebar-toggle secondary-toggle" aria-label="On this page">
<span class="fa-solid fa-outdent"></span>
</button>
</div>
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<dialog id="pst-primary-sidebar-modal"></dialog>
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
<a class="navbar-brand logo" href="../index.html">
<img src="../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT LLM - Home"/>
<img src="../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT LLM - Home"/>
<p class="title logo__title">TensorRT LLM</p>
</a>
<div class="sidebar-header-items sidebar-primary__section">
<div class="sidebar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-3"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-3"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-3"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-3">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="sidebar-header-items__end">
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<nav class="bd-docs-nav bd-links"
aria-label="Table of Contents">
<p class="bd-links__title" role="heading" aria-level="1">Table of Contents</p>
<div class="bd-toc-item navbar-nav"><p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../quick-start-guide.html">Quick Start Guide</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../installation/index.html">Installation</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../installation/containers.html">Pre-built release container images on NGC</a></li>
<li class="toctree-l2"><a class="reference internal" href="../installation/linux.html">Installing on Linux via <code class="docutils literal notranslate"><span class="pre">pip</span></code></a></li>
<li class="toctree-l2"><a class="reference internal" href="../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Deployment Guide</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1 has-children"><a class="reference internal" href="../examples/llm_api_examples.html">LLM Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_async.html">Generate text asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_async_streaming.html">Generate text in streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_logits_processor.html">Control generated text using logits processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_sparse_attention.html">Sparse Attention</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_speculative_decoding.html">Speculative Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_kv_cache_connector.html">KV Cache Connector</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_kv_cache_offloading.html">KV Cache Offloading</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_runtime.html">Runtime Configuration Examples</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_sampling.html">Sampling Techniques Showcase</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_llm_distributed.html">Run LLM-API with pytorch backend on Slurm</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_trtllm_bench.html">Run trtllm-bench with pytorch backend on Slurm</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_trtllm_serve.html">Run trtllm-serve with pytorch backend on Slurm</a></li>
</ul>
</details></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../examples/trtllm_serve_examples.html">Online Serving Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../examples/curl_chat_client.html">Curl Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/curl_completion_client.html">Curl Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/curl_responses_client.html">Curl Responses Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/genai_perf_client.html">Genai Perf Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/genai_perf_client_for_multimodal.html">Genai Perf Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_chat_client.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_chat_client_for_multimodal.html">OpenAI Chat Client for Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_completion_client_for_lora.html">Openai Completion Client For Lora</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_completion_client_json_schema.html">OpenAI Completion Client with JSON Schema</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_responses_client.html">OpenAI Responses Client</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../examples/dynamo_k8s_example.html">Dynamo K8s Example</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../deployment-guide/index.html">Model Recipes</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-deepseek-r1-on-trtllm.html">Deployment Guide for DeepSeek R1 on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-llama3.3-70b-on-trtllm.html">Deployment Guide for Llama3.3 70B on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-llama4-scout-on-trtllm.html">Deployment Guide for Llama4 Scout 17B on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-gpt-oss-on-trtllm.html">Deployment Guide for GPT-OSS on TensorRT-LLM - Blackwell Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-qwen3-on-trtllm.html">Deployment Guide for Qwen3 on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-qwen3-next-on-trtllm.html">Deployment Guide for Qwen3 Next on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-kimi-k2-thinking-on-trtllm.html">Deployment Guide for Kimi K2 Thinking on TensorRT LLM - Blackwell</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Models</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../models/supported-models.html">Supported Models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../models/adding-new-model.html">Adding a New Model</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">CLI Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-bench.html">trtllm-bench</a></li>
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-eval.html">trtllm-eval</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../commands/trtllm-serve/index.html">trtllm-serve</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../commands/trtllm-serve/trtllm-serve.html">trtllm-serve</a></li>
<li class="toctree-l2"><a class="reference internal" href="../commands/trtllm-serve/run-benchmark-with-trtllm-serve.html">Run benchmarking with <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code></a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">API Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../llm-api/index.html">LLM API Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="../llm-api/reference.html">API Reference</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Features</span></p>
<ul class="current nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="feature-combination-matrix.html">Feature Combination Matrix</a></li>
<li class="toctree-l1"><a class="reference internal" href="attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
<li class="toctree-l1"><a class="reference internal" href="disagg-serving.html">Disaggregated Serving</a></li>
<li class="toctree-l1"><a class="reference internal" href="kvcache.html">KV Cache System</a></li>
<li class="toctree-l1"><a class="reference internal" href="long-sequence.html">Long Sequences</a></li>
<li class="toctree-l1"><a class="reference internal" href="lora.html">LoRA (Low-Rank Adaptation)</a></li>
<li class="toctree-l1"><a class="reference internal" href="multi-modality.html">Multimodal Support in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="overlap-scheduler.html">Overlap Scheduler</a></li>
<li class="toctree-l1"><a class="reference internal" href="paged-attention-ifb-scheduler.html">Paged Attention, IFB, and Request Scheduling</a></li>
<li class="toctree-l1"><a class="reference internal" href="parallel-strategy.html">Parallelism in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="quantization.html">Quantization</a></li>
<li class="toctree-l1"><a class="reference internal" href="sampling.html">Sampling</a></li>
<li class="toctree-l1"><a class="reference internal" href="additional-outputs.html">Additional Outputs</a></li>
<li class="toctree-l1 current active"><a class="current reference internal" href="#">Guided Decoding</a></li>
<li class="toctree-l1"><a class="reference internal" href="speculative-decoding.html">Speculative Decoding</a></li>
<li class="toctree-l1"><a class="reference internal" href="checkpoint-loading.html">Checkpoint Loading</a></li>
<li class="toctree-l1"><a class="reference internal" href="auto_deploy/auto-deploy.html">AutoDeploy (Prototype)</a></li>
<li class="toctree-l1"><a class="reference internal" href="ray-orchestrator.html">Ray Orchestrator (Prototype)</a></li>
<li class="toctree-l1"><a class="reference internal" href="torch_compile_and_piecewise_cuda_graph.html">Torch Compile &amp; Piecewise CUDA Graph</a></li>
<li class="toctree-l1"><a class="reference internal" href="helix.html">Helix Parallelism</a></li>
<li class="toctree-l1"><a class="reference internal" href="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 active" aria-current="page"><span class="ellipsis">Guided Decoding</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section class="tex2jax_ignore mathjax_ignore" id="guided-decoding">
<h1>Guided Decoding<a class="headerlink" href="#guided-decoding" title="Link to this heading">#</a></h1>
<p>Guided decoding (or interchangeably constrained decoding, structured generation) guarantees that the LLM outputs are amenable to a user-specified grammar (e.g., JSON schema, <a class="reference external" href="https://en.wikipedia.org/wiki/Regular_expression">regular expression</a> or <a class="reference external" href="https://en.wikipedia.org/wiki/Extended_Backus%E2%80%93Naur_form">EBNF</a> grammar).</p>
<p>TensorRT LLM supports two grammar backends:</p>
<ul class="simple">
<li><p><a class="reference external" href="https://github.com/mlc-ai/xgrammar/blob/v0.1.21/python/xgrammar/matcher.py#L341-L350">XGrammar</a>: Supports JSON schema, regular expression, EBNF and <a class="reference external" href="https://xgrammar.mlc.ai/docs/tutorials/structural_tag.html">structural tag</a>.</p></li>
<li><p><a class="reference external" href="https://github.com/guidance-ai/llguidance/blob/v1.1.1/python/llguidance/_lib.pyi#L363-L366">LLGuidance</a>: Supports JSON schema, regular expression, EBNF.</p></li>
</ul>
<section id="online-api-trtllm-serve">
<h2>Online API: <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code><a class="headerlink" href="#online-api-trtllm-serve" title="Link to this heading">#</a></h2>
<p>If you are using <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code>, enable guided decoding by specifying <code class="docutils literal notranslate"><span class="pre">guided_decoding_backend</span></code> with <code class="docutils literal notranslate"><span class="pre">xgrammar</span></code> or <code class="docutils literal notranslate"><span class="pre">llguidance</span></code> in the YAML configuration file, and pass it to <code class="docutils literal notranslate"><span class="pre">--extra_llm_api_options</span></code>. For example,</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>cat<span class="w"> </span>&gt;<span class="w"> </span>extra_llm_api_options.yaml<span class="w"> </span><span class="s">&lt;&lt;EOF</span>
<span class="s">guided_decoding_backend: xgrammar</span>
<span class="s">EOF</span>
trtllm-serve<span class="w"> </span>nvidia/Llama-3.1-8B-Instruct-FP8<span class="w"> </span>--extra_llm_api_options<span class="w"> </span>extra_llm_api_options.yaml
</pre></div>
</div>
<p>You should see a log like the following, which indicates the grammar backend is successfully enabled.</p>
<div class="highlight-txt notranslate"><div class="highlight"><pre><span></span>......
[TRT-LLM] [I] Guided decoder initialized with backend: GuidedDecodingBackend.XGRAMMAR
......
</pre></div>
</div>
<section id="json-schema">
<h3>JSON Schema<a class="headerlink" href="#json-schema" title="Link to this heading">#</a></h3>
<p>Define a JSON schema and pass it to <code class="docutils literal notranslate"><span class="pre">response_format</span></code> when creating the OpenAI chat completion request. Alternatively, the JSON schema can be created using <a class="reference external" href="https://docs.pydantic.dev/latest/">pydantic</a>.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">openai</span><span class="w"> </span><span class="kn">import</span> <span class="n">OpenAI</span>
<span class="n">client</span> <span class="o">=</span> <span class="n">OpenAI</span><span class="p">(</span>
<span class="n">base_url</span><span class="o">=</span><span class="s2">&quot;http://localhost:8000/v1&quot;</span><span class="p">,</span>
<span class="n">api_key</span><span class="o">=</span><span class="s2">&quot;tensorrt_llm&quot;</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">json_schema</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;object&quot;</span><span class="p">,</span>
<span class="s2">&quot;properties&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;pattern&quot;</span><span class="p">:</span> <span class="s2">&quot;^[</span><span class="se">\\</span><span class="s2">w]+$&quot;</span>
<span class="p">},</span>
<span class="s2">&quot;population&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;integer&quot;</span>
<span class="p">},</span>
<span class="p">},</span>
<span class="s2">&quot;required&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;name&quot;</span><span class="p">,</span> <span class="s2">&quot;population&quot;</span><span class="p">],</span>
<span class="p">}</span>
<span class="n">messages</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;system&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;You are a helpful assistant.&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;user&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;Give me the information of the capital of France in the JSON format.&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">]</span>
<span class="n">chat_completion</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">chat</span><span class="o">.</span><span class="n">completions</span><span class="o">.</span><span class="n">create</span><span class="p">(</span>
<span class="n">model</span><span class="o">=</span><span class="s2">&quot;nvidia/Llama-3.1-8B-Instruct-FP8&quot;</span><span class="p">,</span>
<span class="n">messages</span><span class="o">=</span><span class="n">messages</span><span class="p">,</span>
<span class="n">max_completion_tokens</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
<span class="n">response_format</span><span class="o">=</span><span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;json&quot;</span><span class="p">,</span>
<span class="s2">&quot;schema&quot;</span><span class="p">:</span> <span class="n">json_schema</span>
<span class="p">},</span>
<span class="p">)</span>
<span class="n">message</span> <span class="o">=</span> <span class="n">chat_completion</span><span class="o">.</span><span class="n">choices</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">message</span>
<span class="nb">print</span><span class="p">(</span><span class="n">message</span><span class="o">.</span><span class="n">content</span><span class="p">)</span>
</pre></div>
</div>
<p>The output would look like:</p>
<div class="highlight-txt notranslate"><div class="highlight"><pre><span></span>{
&quot;name&quot;: &quot;Paris&quot;,
&quot;population&quot;: 2145200
}
</pre></div>
</div>
</section>
<section id="regular-expression">
<h3>Regular expression<a class="headerlink" href="#regular-expression" title="Link to this heading">#</a></h3>
<p>Define a regular expression and pass it to <code class="docutils literal notranslate"><span class="pre">response_format</span></code> when creating the OpenAI chat completion request.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">openai</span><span class="w"> </span><span class="kn">import</span> <span class="n">OpenAI</span>
<span class="n">client</span> <span class="o">=</span> <span class="n">OpenAI</span><span class="p">(</span>
<span class="n">base_url</span><span class="o">=</span><span class="s2">&quot;http://localhost:8000/v1&quot;</span><span class="p">,</span>
<span class="n">api_key</span><span class="o">=</span><span class="s2">&quot;tensorrt_llm&quot;</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">messages</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;system&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;You are a helpful assistant.&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;user&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;What is the capital of France?&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">]</span>
<span class="n">chat_completion</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">chat</span><span class="o">.</span><span class="n">completions</span><span class="o">.</span><span class="n">create</span><span class="p">(</span>
<span class="n">model</span><span class="o">=</span><span class="s2">&quot;nvidia/Llama-3.1-8B-Instruct-FP8&quot;</span><span class="p">,</span>
<span class="n">messages</span><span class="o">=</span><span class="n">messages</span><span class="p">,</span>
<span class="n">max_completion_tokens</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
<span class="n">response_format</span><span class="o">=</span><span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;regex&quot;</span><span class="p">,</span>
<span class="s2">&quot;regex&quot;</span><span class="p">:</span> <span class="s2">&quot;(Paris|London)&quot;</span>
<span class="p">},</span>
<span class="p">)</span>
<span class="n">message</span> <span class="o">=</span> <span class="n">chat_completion</span><span class="o">.</span><span class="n">choices</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">message</span>
<span class="nb">print</span><span class="p">(</span><span class="n">message</span><span class="o">.</span><span class="n">content</span><span class="p">)</span>
</pre></div>
</div>
<p>The output would look like:</p>
<div class="highlight-txt notranslate"><div class="highlight"><pre><span></span>Paris
</pre></div>
</div>
</section>
<section id="ebnf-grammar">
<h3>EBNF grammar<a class="headerlink" href="#ebnf-grammar" title="Link to this heading">#</a></h3>
<p>Define an EBNF grammar and pass it to <code class="docutils literal notranslate"><span class="pre">response_format</span></code> when creating the OpenAI chat completion request.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">openai</span><span class="w"> </span><span class="kn">import</span> <span class="n">OpenAI</span>
<span class="n">client</span> <span class="o">=</span> <span class="n">OpenAI</span><span class="p">(</span>
<span class="n">base_url</span><span class="o">=</span><span class="s2">&quot;http://localhost:8000/v1&quot;</span><span class="p">,</span>
<span class="n">api_key</span><span class="o">=</span><span class="s2">&quot;tensorrt_llm&quot;</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">ebnf_grammar</span> <span class="o">=</span> <span class="s2">&quot;&quot;&quot;root ::= description</span>
<span class="s2">city ::= &quot;London&quot; | &quot;Paris&quot; | &quot;Berlin&quot; | &quot;Rome&quot;</span>
<span class="s2">description ::= city &quot; is &quot; status</span>
<span class="s2">status ::= &quot;the capital of &quot; country</span>
<span class="s2">country ::= &quot;England&quot; | &quot;France&quot; | &quot;Germany&quot; | &quot;Italy&quot;</span>
<span class="s2">&quot;&quot;&quot;</span>
<span class="n">messages</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;system&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;You are a helpful geography bot.&quot;</span>
<span class="p">},</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;user&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;Give me the information of the capital of France.&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">]</span>
<span class="n">chat_completion</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">chat</span><span class="o">.</span><span class="n">completions</span><span class="o">.</span><span class="n">create</span><span class="p">(</span>
<span class="n">model</span><span class="o">=</span><span class="s2">&quot;nvidia/Llama-3.1-8B-Instruct-FP8&quot;</span><span class="p">,</span>
<span class="n">messages</span><span class="o">=</span><span class="n">messages</span><span class="p">,</span>
<span class="n">max_completion_tokens</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
<span class="n">response_format</span><span class="o">=</span><span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;ebnf&quot;</span><span class="p">,</span>
<span class="s2">&quot;ebnf&quot;</span><span class="p">:</span> <span class="n">ebnf_grammar</span>
<span class="p">},</span>
<span class="p">)</span>
<span class="n">message</span> <span class="o">=</span> <span class="n">chat_completion</span><span class="o">.</span><span class="n">choices</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">message</span>
<span class="nb">print</span><span class="p">(</span><span class="n">message</span><span class="o">.</span><span class="n">content</span><span class="p">)</span>
</pre></div>
</div>
<p>The output would look like:</p>
<div class="highlight-txt notranslate"><div class="highlight"><pre><span></span>Paris is the capital of France
</pre></div>
</div>
</section>
<section id="structural-tag">
<h3>Structural tag<a class="headerlink" href="#structural-tag" title="Link to this heading">#</a></h3>
<p>Define a structural tag and pass it to <code class="docutils literal notranslate"><span class="pre">response_format</span></code> when creating the OpenAI chat completion request.</p>
<p>Structural tag is supported by <code class="docutils literal notranslate"><span class="pre">xgrammar</span></code> backend only. It is a powerful and flexible tool to represent the LLM output constraints. Please see <a class="reference external" href="https://xgrammar.mlc.ai/docs/tutorials/structural_tag.html">structural tag usage</a> for a comprehensive tutorial. Below is an example of function calling with customized function call format for <code class="docutils literal notranslate"><span class="pre">Llama-3.1-8B-Instruct</span></code>.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">openai</span><span class="w"> </span><span class="kn">import</span> <span class="n">OpenAI</span>
<span class="n">client</span> <span class="o">=</span> <span class="n">OpenAI</span><span class="p">(</span>
<span class="n">base_url</span><span class="o">=</span><span class="s2">&quot;http://localhost:8000/v1&quot;</span><span class="p">,</span>
<span class="n">api_key</span><span class="o">=</span><span class="s2">&quot;tensorrt_llm&quot;</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">tool_get_current_weather</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;function&quot;</span><span class="p">,</span>
<span class="s2">&quot;function&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="s2">&quot;get_current_weather&quot;</span><span class="p">,</span>
<span class="s2">&quot;description&quot;</span><span class="p">:</span> <span class="s2">&quot;Get the current weather in a given location&quot;</span><span class="p">,</span>
<span class="s2">&quot;parameters&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;object&quot;</span><span class="p">,</span>
<span class="s2">&quot;properties&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;city&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;description&quot;</span><span class="p">:</span> <span class="s2">&quot;The city to find the weather for, e.g. &#39;San Francisco&#39;&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="s2">&quot;state&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;description&quot;</span><span class="p">:</span> <span class="s2">&quot;the two-letter abbreviation for the state that the city is in, e.g. &#39;CA&#39; which would mean &#39;California&#39;&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="s2">&quot;unit&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;description&quot;</span><span class="p">:</span> <span class="s2">&quot;The unit to fetch the temperature in&quot;</span><span class="p">,</span>
<span class="s2">&quot;enum&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;celsius&quot;</span><span class="p">,</span> <span class="s2">&quot;fahrenheit&quot;</span><span class="p">],</span>
<span class="p">},</span>
<span class="p">},</span>
<span class="s2">&quot;required&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;city&quot;</span><span class="p">,</span> <span class="s2">&quot;state&quot;</span><span class="p">,</span> <span class="s2">&quot;unit&quot;</span><span class="p">],</span>
<span class="p">},</span>
<span class="p">},</span>
<span class="p">}</span>
<span class="n">tool_get_current_date</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;function&quot;</span><span class="p">,</span>
<span class="s2">&quot;function&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="s2">&quot;get_current_date&quot;</span><span class="p">,</span>
<span class="s2">&quot;description&quot;</span><span class="p">:</span> <span class="s2">&quot;Get the current date and time for a given timezone&quot;</span><span class="p">,</span>
<span class="s2">&quot;parameters&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;object&quot;</span><span class="p">,</span>
<span class="s2">&quot;properties&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;timezone&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;description&quot;</span><span class="p">:</span> <span class="s2">&quot;The timezone to fetch the current date and time for, e.g. &#39;America/New_York&#39;&quot;</span><span class="p">,</span>
<span class="p">}</span>
<span class="p">},</span>
<span class="s2">&quot;required&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;timezone&quot;</span><span class="p">],</span>
<span class="p">},</span>
<span class="p">},</span>
<span class="p">}</span>
<span class="n">system_prompt</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">&quot;&quot;&quot;# Tool Instructions</span>
<span class="s2">- Always execute python code in messages that you share.</span>
<span class="s2">- When looking for real time information use relevant functions if available else fallback to brave_search</span>
<span class="s2">You have access to the following functions:</span>
<span class="s2">Use the function &#39;get_current_weather&#39; to: Get the current weather in a given location</span>
<span class="si">{</span><span class="n">tool_get_current_weather</span><span class="p">[</span><span class="s2">&quot;function&quot;</span><span class="p">]</span><span class="si">}</span>
<span class="s2">Use the function &#39;get_current_date&#39; to: Get the current date and time for a given timezone</span>
<span class="si">{</span><span class="n">tool_get_current_date</span><span class="p">[</span><span class="s2">&quot;function&quot;</span><span class="p">]</span><span class="si">}</span>
<span class="s2">If a you choose to call a function ONLY reply in the following format:</span>
<span class="s2">&lt;</span><span class="se">{{</span><span class="s2">start_tag</span><span class="se">}}</span><span class="s2">=</span><span class="se">{{</span><span class="s2">function_name</span><span class="se">}}</span><span class="s2">&gt;</span><span class="se">{{</span><span class="s2">parameters</span><span class="se">}}{{</span><span class="s2">end_tag</span><span class="se">}}</span>
<span class="s2">where</span>
<span class="s2">start_tag =&gt; `&lt;function`</span>
<span class="s2">parameters =&gt; a JSON dict with the function argument name as key and function argument value as value.</span>
<span class="s2">end_tag =&gt; `&lt;/function&gt;`</span>
<span class="s2">Here is an example,</span>
<span class="s2">&lt;function=example_function_name&gt;</span><span class="se">{{</span><span class="s2">&quot;example_name&quot;: &quot;example_value&quot;</span><span class="se">}}</span><span class="s2">&lt;/function&gt;</span>
<span class="s2">Reminder:</span>
<span class="s2">- Function calls MUST follow the specified format</span>
<span class="s2">- Required parameters MUST be specified</span>
<span class="s2">- Only call one function at a time</span>
<span class="s2">- Put the entire function call reply on one line</span>
<span class="s2">- Always add your sources when using search results to answer the user query</span>
<span class="s2">You are a helpful assistant.&quot;&quot;&quot;</span>
<span class="n">user_prompt</span> <span class="o">=</span> <span class="s2">&quot;You are in New York. Please get the current date and time, and the weather.&quot;</span>
<span class="n">messages</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;system&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="n">system_prompt</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;user&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="n">user_prompt</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">]</span>
<span class="n">chat_completion</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">chat</span><span class="o">.</span><span class="n">completions</span><span class="o">.</span><span class="n">create</span><span class="p">(</span>
<span class="n">model</span><span class="o">=</span><span class="s2">&quot;nvidia/Llama-3.1-8B-Instruct-FP8&quot;</span><span class="p">,</span>
<span class="n">messages</span><span class="o">=</span><span class="n">messages</span><span class="p">,</span>
<span class="n">max_completion_tokens</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
<span class="n">response_format</span><span class="o">=</span><span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;structural_tag&quot;</span><span class="p">,</span>
<span class="s2">&quot;format&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;triggered_tags&quot;</span><span class="p">,</span>
<span class="s2">&quot;triggers&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;&lt;function=&quot;</span><span class="p">],</span>
<span class="s2">&quot;tags&quot;</span><span class="p">:</span> <span class="p">[</span>
<span class="p">{</span>
<span class="s2">&quot;begin&quot;</span><span class="p">:</span> <span class="s2">&quot;&lt;function=get_current_weather&gt;&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;json_schema&quot;</span><span class="p">,</span>
<span class="s2">&quot;json_schema&quot;</span><span class="p">:</span> <span class="n">tool_get_current_weather</span><span class="p">[</span><span class="s2">&quot;function&quot;</span><span class="p">][</span><span class="s2">&quot;parameters&quot;</span><span class="p">]</span>
<span class="p">},</span>
<span class="s2">&quot;end&quot;</span><span class="p">:</span> <span class="s2">&quot;&lt;/function&gt;&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">{</span>
<span class="s2">&quot;begin&quot;</span><span class="p">:</span> <span class="s2">&quot;&lt;function=get_current_date&gt;&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;json_schema&quot;</span><span class="p">,</span>
<span class="s2">&quot;json_schema&quot;</span><span class="p">:</span> <span class="n">tool_get_current_date</span><span class="p">[</span><span class="s2">&quot;function&quot;</span><span class="p">][</span><span class="s2">&quot;parameters&quot;</span><span class="p">]</span>
<span class="p">},</span>
<span class="s2">&quot;end&quot;</span><span class="p">:</span> <span class="s2">&quot;&lt;/function&gt;&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">],</span>
<span class="p">},</span>
<span class="p">},</span>
<span class="p">)</span>
<span class="n">message</span> <span class="o">=</span> <span class="n">chat_completion</span><span class="o">.</span><span class="n">choices</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">message</span>
<span class="nb">print</span><span class="p">(</span><span class="n">message</span><span class="o">.</span><span class="n">content</span><span class="p">)</span>
</pre></div>
</div>
<p>The output would look like:</p>
<div class="highlight-txt notranslate"><div class="highlight"><pre><span></span>&lt;function=get_current_date&gt;{&quot;timezone&quot;: &quot;America/New_York&quot;}&lt;/function&gt;
&lt;function=get_current_weather&gt;{&quot;city&quot;: &quot;New York&quot;, &quot;state&quot;: &quot;NY&quot;, &quot;unit&quot;: &quot;fahrenheit&quot;}&lt;/function&gt;
</pre></div>
</div>
</section>
</section>
<section id="offline-api-llm-api">
<h2>Offline API: LLM API<a class="headerlink" href="#offline-api-llm-api" title="Link to this heading">#</a></h2>
<p>If you are using LLM API, enable guided decoding by specifying <code class="docutils literal notranslate"><span class="pre">guided_decoding_backend</span></code> with <code class="docutils literal notranslate"><span class="pre">xgrammar</span></code> or <code class="docutils literal notranslate"><span class="pre">llguidance</span></code> when creating the LLM instance. For example,</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="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span><span class="s2">&quot;nvidia/Llama-3.1-8B-Instruct-FP8&quot;</span><span class="p">,</span> <span class="n">guided_decoding_backend</span><span class="o">=</span><span class="s2">&quot;xgrammar&quot;</span><span class="p">)</span>
</pre></div>
</div>
<section id="id1">
<h3>JSON Schema<a class="headerlink" href="#id1" title="Link to this heading">#</a></h3>
<p>Create a <code class="docutils literal notranslate"><span class="pre">GuidedDecodingParams</span></code> with the <code class="docutils literal notranslate"><span class="pre">json</span></code> field specified with a JSON schema, use it to create <code class="docutils literal notranslate"><span class="pre">SamplingParams</span></code>, and then pass to <code class="docutils literal notranslate"><span class="pre">llm.generate</span></code> or <code class="docutils literal notranslate"><span class="pre">llm.generate_async</span></code>. Alternatively, the JSON schema can be created using <a class="reference external" href="https://docs.pydantic.dev/latest/">pydantic</a>.</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="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.sampling_params</span><span class="w"> </span><span class="kn">import</span> <span class="n">SamplingParams</span><span class="p">,</span> <span class="n">GuidedDecodingParams</span>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;__main__&quot;</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="s2">&quot;nvidia/Llama-3.1-8B-Instruct-FP8&quot;</span><span class="p">,</span> <span class="n">guided_decoding_backend</span><span class="o">=</span><span class="s2">&quot;xgrammar&quot;</span><span class="p">)</span>
<span class="n">json_schema</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;object&quot;</span><span class="p">,</span>
<span class="s2">&quot;properties&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;pattern&quot;</span><span class="p">:</span> <span class="s2">&quot;^[</span><span class="se">\\</span><span class="s2">w]+$&quot;</span>
<span class="p">},</span>
<span class="s2">&quot;population&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;integer&quot;</span>
<span class="p">},</span>
<span class="p">},</span>
<span class="s2">&quot;required&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;name&quot;</span><span class="p">,</span> <span class="s2">&quot;population&quot;</span><span class="p">],</span>
<span class="p">}</span>
<span class="n">messages</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;system&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;You are a helpful assistant.&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;user&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;Give me the information of the capital of France in the JSON format.&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">]</span>
<span class="n">prompt</span> <span class="o">=</span> <span class="n">llm</span><span class="o">.</span><span class="n">tokenizer</span><span class="o">.</span><span class="n">apply_chat_template</span><span class="p">(</span><span class="n">messages</span><span class="p">,</span> <span class="n">tokenize</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">add_generation_prompt</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">output</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">prompt</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">max_tokens</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">guided_decoding</span><span class="o">=</span><span class="n">GuidedDecodingParams</span><span class="p">(</span><span class="n">json</span><span class="o">=</span><span class="n">json_schema</span><span class="p">)),</span>
<span class="p">)</span>
<span class="nb">print</span><span class="p">(</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="p">)</span>
</pre></div>
</div>
<p>The output would look like:</p>
<div class="highlight-txt notranslate"><div class="highlight"><pre><span></span>{
&quot;name&quot;: &quot;Paris&quot;,
&quot;population&quot;: 2145206
}
</pre></div>
</div>
</section>
<section id="id2">
<h3>Regular expression<a class="headerlink" href="#id2" title="Link to this heading">#</a></h3>
<p>Create a <code class="docutils literal notranslate"><span class="pre">GuidedDecodingParams</span></code> with the <code class="docutils literal notranslate"><span class="pre">regex</span></code> field specified with a regular expression, use it to create <code class="docutils literal notranslate"><span class="pre">SamplingParams</span></code>, and then pass to <code class="docutils literal notranslate"><span class="pre">llm.generate</span></code> or <code class="docutils literal notranslate"><span class="pre">llm.generate_async</span></code>.</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="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.sampling_params</span><span class="w"> </span><span class="kn">import</span> <span class="n">SamplingParams</span><span class="p">,</span> <span class="n">GuidedDecodingParams</span>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;__main__&quot;</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="s2">&quot;nvidia/Llama-3.1-8B-Instruct-FP8&quot;</span><span class="p">,</span> <span class="n">guided_decoding_backend</span><span class="o">=</span><span class="s2">&quot;xgrammar&quot;</span><span class="p">)</span>
<span class="n">messages</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;system&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;You are a helpful assistant.&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;user&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;What is the capital of France?&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">]</span>
<span class="n">prompt</span> <span class="o">=</span> <span class="n">llm</span><span class="o">.</span><span class="n">tokenizer</span><span class="o">.</span><span class="n">apply_chat_template</span><span class="p">(</span><span class="n">messages</span><span class="p">,</span> <span class="n">tokenize</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">add_generation_prompt</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">output</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">prompt</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">max_tokens</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">guided_decoding</span><span class="o">=</span><span class="n">GuidedDecodingParams</span><span class="p">(</span><span class="n">regex</span><span class="o">=</span><span class="s2">&quot;(Paris|London)&quot;</span><span class="p">)),</span>
<span class="p">)</span>
<span class="nb">print</span><span class="p">(</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="p">)</span>
</pre></div>
</div>
<p>The output would look like:</p>
<div class="highlight-txt notranslate"><div class="highlight"><pre><span></span>Paris
</pre></div>
</div>
</section>
<section id="id3">
<h3>EBNF grammar<a class="headerlink" href="#id3" title="Link to this heading">#</a></h3>
<p>Create a <code class="docutils literal notranslate"><span class="pre">GuidedDecodingParams</span></code> with the <code class="docutils literal notranslate"><span class="pre">grammar</span></code> field specified with an EBNF grammar, use it to create <code class="docutils literal notranslate"><span class="pre">SamplingParams</span></code>, and then pass to <code class="docutils literal notranslate"><span class="pre">llm.generate</span></code> or <code class="docutils literal notranslate"><span class="pre">llm.generate_async</span></code>.</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="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.sampling_params</span><span class="w"> </span><span class="kn">import</span> <span class="n">SamplingParams</span><span class="p">,</span> <span class="n">GuidedDecodingParams</span>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;__main__&quot;</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="s2">&quot;nvidia/Llama-3.1-8B-Instruct-FP8&quot;</span><span class="p">,</span> <span class="n">guided_decoding_backend</span><span class="o">=</span><span class="s2">&quot;xgrammar&quot;</span><span class="p">)</span>
<span class="n">ebnf_grammar</span> <span class="o">=</span> <span class="s2">&quot;&quot;&quot;root ::= description</span>
<span class="s2">city ::= &quot;London&quot; | &quot;Paris&quot; | &quot;Berlin&quot; | &quot;Rome&quot;</span>
<span class="s2">description ::= city &quot; is &quot; status</span>
<span class="s2">status ::= &quot;the capital of &quot; country</span>
<span class="s2">country ::= &quot;England&quot; | &quot;France&quot; | &quot;Germany&quot; | &quot;Italy&quot;</span>
<span class="s2">&quot;&quot;&quot;</span>
<span class="n">messages</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;system&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;You are a helpful geography bot.&quot;</span>
<span class="p">},</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;user&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;Give me the information of the capital of France.&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">]</span>
<span class="n">prompt</span> <span class="o">=</span> <span class="n">llm</span><span class="o">.</span><span class="n">tokenizer</span><span class="o">.</span><span class="n">apply_chat_template</span><span class="p">(</span><span class="n">messages</span><span class="p">,</span> <span class="n">tokenize</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">add_generation_prompt</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">output</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">prompt</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">max_tokens</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">guided_decoding</span><span class="o">=</span><span class="n">GuidedDecodingParams</span><span class="p">(</span><span class="n">grammar</span><span class="o">=</span><span class="n">ebnf_grammar</span><span class="p">)),</span>
<span class="p">)</span>
<span class="nb">print</span><span class="p">(</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="p">)</span>
</pre></div>
</div>
<p>The output would look like:</p>
<div class="highlight-txt notranslate"><div class="highlight"><pre><span></span>Paris is the capital of France
</pre></div>
</div>
</section>
<section id="id4">
<h3>Structural tag<a class="headerlink" href="#id4" title="Link to this heading">#</a></h3>
<p>Create a <code class="docutils literal notranslate"><span class="pre">GuidedDecodingParams</span></code> with the <code class="docutils literal notranslate"><span class="pre">structural_tag</span></code> field specified with a structural tag string, use it to create <code class="docutils literal notranslate"><span class="pre">SamplingParams</span></code>, and then pass to <code class="docutils literal notranslate"><span class="pre">llm.generate</span></code> or <code class="docutils literal notranslate"><span class="pre">llm.generate_async</span></code>.</p>
<p>Structural tag is supported by <code class="docutils literal notranslate"><span class="pre">xgrammar</span></code> backend only. It is a powerful and flexible tool to represent the LLM output constraints. Please see <a class="reference external" href="https://xgrammar.mlc.ai/docs/tutorials/structural_tag.html">structural tag usage</a> for a comprehensive tutorial. Below is an example of function calling with customized function call format for <code class="docutils literal notranslate"><span class="pre">Llama-3.1-8B-Instruct</span></code>.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">json</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="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.sampling_params</span><span class="w"> </span><span class="kn">import</span> <span class="n">SamplingParams</span><span class="p">,</span> <span class="n">GuidedDecodingParams</span>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;__main__&quot;</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="s2">&quot;nvidia/Llama-3.1-8B-Instruct-FP8&quot;</span><span class="p">,</span> <span class="n">guided_decoding_backend</span><span class="o">=</span><span class="s2">&quot;xgrammar&quot;</span><span class="p">)</span>
<span class="n">tool_get_current_weather</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;function&quot;</span><span class="p">,</span>
<span class="s2">&quot;function&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="s2">&quot;get_current_weather&quot;</span><span class="p">,</span>
<span class="s2">&quot;description&quot;</span><span class="p">:</span> <span class="s2">&quot;Get the current weather in a given location&quot;</span><span class="p">,</span>
<span class="s2">&quot;parameters&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;object&quot;</span><span class="p">,</span>
<span class="s2">&quot;properties&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;city&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;description&quot;</span><span class="p">:</span> <span class="s2">&quot;The city to find the weather for, e.g. &#39;San Francisco&#39;&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="s2">&quot;state&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;description&quot;</span><span class="p">:</span> <span class="s2">&quot;the two-letter abbreviation for the state that the city is in, e.g. &#39;CA&#39; which would mean &#39;California&#39;&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="s2">&quot;unit&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;description&quot;</span><span class="p">:</span> <span class="s2">&quot;The unit to fetch the temperature in&quot;</span><span class="p">,</span>
<span class="s2">&quot;enum&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;celsius&quot;</span><span class="p">,</span> <span class="s2">&quot;fahrenheit&quot;</span><span class="p">],</span>
<span class="p">},</span>
<span class="p">},</span>
<span class="s2">&quot;required&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;city&quot;</span><span class="p">,</span> <span class="s2">&quot;state&quot;</span><span class="p">,</span> <span class="s2">&quot;unit&quot;</span><span class="p">],</span>
<span class="p">},</span>
<span class="p">},</span>
<span class="p">}</span>
<span class="n">tool_get_current_date</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;function&quot;</span><span class="p">,</span>
<span class="s2">&quot;function&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="s2">&quot;get_current_date&quot;</span><span class="p">,</span>
<span class="s2">&quot;description&quot;</span><span class="p">:</span> <span class="s2">&quot;Get the current date and time for a given timezone&quot;</span><span class="p">,</span>
<span class="s2">&quot;parameters&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;object&quot;</span><span class="p">,</span>
<span class="s2">&quot;properties&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;timezone&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;description&quot;</span><span class="p">:</span> <span class="s2">&quot;The timezone to fetch the current date and time for, e.g. &#39;America/New_York&#39;&quot;</span><span class="p">,</span>
<span class="p">}</span>
<span class="p">},</span>
<span class="s2">&quot;required&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;timezone&quot;</span><span class="p">],</span>
<span class="p">},</span>
<span class="p">},</span>
<span class="p">}</span>
<span class="n">system_prompt</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">&quot;&quot;&quot;# Tool Instructions</span>
<span class="s2">- Always execute python code in messages that you share.</span>
<span class="s2">- When looking for real time information use relevant functions if available else fallback to brave_search</span>
<span class="s2">You have access to the following functions:</span>
<span class="s2">Use the function &#39;get_current_weather&#39; to: Get the current weather in a given location</span>
<span class="si">{</span><span class="n">tool_get_current_weather</span><span class="p">[</span><span class="s2">&quot;function&quot;</span><span class="p">]</span><span class="si">}</span>
<span class="s2">Use the function &#39;get_current_date&#39; to: Get the current date and time for a given timezone</span>
<span class="si">{</span><span class="n">tool_get_current_date</span><span class="p">[</span><span class="s2">&quot;function&quot;</span><span class="p">]</span><span class="si">}</span>
<span class="s2">If a you choose to call a function ONLY reply in the following format:</span>
<span class="s2">&lt;</span><span class="se">{{</span><span class="s2">start_tag</span><span class="se">}}</span><span class="s2">=</span><span class="se">{{</span><span class="s2">function_name</span><span class="se">}}</span><span class="s2">&gt;</span><span class="se">{{</span><span class="s2">parameters</span><span class="se">}}{{</span><span class="s2">end_tag</span><span class="se">}}</span>
<span class="s2">where</span>
<span class="s2">start_tag =&gt; `&lt;function`</span>
<span class="s2">parameters =&gt; a JSON dict with the function argument name as key and function argument value as value.</span>
<span class="s2">end_tag =&gt; `&lt;/function&gt;`</span>
<span class="s2">Here is an example,</span>
<span class="s2">&lt;function=example_function_name&gt;</span><span class="se">{{</span><span class="s2">&quot;example_name&quot;: &quot;example_value&quot;</span><span class="se">}}</span><span class="s2">&lt;/function&gt;</span>
<span class="s2">Reminder:</span>
<span class="s2">- Function calls MUST follow the specified format</span>
<span class="s2">- Required parameters MUST be specified</span>
<span class="s2">- Only call one function at a time</span>
<span class="s2">- Put the entire function call reply on one line</span>
<span class="s2">- Always add your sources when using search results to answer the user query</span>
<span class="s2">You are a helpful assistant.&quot;&quot;&quot;</span>
<span class="n">user_prompt</span> <span class="o">=</span> <span class="s2">&quot;You are in New York. Please get the current date and time, and the weather.&quot;</span>
<span class="n">structural_tag</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;structural_tag&quot;</span><span class="p">,</span>
<span class="s2">&quot;format&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;triggered_tags&quot;</span><span class="p">,</span>
<span class="s2">&quot;triggers&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;&lt;function=&quot;</span><span class="p">],</span>
<span class="s2">&quot;tags&quot;</span><span class="p">:</span> <span class="p">[</span>
<span class="p">{</span>
<span class="s2">&quot;begin&quot;</span><span class="p">:</span> <span class="s2">&quot;&lt;function=get_current_weather&gt;&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;json_schema&quot;</span><span class="p">,</span>
<span class="s2">&quot;json_schema&quot;</span><span class="p">:</span> <span class="n">tool_get_current_weather</span><span class="p">[</span><span class="s2">&quot;function&quot;</span><span class="p">][</span><span class="s2">&quot;parameters&quot;</span><span class="p">]</span>
<span class="p">},</span>
<span class="s2">&quot;end&quot;</span><span class="p">:</span> <span class="s2">&quot;&lt;/function&gt;&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">{</span>
<span class="s2">&quot;begin&quot;</span><span class="p">:</span> <span class="s2">&quot;&lt;function=get_current_date&gt;&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;json_schema&quot;</span><span class="p">,</span>
<span class="s2">&quot;json_schema&quot;</span><span class="p">:</span> <span class="n">tool_get_current_date</span><span class="p">[</span><span class="s2">&quot;function&quot;</span><span class="p">][</span><span class="s2">&quot;parameters&quot;</span><span class="p">]</span>
<span class="p">},</span>
<span class="s2">&quot;end&quot;</span><span class="p">:</span> <span class="s2">&quot;&lt;/function&gt;&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">],</span>
<span class="p">},</span>
<span class="p">}</span>
<span class="n">messages</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;system&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="n">system_prompt</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">{</span>
<span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;user&quot;</span><span class="p">,</span>
<span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="n">user_prompt</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">]</span>
<span class="n">prompt</span> <span class="o">=</span> <span class="n">llm</span><span class="o">.</span><span class="n">tokenizer</span><span class="o">.</span><span class="n">apply_chat_template</span><span class="p">(</span><span class="n">messages</span><span class="p">,</span> <span class="n">tokenize</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">add_generation_prompt</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">output</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">prompt</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">max_tokens</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">guided_decoding</span><span class="o">=</span><span class="n">GuidedDecodingParams</span><span class="p">(</span><span class="n">structural_tag</span><span class="o">=</span><span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">structural_tag</span><span class="p">))),</span>
<span class="p">)</span>
<span class="nb">print</span><span class="p">(</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="p">)</span>
</pre></div>
</div>
<p>The output would look like:</p>
<div class="highlight-txt notranslate"><div class="highlight"><pre><span></span>&lt;function=get_current_date&gt;{&quot;timezone&quot;: &quot;America/New_York&quot;}&lt;/function&gt;
&lt;function=get_current_weather&gt;{&quot;city&quot;: &quot;New York&quot;, &quot;state&quot;: &quot;NY&quot;, &quot;unit&quot;: &quot;fahrenheit&quot;}&lt;/function&gt;
</pre></div>
</div>
</section>
</section>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="additional-outputs.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">Additional Outputs</p>
</div>
</a>
<a class="right-next"
href="speculative-decoding.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Speculative Decoding</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="#online-api-trtllm-serve">Online API: <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code></a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#json-schema">JSON Schema</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#regular-expression">Regular expression</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#ebnf-grammar">EBNF grammar</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#structural-tag">Structural tag</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#offline-api-llm-api">Offline API: LLM API</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id1">JSON Schema</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id2">Regular expression</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id3">EBNF grammar</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id4">Structural tag</a></li>
</ul>
</li>
</ul>
</nav></div>
</div></div>
</div>
<footer class="bd-footer-content">
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script defer src="../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf"></script>
<script defer src="../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf"></script>
<footer class="bd-footer">
<div class="bd-footer__inner bd-page-width">
<div class="footer-items__start">
<div class="footer-item">
<a class="footer-brand logo" href="https://www.nvidia.com">
<img src="../_static/nvidia-logo-horiz-rgb-1c-blk-for-screen.svg" class="logo__image only-light" alt="NVIDIA"/>
<img src="../_static/nvidia-logo-horiz-rgb-1c-wht-for-screen.svg" class="logo__image only-dark" alt="NVIDIA"/>
</a></div>
<div class="footer-item">
<div class="footer-links">
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/">Privacy Policy</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-center/">Your Privacy Choices</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/terms-of-service/">Terms of Service</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/accessibility/">Accessibility</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/company-policies/">Corporate Policies</a>
|
<a class="external" href="https://www.nvidia.com/en-us/product-security/">Product Security</a>
|
<a class="external" href="https://www.nvidia.com/en-us/contact/">Contact</a>
</div>
</div>
<div class="footer-item">
<p class="copyright">
Copyright © 2025, NVidia.
<br/>
</p>
</div>
<div class="footer-item">
<div class="extra_footer">
<p>Last updated on December 15, 2025.</p>
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/9ba1426">9ba1426</a>.</p>
</div></div>
</div>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink