mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
1041 lines
62 KiB
HTML
1041 lines
62 KiB
HTML
|
||
|
||
<!DOCTYPE html>
|
||
|
||
|
||
<html lang="en" data-content_root="../" >
|
||
|
||
<head>
|
||
<meta charset="utf-8" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||
|
||
<title>LLM API Change Guide — TensorRT LLM</title>
|
||
|
||
|
||
|
||
<script data-cfasync="false">
|
||
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
|
||
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
|
||
</script>
|
||
<!--
|
||
this give us a css class that will be invisible only if js is disabled
|
||
-->
|
||
<noscript>
|
||
<style>
|
||
.pst-js-only { display: none !important; }
|
||
|
||
</style>
|
||
</noscript>
|
||
|
||
<!-- Loaded before other Sphinx assets -->
|
||
<link href="../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
|
||
<link href="../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
|
||
|
||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=8f2a1f02" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/styles/nvidia-sphinx-theme.css?v=df3ac72c" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/copybutton.css?v=76b2166b" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/autodoc_pydantic.css" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/togglebutton.css?v=13237357" />
|
||
<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 = 'developer-guide/api-change';</script>
|
||
<script>
|
||
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.2.0rc2';
|
||
DOCUMENTATION_OPTIONS.show_version_warning_banner =
|
||
false;
|
||
</script>
|
||
<link rel="icon" href="../_static/favicon.png"/>
|
||
<link rel="index" title="Index" href="../genindex.html" />
|
||
<link rel="search" title="Search" href="../search.html" />
|
||
<link rel="next" title="Introduction to KV Cache Transmission" href="kv-transfer.html" />
|
||
<link rel="prev" title="Using Dev Containers" href="dev-containers.html" />
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
||
<meta name="docsearch:language" content="en"/>
|
||
<meta name="docsearch:version" content="1.2.0rc2" />
|
||
|
||
|
||
</head>
|
||
|
||
|
||
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
|
||
|
||
|
||
|
||
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
|
||
|
||
<div id="pst-scroll-pixel-helper"></div>
|
||
|
||
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
|
||
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
|
||
|
||
|
||
<dialog id="pst-search-dialog">
|
||
|
||
<form class="bd-search d-flex align-items-center"
|
||
action="../search.html"
|
||
method="get">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<input type="search"
|
||
class="form-control"
|
||
name="q"
|
||
placeholder="Search the docs ..."
|
||
aria-label="Search the docs ..."
|
||
autocomplete="off"
|
||
autocorrect="off"
|
||
autocapitalize="off"
|
||
spellcheck="false"/>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
|
||
</form>
|
||
</dialog>
|
||
|
||
<div class="pst-async-banner-revealer d-none">
|
||
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
|
||
</div>
|
||
|
||
|
||
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
|
||
<div class="bd-header__inner bd-page-width">
|
||
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
|
||
<span class="fa-solid fa-bars"></span>
|
||
</button>
|
||
|
||
|
||
<div class="col-lg-3 navbar-header-items__start">
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
|
||
|
||
|
||
<a class="navbar-brand logo" href="../index.html">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<img src="../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT LLM - Home"/>
|
||
<img src="../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT LLM - Home"/>
|
||
|
||
|
||
<p class="title logo__title">TensorRT LLM</p>
|
||
|
||
</a></div>
|
||
|
||
</div>
|
||
|
||
<div class="col-lg-9 navbar-header-items">
|
||
|
||
<div class="me-auto navbar-header-items__center">
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
<div class="version-switcher__container dropdown pst-js-only">
|
||
<button id="pst-version-switcher-button-2"
|
||
type="button"
|
||
class="version-switcher__button btn btn-sm dropdown-toggle"
|
||
data-bs-toggle="dropdown"
|
||
aria-haspopup="listbox"
|
||
aria-controls="pst-version-switcher-list-2"
|
||
aria-label="Version switcher list"
|
||
>
|
||
Choose version <!-- this text may get changed later by javascript -->
|
||
<span class="caret"></span>
|
||
</button>
|
||
<div id="pst-version-switcher-list-2"
|
||
class="version-switcher__menu dropdown-menu list-group-flush py-0"
|
||
role="listbox" aria-labelledby="pst-version-switcher-button-2">
|
||
<!-- dropdown will be populated by javascript on page load -->
|
||
</div>
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="navbar-header-items__end">
|
||
|
||
<div class="navbar-item navbar-persistent--container">
|
||
|
||
|
||
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
</div>
|
||
|
||
|
||
<div class="navbar-item">
|
||
|
||
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
||
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
||
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
||
</button></div>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="navbar-persistent--mobile">
|
||
|
||
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
</div>
|
||
|
||
|
||
|
||
<button class="pst-navbar-icon sidebar-toggle secondary-toggle" aria-label="On this page">
|
||
<span class="fa-solid fa-outdent"></span>
|
||
</button>
|
||
|
||
</div>
|
||
|
||
</header>
|
||
|
||
|
||
<div class="bd-container">
|
||
<div class="bd-container__inner bd-page-width">
|
||
|
||
|
||
|
||
<dialog id="pst-primary-sidebar-modal"></dialog>
|
||
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<a class="navbar-brand logo" href="../index.html">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<img src="../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT LLM - Home"/>
|
||
<img src="../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT LLM - Home"/>
|
||
|
||
|
||
<p class="title logo__title">TensorRT LLM</p>
|
||
|
||
</a>
|
||
|
||
|
||
|
||
<div class="sidebar-header-items sidebar-primary__section">
|
||
|
||
|
||
<div class="sidebar-header-items__center">
|
||
|
||
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
<div class="version-switcher__container dropdown pst-js-only">
|
||
<button id="pst-version-switcher-button-3"
|
||
type="button"
|
||
class="version-switcher__button btn btn-sm dropdown-toggle"
|
||
data-bs-toggle="dropdown"
|
||
aria-haspopup="listbox"
|
||
aria-controls="pst-version-switcher-list-3"
|
||
aria-label="Version switcher list"
|
||
>
|
||
Choose version <!-- this text may get changed later by javascript -->
|
||
<span class="caret"></span>
|
||
</button>
|
||
<div id="pst-version-switcher-list-3"
|
||
class="version-switcher__menu dropdown-menu list-group-flush py-0"
|
||
role="listbox" aria-labelledby="pst-version-switcher-button-3">
|
||
<!-- dropdown will be populated by javascript on page load -->
|
||
</div>
|
||
</div></div>
|
||
|
||
|
||
</div>
|
||
|
||
|
||
|
||
<div class="sidebar-header-items__end">
|
||
|
||
<div class="navbar-item">
|
||
|
||
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
||
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
||
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
||
</button></div>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
|
||
<div class="sidebar-primary-items__start sidebar-primary__section">
|
||
<div class="sidebar-primary-item">
|
||
|
||
|
||
|
||
<nav class="bd-docs-nav bd-links"
|
||
aria-label="Table of Contents">
|
||
<p class="bd-links__title" role="heading" aria-level="1">Table of Contents</p>
|
||
<div class="bd-toc-item navbar-nav"><p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../overview.html">Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../quick-start-guide.html">Quick Start Guide</a></li>
|
||
<li class="toctree-l1 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/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>
|
||
</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 & 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 & 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 & 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-next-on-trtllm.html">Deployment Guide for Qwen3 Next on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Models</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../models/supported-models.html">Supported Models</a></li>
|
||
|
||
<li class="toctree-l1"><a class="reference internal" href="../models/adding-new-model.html">Adding a New Model</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">CLI Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-bench.html">trtllm-bench</a></li>
|
||
|
||
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-eval.html">trtllm-eval</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../commands/trtllm-serve/index.html">trtllm-serve</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../commands/trtllm-serve/trtllm-serve.html">trtllm-serve</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../commands/trtllm-serve/run-benchmark-with-trtllm-serve.html">Run benchmarking with <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code></a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">API Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../llm-api/index.html">LLM API Introduction</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../llm-api/reference.html">API Reference</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Features</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/feature-combination-matrix.html">Feature Combination Matrix</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/disagg-serving.html">Disaggregated Serving</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/kvcache.html">KV Cache System</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/long-sequence.html">Long Sequences</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/lora.html">LoRA (Low-Rank Adaptation)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/multi-modality.html">Multimodal Support in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/overlap-scheduler.html">Overlap Scheduler</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/paged-attention-ifb-scheduler.html">Paged Attention, IFB, and Request Scheduling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/parallel-strategy.html">Parallelism in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/quantization.html">Quantization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/sampling.html">Sampling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/additional-outputs.html">Additional Outputs</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/speculative-decoding.html">Speculative Decoding</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/checkpoint-loading.html">Checkpoint Loading</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/auto_deploy/auto-deploy.html">AutoDeploy (Prototype)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/ray-orchestrator.html">Ray Orchestrator (Prototype)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/torch_compile_and_piecewise_cuda_graph.html">Torch Compile & Piecewise CUDA Graph</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Developer Guide</span></p>
|
||
<ul class="current nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="overview.html">Architecture Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="perf-analysis.html">Performance Analysis</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="perf-benchmarking.html">TensorRT LLM Benchmarking</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="ci-overview.html">Continuous Integration Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="dev-containers.html">Using Dev Containers</a></li>
|
||
<li class="toctree-l1 current active"><a class="current reference internal" href="#">LLM API Change Guide</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="kv-transfer.html">Introduction to KV Cache Transmission</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog10_ADP_Balance_Strategy.html">ADP Balance Strategy</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog11_GPT_OSS_Eagle3.html">Running GPT-OSS-120B with Eagle3 Speculative Decoding on GB200/B200 (TensorRT LLM)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.html">Combining Guided Decoding and Speculative Decoding: Making CPU and GPU Cooperate Seamlessly</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog13_Inference_Time_Compute_Implementation_in_TensorRT-LLM.html">Inference Time Compute Implementation in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog14_Scaling_Expert_Parallelism_in_TensorRT-LLM_part3.html">Scaling Expert Parallelism in TensorRT LLM (Part 3: Pushing the Performance Boundary)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html">Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html">DeepSeek R1 MTP Implementation and Optimization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html">Optimizing DeepSeek R1 Throughput on NVIDIA Blackwell GPUs: A Deep Dive for Developers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html">Scaling Expert Parallelism in TensorRT LLM (Part 1: Design and Implementation of Large-scale EP)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html">Disaggregated Serving in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html">How to launch Llama4 Maverick + Eagle3 TensorRT LLM server</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html">N-Gram Speculative Decoding in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html">Scaling Expert Parallelism in TensorRT LLM (Part 2: Performance Status and Optimization)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html">Running a High Performance GPT-OSS-120B Inference Server with TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.html">How to get best performance on DeepSeek-R1 in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Quick Links</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/releases">Releases</a></li>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM">Github Code</a></li>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/issues?q=is%3Aissue%20state%3Aopen%20label%3Aroadmap">Roadmap</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Use TensorRT Engine</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../legacy/tensorrt_quickstart.html">LLM API with TensorRT Engine</a></li>
|
||
</ul>
|
||
</div>
|
||
</nav></div>
|
||
</div>
|
||
|
||
|
||
<div class="sidebar-primary-items__end sidebar-primary__section">
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
<main id="main-content" class="bd-main" role="main">
|
||
|
||
|
||
<div class="bd-content">
|
||
<div class="bd-article-container">
|
||
|
||
<div class="bd-header-article d-print-none">
|
||
<div class="header-article-items header-article__inner">
|
||
|
||
<div class="header-article-items__start">
|
||
|
||
<div class="header-article-item">
|
||
|
||
<nav aria-label="Breadcrumb" class="d-print-none">
|
||
<ul class="bd-breadcrumbs">
|
||
|
||
<li class="breadcrumb-item breadcrumb-home">
|
||
<a href="../index.html" class="nav-link" aria-label="Home">
|
||
<i class="fa-solid fa-home"></i>
|
||
</a>
|
||
</li>
|
||
<li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">LLM API Change Guide</span></li>
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<div id="searchbox"></div>
|
||
<article class="bd-article">
|
||
|
||
<section class="tex2jax_ignore mathjax_ignore" id="llm-api-change-guide">
|
||
<h1>LLM API Change Guide<a class="headerlink" href="#llm-api-change-guide" title="Link to this heading">#</a></h1>
|
||
<p>This guide explains how to modify and manage APIs in TensorRT LLM, focusing on the high-level LLM API.</p>
|
||
<section id="overview">
|
||
<h2>Overview<a class="headerlink" href="#overview" title="Link to this heading">#</a></h2>
|
||
<p>TensorRT LLM provides multiple API levels:</p>
|
||
<ol class="arabic simple">
|
||
<li><p><strong>LLM API</strong> - The highest-level API (e.g., the <code class="docutils literal notranslate"><span class="pre">LLM</span></code> class)</p></li>
|
||
<li><p><strong>PyExecutor API</strong> - The mid-level API (e.g., the <code class="docutils literal notranslate"><span class="pre">PyExecutor</span></code> class)</p></li>
|
||
</ol>
|
||
<p>This guide focuses on the LLM API, which is the primary interface for most users.</p>
|
||
</section>
|
||
<section id="api-types-and-stability-guarantees">
|
||
<h2>API Types and Stability Guarantees<a class="headerlink" href="#api-types-and-stability-guarantees" title="Link to this heading">#</a></h2>
|
||
<p>TensorRT LLM classifies APIs into two categories:</p>
|
||
<section id="committed-apis">
|
||
<h3>1. Committed APIs<a class="headerlink" href="#committed-apis" title="Link to this heading">#</a></h3>
|
||
<ul class="simple">
|
||
<li><p><strong>Stable</strong> and guaranteed to remain consistent across releases</p></li>
|
||
<li><p>No breaking changes without major version updates</p></li>
|
||
<li><p>Schema stored in: <code class="docutils literal notranslate"><span class="pre">tests/unittest/api_stability/references_committed/</span></code></p></li>
|
||
</ul>
|
||
</section>
|
||
<section id="non-committed-apis">
|
||
<h3>2. Non-committed APIs<a class="headerlink" href="#non-committed-apis" title="Link to this heading">#</a></h3>
|
||
<ul class="simple">
|
||
<li><p>Under active development and may change between releases</p></li>
|
||
<li><p>Marked with a <code class="docutils literal notranslate"><span class="pre">status</span></code> field in the docstring:</p>
|
||
<ul>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">prototype</span></code> - Early experimental stage</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">beta</span></code> - More stable but still subject to change</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">deprecated</span></code> - Scheduled for removal</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p>Schema stored in: <code class="docutils literal notranslate"><span class="pre">tests/unittest/api_stability/references/</span></code></p></li>
|
||
<li><p>See <a class="reference external" href="https://nvidia.github.io/TensorRT-LLM/llm-api/reference.html">API status documentation</a> for complete details</p></li>
|
||
</ul>
|
||
</section>
|
||
</section>
|
||
<section id="api-schema-management">
|
||
<h2>API Schema Management<a class="headerlink" href="#api-schema-management" title="Link to this heading">#</a></h2>
|
||
<p>All API schemas are:</p>
|
||
<ul class="simple">
|
||
<li><p>Stored as YAML files in the codebase</p></li>
|
||
<li><p>Protected by unit tests in <code class="docutils literal notranslate"><span class="pre">tests/unittest/api_stability/</span></code></p></li>
|
||
<li><p>Automatically validated to ensure consistency</p></li>
|
||
</ul>
|
||
</section>
|
||
<section id="api-change-principles">
|
||
<h2>API Change Principles<a class="headerlink" href="#api-change-principles" title="Link to this heading">#</a></h2>
|
||
<section id="knob-naming">
|
||
<h3>1. Knob Naming<a class="headerlink" href="#knob-naming" title="Link to this heading">#</a></h3>
|
||
<p><strong>Use Semantic Clarity</strong></p>
|
||
<p>Argument names should describe what the argument represents, not how it is used internally.</p>
|
||
<p>✅ <strong>Good</strong>: <code class="docutils literal notranslate"><span class="pre">max_new_tokens</span></code> (clear meaning)<br />
|
||
❌ <strong>Bad</strong>: <code class="docutils literal notranslate"><span class="pre">num</span></code> (ambiguous)</p>
|
||
<p><strong>Reflect Argument Type and Granularity</strong></p>
|
||
<ul class="simple">
|
||
<li><p>For <strong>boolean</strong> knobs, prefix with verbs like <code class="docutils literal notranslate"><span class="pre">enable_</span></code> and so on.
|
||
Examples: <code class="docutils literal notranslate"><span class="pre">enable_cache</span></code>, <code class="docutils literal notranslate"><span class="pre">enable_flash_attention</span></code></p></li>
|
||
<li><p>For <strong>numerical threshold</strong> knobs, suffix with <code class="docutils literal notranslate"><span class="pre">_limit</span></code>, <code class="docutils literal notranslate"><span class="pre">_size</span></code>, <code class="docutils literal notranslate"><span class="pre">_count</span></code>, <code class="docutils literal notranslate"><span class="pre">_len_</span></code> or <code class="docutils literal notranslate"><span class="pre">_ratio</span></code><br />
|
||
Examples: <code class="docutils literal notranslate"><span class="pre">max_seq_len</span></code>, <code class="docutils literal notranslate"><span class="pre">prefill_batch_size</span></code></p></li>
|
||
</ul>
|
||
<p><strong>Avoid Redundant Prefixes</strong></p>
|
||
<p>Example (in <code class="docutils literal notranslate"><span class="pre">MoeConfig</span></code>):</p>
|
||
<p>✅ <strong>Good</strong>: <code class="docutils literal notranslate"><span class="pre">backend</span></code><br />
|
||
❌ <strong>Bad</strong>: <code class="docutils literal notranslate"><span class="pre">moe_backend</span></code> (redundant since it’s already in <code class="docutils literal notranslate"><span class="pre">MoeConfig</span></code>)</p>
|
||
<p><strong>Use Specific Names for Narrow Scenarios</strong></p>
|
||
<p>When adding knobs for specific use cases, make the name convey the restriction clearly via a prefix. It’s acceptable to rename later when the knob becomes more generic or is moved into a dedicated config.</p>
|
||
<p>Example (argument to the LLM class):</p>
|
||
<p>✅ <strong>Good</strong>: <code class="docutils literal notranslate"><span class="pre">rope_scaling_factor</span></code> → clearly indicates it’s for RoPE<br />
|
||
❌ <strong>Bad</strong>: <code class="docutils literal notranslate"><span class="pre">scaling_factor</span></code> → too generic and prone to misuse</p>
|
||
</section>
|
||
<section id="hierarchical-configuration">
|
||
<h3>2. Hierarchical Configuration<a class="headerlink" href="#hierarchical-configuration" title="Link to this heading">#</a></h3>
|
||
<p>Organize complex or hierarchical arguments into <strong>dedicated configuration dataclasses</strong> with intuitive and consistent naming.</p>
|
||
<p><strong>Guidelines</strong></p>
|
||
<ul class="simple">
|
||
<li><p>Use the <code class="docutils literal notranslate"><span class="pre">XxxConfig</span></code> suffix consistently<br />
|
||
Examples: <code class="docutils literal notranslate"><span class="pre">ModelConfig</span></code>, <code class="docutils literal notranslate"><span class="pre">ParallelConfig</span></code>, <code class="docutils literal notranslate"><span class="pre">MoeConfig</span></code></p></li>
|
||
<li><p><strong>Reflect conceptual hierarchy</strong><br />
|
||
The dataclass name should represent a coherent functional unit, not an arbitrary grouping</p></li>
|
||
<li><p><strong>Avoid over-nesting</strong><br />
|
||
Use only one level of configuration hierarchy whenever possible (e.g., <code class="docutils literal notranslate"><span class="pre">LlmArgs</span> <span class="pre">→</span> <span class="pre">ParallelConfig</span></code>) to balance readability and modularity</p></li>
|
||
</ul>
|
||
</section>
|
||
<section id="prefer-llmargs-over-environment-variables">
|
||
<h3>3. Prefer <code class="docutils literal notranslate"><span class="pre">LlmArgs</span></code> Over Environment Variables<a class="headerlink" href="#prefer-llmargs-over-environment-variables" title="Link to this heading">#</a></h3>
|
||
<p><code class="docutils literal notranslate"><span class="pre">LlmArgs</span></code> is the central place for all configuration knobs. It integrates with our infrastructure to ensure:</p>
|
||
<ul class="simple">
|
||
<li><p><strong>API Stability</strong></p>
|
||
<ul>
|
||
<li><p>Protects committed (stable) APIs</p></li>
|
||
<li><p>GitHub reviewer committee oversees API stability</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p><strong>API Status Registration</strong></p>
|
||
<ul>
|
||
<li><p>Uncommitted (unstable) APIs must be marked as <code class="docutils literal notranslate"><span class="pre">"prototype"</span></code> or <code class="docutils literal notranslate"><span class="pre">"beta"</span></code></p></li>
|
||
<li><p>API statuses are displayed in the documentation</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p><strong>API Documentation</strong></p>
|
||
<ul>
|
||
<li><p>Each knob uses a <code class="docutils literal notranslate"><span class="pre">Field</span></code> with a description</p></li>
|
||
<li><p>Automatically rendered in public documentation</p></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
<blockquote>
|
||
<div><p>Managing knobs in <code class="docutils literal notranslate"><span class="pre">LlmArgs</span></code> remains <strong>scalable and maintainable</strong> thanks to our existing infrastructure and review processes.</p>
|
||
</div></blockquote>
|
||
<p><strong>Drawbacks of Environment Variables:</strong></p>
|
||
<ul class="simple">
|
||
<li><p>Dispersed across the codebase</p></li>
|
||
<li><p>Lack documentation and discoverability</p></li>
|
||
<li><p>Pose challenges for testing and validation</p></li>
|
||
</ul>
|
||
<p><strong>Guidelines for Adding Knobs:</strong></p>
|
||
<ul class="simple">
|
||
<li><p>✅ Add clear, descriptive documentation for each field</p></li>
|
||
<li><p>✅ It’s fine to add temporary knobs and refine them later</p></li>
|
||
<li><p>⚠️ Always mark temporary knobs as <code class="docutils literal notranslate"><span class="pre">"prototype"</span></code> if not stable yet</p></li>
|
||
<li><p>✅ Refactor prototype knobs as they mature, promote them to “beta” or “stable”.</p></li>
|
||
</ul>
|
||
</section>
|
||
</section>
|
||
<section id="modifying-llm-constructor-arguments">
|
||
<h2>Modifying LLM Constructor Arguments<a class="headerlink" href="#modifying-llm-constructor-arguments" title="Link to this heading">#</a></h2>
|
||
<p>The LLM class accepts numerous configuration parameters for models, runtime, and other components. These are managed through a Pydantic dataclass called <code class="docutils literal notranslate"><span class="pre">LlmArgs</span></code>.</p>
|
||
<section id="architecture">
|
||
<h3>Architecture<a class="headerlink" href="#architecture" title="Link to this heading">#</a></h3>
|
||
<ul class="simple">
|
||
<li><p>The LLM’s <code class="docutils literal notranslate"><span class="pre">__init__</span></code> method parameters map directly to <code class="docutils literal notranslate"><span class="pre">LlmArgs</span></code> fields</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">LlmArgs</span></code> is an alias for <code class="docutils literal notranslate"><span class="pre">TorchLlmArgs</span></code> (defined in <code class="docutils literal notranslate"><span class="pre">tensorrt_llm/llmapi/llm_args.py</span></code>)</p></li>
|
||
<li><p>All arguments are validated and type-checked through Pydantic</p></li>
|
||
</ul>
|
||
</section>
|
||
<section id="adding-a-new-argument">
|
||
<h3>Adding a New Argument<a class="headerlink" href="#adding-a-new-argument" title="Link to this heading">#</a></h3>
|
||
<p>Follow these steps to add a new constructor argument:</p>
|
||
<section id="add-the-field-to-torchllmargs">
|
||
<h4>1. Add the field to <code class="docutils literal notranslate"><span class="pre">TorchLlmArgs</span></code><a class="headerlink" href="#add-the-field-to-torchllmargs" title="Link to this heading">#</a></h4>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">garbage_collection_gen0_threshold</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="n">Field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="mi">20000</span><span class="p">,</span>
|
||
<span class="n">description</span><span class="o">=</span><span class="p">(</span>
|
||
<span class="s2">"Threshold for Python garbage collection of generation 0 objects. "</span>
|
||
<span class="s2">"Lower values trigger more frequent garbage collection."</span>
|
||
<span class="p">),</span>
|
||
<span class="n">status</span><span class="o">=</span><span class="s2">"beta"</span> <span class="c1"># Required for non-committed arguments</span>
|
||
<span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
<p><strong>Field requirements:</strong></p>
|
||
<ul class="simple">
|
||
<li><p><strong>Type annotation</strong>: Required for all fields</p></li>
|
||
<li><p><strong>Default value</strong>: Recommended unless the field is mandatory</p></li>
|
||
<li><p><strong>Description</strong>: Clear explanation of the parameter’s purpose</p></li>
|
||
<li><p><strong>Status</strong>: Required for non-committed arguments (<code class="docutils literal notranslate"><span class="pre">prototype</span></code>, <code class="docutils literal notranslate"><span class="pre">beta</span></code>, etc.)</p></li>
|
||
</ul>
|
||
</section>
|
||
<section id="update-the-api-schema">
|
||
<h4>2. Update the API schema<a class="headerlink" href="#update-the-api-schema" title="Link to this heading">#</a></h4>
|
||
<p>Add the field to the appropriate schema file:</p>
|
||
<ul>
|
||
<li><p><strong>Non-committed arguments</strong>: <code class="docutils literal notranslate"><span class="pre">tests/unittest/api_stability/references/llm_args.yaml</span></code></p>
|
||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><span class="nt">garbage_collection_gen0_threshold</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">int</span>
|
||
<span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">20000</span>
|
||
<span class="w"> </span><span class="nt">status</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">beta</span><span class="w"> </span><span class="c1"># Must match the status in code</span>
|
||
</pre></div>
|
||
</div>
|
||
</li>
|
||
<li><p><strong>Committed arguments</strong>: <code class="docutils literal notranslate"><span class="pre">tests/unittest/api_stability/references_committed/llm_args.yaml</span></code></p>
|
||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><span class="nt">garbage_collection_gen0_threshold</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">int</span>
|
||
<span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">20000</span>
|
||
<span class="w"> </span><span class="c1"># No status field for committed arguments</span>
|
||
</pre></div>
|
||
</div>
|
||
</li>
|
||
</ul>
|
||
</section>
|
||
<section id="run-validation-tests">
|
||
<h4>3. Run validation tests<a class="headerlink" href="#run-validation-tests" title="Link to this heading">#</a></h4>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>python<span class="w"> </span>-m<span class="w"> </span>pytest<span class="w"> </span>tests/unittest/api_stability/test_llm_api.py
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
</section>
|
||
</section>
|
||
<section id="modifying-llm-class-methods">
|
||
<h2>Modifying LLM Class Methods<a class="headerlink" href="#modifying-llm-class-methods" title="Link to this heading">#</a></h2>
|
||
<p>Public methods in the LLM class constitute the API surface. All changes must be properly documented and tracked.</p>
|
||
<section id="implementation-details">
|
||
<h3>Implementation Details<a class="headerlink" href="#implementation-details" title="Link to this heading">#</a></h3>
|
||
<ul class="simple">
|
||
<li><p>The actual implementation is in the <code class="docutils literal notranslate"><span class="pre">_TorchLLM</span></code> class (<a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/blob/release/1.0/tensorrt_llm/llmapi/llm.py">llm.py</a>)</p></li>
|
||
<li><p>Public methods (not starting with <code class="docutils literal notranslate"><span class="pre">_</span></code>) are automatically exposed as APIs</p></li>
|
||
</ul>
|
||
</section>
|
||
<section id="adding-a-new-method">
|
||
<h3>Adding a New Method<a class="headerlink" href="#adding-a-new-method" title="Link to this heading">#</a></h3>
|
||
<p>Follow these steps to add a new API method:</p>
|
||
<section id="implement-the-method-in-torchllm">
|
||
<h4>1. Implement the method in <code class="docutils literal notranslate"><span class="pre">_TorchLLM</span></code><a class="headerlink" href="#implement-the-method-in-torchllm" title="Link to this heading">#</a></h4>
|
||
<p>For non-committed APIs, use the <code class="docutils literal notranslate"><span class="pre">@set_api_status</span></code> decorator:</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="nd">@set_api_status</span><span class="p">(</span><span class="s2">"beta"</span><span class="p">)</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">generate_with_streaming</span><span class="p">(</span>
|
||
<span class="bp">self</span><span class="p">,</span>
|
||
<span class="n">prompts</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">],</span>
|
||
<span class="o">**</span><span class="n">kwargs</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="n">Iterator</span><span class="p">[</span><span class="n">GenerationOutput</span><span class="p">]:</span>
|
||
<span class="w"> </span><span class="sd">"""Generate text with streaming output.</span>
|
||
<span class="sd"> </span>
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> prompts: Input prompts for generation</span>
|
||
<span class="sd"> **kwargs: Additional generation parameters</span>
|
||
<span class="sd"> </span>
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> Iterator of generation outputs</span>
|
||
<span class="sd"> """</span>
|
||
<span class="c1"># Implementation here</span>
|
||
<span class="k">pass</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>For committed APIs, no decorator is needed:</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">def</span><span class="w"> </span><span class="nf">generate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">prompts</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">],</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> <span class="o">-></span> <span class="n">GenerationOutput</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""Generate text from prompts."""</span>
|
||
<span class="c1"># Implementation here</span>
|
||
<span class="k">pass</span>
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
<section id="id1">
|
||
<h4>2. Update the API schema<a class="headerlink" href="#id1" title="Link to this heading">#</a></h4>
|
||
<p>Add the method to the appropriate <code class="docutils literal notranslate"><span class="pre">llm.yaml</span></code> file:</p>
|
||
<p><strong>Non-committed API</strong> (<code class="docutils literal notranslate"><span class="pre">tests/unittest/api_stability/references/llm.yaml</span></code>):</p>
|
||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><span class="nt">generate_with_streaming</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="nt">status</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">beta</span><span class="w"> </span><span class="c1"># Must match @set_api_status</span>
|
||
<span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">prompts</span>
|
||
<span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">List[str]</span>
|
||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">kwargs</span>
|
||
<span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">dict</span>
|
||
<span class="w"> </span><span class="nt">returns</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Iterator[GenerationOutput]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p><strong>Committed API</strong> (<code class="docutils literal notranslate"><span class="pre">tests/unittest/api_stability/references_committed/llm.yaml</span></code>):</p>
|
||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><span class="nt">generate</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">prompts</span>
|
||
<span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">List[str]</span>
|
||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">kwargs</span>
|
||
<span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">dict</span>
|
||
<span class="w"> </span><span class="nt">returns</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">GenerationOutput</span>
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
</section>
|
||
<section id="modifying-existing-methods">
|
||
<h3>Modifying Existing Methods<a class="headerlink" href="#modifying-existing-methods" title="Link to this heading">#</a></h3>
|
||
<p>When modifying existing methods:</p>
|
||
<ol class="arabic simple">
|
||
<li><p><strong>Non-breaking changes</strong> (adding optional parameters):</p>
|
||
<ul class="simple">
|
||
<li><p>Update the method signature</p></li>
|
||
<li><p>Update the schema file</p></li>
|
||
<li><p>No status change needed</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p><strong>Breaking changes</strong> (changing required parameters, return types):</p>
|
||
<ul class="simple">
|
||
<li><p>Only allowed for non-committed APIs</p></li>
|
||
<li><p>Consider deprecation path for beta APIs</p></li>
|
||
<li><p>Update documentation with migration guide</p></li>
|
||
</ul>
|
||
</li>
|
||
</ol>
|
||
</section>
|
||
<section id="best-practices">
|
||
<h3>Best Practices<a class="headerlink" href="#best-practices" title="Link to this heading">#</a></h3>
|
||
<ol class="arabic simple">
|
||
<li><p><strong>Documentation</strong>: Always include comprehensive docstrings</p></li>
|
||
<li><p><strong>Type hints</strong>: Use proper type annotations for all parameters and returns</p></li>
|
||
<li><p><strong>Testing</strong>: Add unit tests for new methods</p></li>
|
||
<li><p><strong>Examples</strong>: Provide usage examples in the docstring</p></li>
|
||
<li><p><strong>Validation</strong>: Run API stability tests before submitting changes</p></li>
|
||
</ol>
|
||
</section>
|
||
<section id="running-tests">
|
||
<h3>Running Tests<a class="headerlink" href="#running-tests" title="Link to this heading">#</a></h3>
|
||
<p>Validate your changes:</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Run API stability tests</span>
|
||
python<span class="w"> </span>-m<span class="w"> </span>pytest<span class="w"> </span>tests/unittest/api_stability/
|
||
|
||
<span class="c1"># Run specific test for LLM API</span>
|
||
python<span class="w"> </span>-m<span class="w"> </span>pytest<span class="w"> </span>tests/unittest/api_stability/test_llm_api.py<span class="w"> </span>-v
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
</section>
|
||
<section id="common-workflows">
|
||
<h2>Common Workflows<a class="headerlink" href="#common-workflows" title="Link to this heading">#</a></h2>
|
||
<section id="promoting-an-api-from-beta-to-committed">
|
||
<h3>Promoting an API from Beta to Committed<a class="headerlink" href="#promoting-an-api-from-beta-to-committed" title="Link to this heading">#</a></h3>
|
||
<ol class="arabic simple">
|
||
<li><p>Remove the <code class="docutils literal notranslate"><span class="pre">@set_api_status("beta")</span></code> decorator from the method</p></li>
|
||
<li><p>Move the schema entry from <code class="docutils literal notranslate"><span class="pre">tests/unittest/api_stability/references/</span></code> to <code class="docutils literal notranslate"><span class="pre">tests/unittest/api_stability/references_committed/</span></code></p></li>
|
||
<li><p>Remove the <code class="docutils literal notranslate"><span class="pre">status</span></code> field from the schema</p></li>
|
||
<li><p>Update any documentation referring to the API’s beta status</p></li>
|
||
</ol>
|
||
</section>
|
||
<section id="deprecating-an-api">
|
||
<h3>Deprecating an API<a class="headerlink" href="#deprecating-an-api" title="Link to this heading">#</a></h3>
|
||
<ol class="arabic">
|
||
<li><p>Add <code class="docutils literal notranslate"><span class="pre">@set_api_status("deprecated")</span></code> to the method</p></li>
|
||
<li><p>Update the schema with <code class="docutils literal notranslate"><span class="pre">status:</span> <span class="pre">deprecated</span></code></p></li>
|
||
<li><p>Add deprecation warning in the method:</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">warnings</span>
|
||
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span>
|
||
<span class="s2">"This method is deprecated and will be removed in v2.0. "</span>
|
||
<span class="s2">"Use new_method() instead."</span><span class="p">,</span>
|
||
<span class="ne">DeprecationWarning</span><span class="p">,</span>
|
||
<span class="n">stacklevel</span><span class="o">=</span><span class="mi">2</span>
|
||
<span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</li>
|
||
<li><p>Document the migration path</p></li>
|
||
</ol>
|
||
</section>
|
||
</section>
|
||
</section>
|
||
|
||
|
||
</article>
|
||
|
||
|
||
|
||
|
||
|
||
<footer class="prev-next-footer d-print-none">
|
||
|
||
<div class="prev-next-area">
|
||
<a class="left-prev"
|
||
href="dev-containers.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">Using Dev Containers</p>
|
||
</div>
|
||
</a>
|
||
<a class="right-next"
|
||
href="kv-transfer.html"
|
||
title="next page">
|
||
<div class="prev-next-info">
|
||
<p class="prev-next-subtitle">next</p>
|
||
<p class="prev-next-title">Introduction to KV Cache Transmission</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="#overview">Overview</a></li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#api-types-and-stability-guarantees">API Types and Stability Guarantees</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#committed-apis">1. Committed APIs</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#non-committed-apis">2. Non-committed APIs</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#api-schema-management">API Schema Management</a></li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#api-change-principles">API Change Principles</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#knob-naming">1. Knob Naming</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#hierarchical-configuration">2. Hierarchical Configuration</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#prefer-llmargs-over-environment-variables">3. Prefer <code class="docutils literal notranslate"><span class="pre">LlmArgs</span></code> Over Environment Variables</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#modifying-llm-constructor-arguments">Modifying LLM Constructor Arguments</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#architecture">Architecture</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#adding-a-new-argument">Adding a New Argument</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#add-the-field-to-torchllmargs">1. Add the field to <code class="docutils literal notranslate"><span class="pre">TorchLlmArgs</span></code></a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#update-the-api-schema">2. Update the API schema</a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#run-validation-tests">3. Run validation tests</a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#modifying-llm-class-methods">Modifying LLM Class Methods</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#implementation-details">Implementation Details</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#adding-a-new-method">Adding a New Method</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#implement-the-method-in-torchllm">1. Implement the method in <code class="docutils literal notranslate"><span class="pre">_TorchLLM</span></code></a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#id1">2. Update the API schema</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#modifying-existing-methods">Modifying Existing Methods</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#best-practices">Best Practices</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#running-tests">Running Tests</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#common-workflows">Common Workflows</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#promoting-an-api-from-beta-to-committed">Promoting an API from Beta to Committed</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#deprecating-an-api">Deprecating an API</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/">Manage My Privacy</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/preferences/start/">Do Not Sell or Share My Data</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/terms-of-service/">Terms of Service</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/accessibility/">Accessibility</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/company-policies/">Corporate Policies</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/product-security/">Product Security</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/contact/">Contact</a>
|
||
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
<div class="footer-item">
|
||
|
||
|
||
|
||
|
||
<p class="copyright">
|
||
|
||
Copyright © 2025, NVidia.
|
||
<br/>
|
||
|
||
</p>
|
||
</div>
|
||
|
||
<div class="footer-item">
|
||
<div class="extra_footer">
|
||
|
||
<p>Last updated on November 05, 2025.</p>
|
||
|
||
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/3111682">3111682</a>.</p>
|
||
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
</footer>
|
||
</body>
|
||
</html> |