mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
894 lines
61 KiB
HTML
894 lines
61 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>Adding a New Model — TensorRT LLM</title>
|
||
|
||
|
||
|
||
<script data-cfasync="false">
|
||
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
|
||
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
|
||
</script>
|
||
<!--
|
||
this give us a css class that will be invisible only if js is disabled
|
||
-->
|
||
<noscript>
|
||
<style>
|
||
.pst-js-only { display: none !important; }
|
||
|
||
</style>
|
||
</noscript>
|
||
|
||
<!-- Loaded before other Sphinx assets -->
|
||
<link href="../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
|
||
<link href="../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
|
||
|
||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=8f2a1f02" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/styles/nvidia-sphinx-theme.css?v=933278ad" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/copybutton.css?v=76b2166b" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/autodoc_pydantic.css" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/togglebutton.css?v=13237357" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/config_selector.css?v=e17d8078" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/custom.css?v=19d20f17" />
|
||
|
||
<!-- So that users can add custom icons -->
|
||
<script src="../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script>
|
||
<!-- Pre-loaded scripts that we'll load fully later -->
|
||
<link rel="preload" as="script" href="../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" />
|
||
<link rel="preload" as="script" href="../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" />
|
||
|
||
|
||
|
||
<script src="../_static/documentation_options.js?v=5929fcd5"></script>
|
||
<script src="../_static/doctools.js?v=9a2dae69"></script>
|
||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||
<script src="../_static/clipboard.min.js?v=a7894cd8"></script>
|
||
<script src="../_static/copybutton.js?v=65e89d2a"></script>
|
||
<script src="../_static/config_selector.js?v=aaf6cd4a"></script>
|
||
<script>let toggleHintShow = 'Click to show';</script>
|
||
<script>let toggleHintHide = 'Click to hide';</script>
|
||
<script>let toggleOpenOnPrint = 'true';</script>
|
||
<script src="../_static/togglebutton.js?v=4a39c7ea"></script>
|
||
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
|
||
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
|
||
<script>DOCUMENTATION_OPTIONS.pagename = 'models/adding-new-model';</script>
|
||
<script>
|
||
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.2.0rc7';
|
||
DOCUMENTATION_OPTIONS.show_version_warning_banner =
|
||
false;
|
||
</script>
|
||
|
||
<link rel="icon" href="../_static/favicon.png"/>
|
||
|
||
<link rel="index" title="Index" href="../genindex.html" />
|
||
<link rel="search" title="Search" href="../search.html" />
|
||
<link rel="next" title="trtllm-bench" href="../commands/trtllm-bench.html" />
|
||
<link rel="prev" title="Supported Models" href="supported-models.html" />
|
||
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
||
<meta name="docsearch:language" content="en"/>
|
||
<meta name="docsearch:version" content="1.2.0rc7" />
|
||
|
||
|
||
</head>
|
||
|
||
|
||
|
||
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
|
||
|
||
|
||
|
||
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
|
||
|
||
|
||
|
||
<div id="pst-scroll-pixel-helper"></div>
|
||
|
||
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
|
||
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
|
||
|
||
|
||
<dialog id="pst-search-dialog">
|
||
|
||
<form class="bd-search d-flex align-items-center"
|
||
action="../search.html"
|
||
method="get">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<input type="search"
|
||
class="form-control"
|
||
name="q"
|
||
placeholder="Search the docs ..."
|
||
aria-label="Search the docs ..."
|
||
autocomplete="off"
|
||
autocorrect="off"
|
||
autocapitalize="off"
|
||
spellcheck="false"/>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
|
||
</form>
|
||
</dialog>
|
||
|
||
<div class="pst-async-banner-revealer d-none">
|
||
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
|
||
</div>
|
||
|
||
|
||
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
|
||
<div class="bd-header__inner bd-page-width">
|
||
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
|
||
<span class="fa-solid fa-bars"></span>
|
||
</button>
|
||
|
||
|
||
<div class="col-lg-3 navbar-header-items__start">
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
|
||
|
||
|
||
<a class="navbar-brand logo" href="../index.html">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<img src="../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT LLM - Home"/>
|
||
<img src="../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT LLM - Home"/>
|
||
|
||
|
||
<p class="title logo__title">TensorRT LLM</p>
|
||
|
||
</a></div>
|
||
|
||
</div>
|
||
|
||
<div class="col-lg-9 navbar-header-items">
|
||
|
||
<div class="me-auto navbar-header-items__center">
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
<div class="version-switcher__container dropdown pst-js-only">
|
||
<button id="pst-version-switcher-button-2"
|
||
type="button"
|
||
class="version-switcher__button btn btn-sm dropdown-toggle"
|
||
data-bs-toggle="dropdown"
|
||
aria-haspopup="listbox"
|
||
aria-controls="pst-version-switcher-list-2"
|
||
aria-label="Version switcher list"
|
||
>
|
||
Choose version <!-- this text may get changed later by javascript -->
|
||
<span class="caret"></span>
|
||
</button>
|
||
<div id="pst-version-switcher-list-2"
|
||
class="version-switcher__menu dropdown-menu list-group-flush py-0"
|
||
role="listbox" aria-labelledby="pst-version-switcher-button-2">
|
||
<!-- dropdown will be populated by javascript on page load -->
|
||
</div>
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="navbar-header-items__end">
|
||
|
||
<div class="navbar-item navbar-persistent--container">
|
||
|
||
|
||
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
</div>
|
||
|
||
|
||
<div class="navbar-item">
|
||
|
||
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
||
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
||
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
||
</button></div>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="navbar-persistent--mobile">
|
||
|
||
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
</div>
|
||
|
||
|
||
|
||
<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/aiperf_client.html">Aiperf Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/aiperf_client_for_multimodal.html">Aiperf Client For Multimodal</a></li>
|
||
<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/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 & 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-on-trtllm.html">Deployment Guide for Qwen3 on TensorRT LLM - Blackwell & 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 & 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="current nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="supported-models.html">Supported Models</a></li>
|
||
|
||
<li class="toctree-l1 current active"><a class="current reference internal" href="#">Adding a New Model</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">CLI Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-bench.html">trtllm-bench</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-eval.html">trtllm-eval</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../commands/trtllm-serve/index.html">trtllm-serve</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../commands/trtllm-serve/trtllm-serve.html">trtllm-serve</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../commands/trtllm-serve/run-benchmark-with-trtllm-serve.html">Run benchmarking with <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code></a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">API Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../llm-api/index.html">LLM API Introduction</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../llm-api/reference.html">API Reference</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Features</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/feature-combination-matrix.html">Feature Combination Matrix</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/disagg-serving.html">Disaggregated Serving</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/kvcache.html">KV Cache System</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/long-sequence.html">Long Sequences</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/lora.html">LoRA (Low-Rank Adaptation)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/multi-modality.html">Multimodal Support in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/overlap-scheduler.html">Overlap Scheduler</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/paged-attention-ifb-scheduler.html">Paged Attention, IFB, and Request Scheduling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/parallel-strategy.html">Parallelism in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/quantization.html">Quantization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/sampling.html">Sampling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/additional-outputs.html">Additional Outputs</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/guided-decoding.html">Guided Decoding</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/speculative-decoding.html">Speculative Decoding</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/checkpoint-loading.html">Checkpoint Loading</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/auto_deploy/auto-deploy.html">AutoDeploy (Beta)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/ray-orchestrator.html">Ray Orchestrator (Prototype)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/torch_compile_and_piecewise_cuda_graph.html">Torch Compile & Piecewise CUDA Graph</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/helix.html">Helix Parallelism</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/kv-cache-connector.html">KV Cache Connector</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Developer Guide</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/overview.html">Architecture Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/perf-analysis.html">Performance Analysis</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/perf-benchmarking.html">TensorRT LLM Benchmarking</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/ci-overview.html">Continuous Integration Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/dev-containers.html">Using Dev Containers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/api-change.html">LLM API Change Guide</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../developer-guide/kv-transfer.html">Introduction to KV Cache Transmission</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog10_ADP_Balance_Strategy.html">ADP Balance Strategy</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog11_GPT_OSS_Eagle3.html">Running GPT-OSS-120B with Eagle3 Speculative Decoding on GB200/B200 (TensorRT LLM)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.html">Combining Guided Decoding and Speculative Decoding: Making CPU and GPU Cooperate Seamlessly</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog13_Inference_Time_Compute_Implementation_in_TensorRT-LLM.html">Inference Time Compute Implementation in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog14_Scaling_Expert_Parallelism_in_TensorRT-LLM_part3.html">Scaling Expert Parallelism in TensorRT LLM (Part 3: Pushing the Performance Boundary)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html">Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html">DeepSeek R1 MTP Implementation and Optimization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html">Optimizing DeepSeek R1 Throughput on NVIDIA Blackwell GPUs: A Deep Dive for Developers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html">Scaling Expert Parallelism in TensorRT LLM (Part 1: Design and Implementation of Large-scale EP)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html">Disaggregated Serving in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html">How to launch Llama4 Maverick + Eagle3 TensorRT LLM server</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html">N-Gram Speculative Decoding in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html">Scaling Expert Parallelism in TensorRT LLM (Part 2: Performance Status and Optimization)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html">Running a High Performance GPT-OSS-120B Inference Server with TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.html">How to get best performance on DeepSeek-R1 in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../blogs/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Quick Links</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/releases">Releases</a></li>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM">Github Code</a></li>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/issues?q=is%3Aissue%20state%3Aopen%20label%3Aroadmap">Roadmap</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Use TensorRT Engine</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../legacy/tensorrt_quickstart.html">LLM API with TensorRT Engine</a></li>
|
||
</ul>
|
||
</div>
|
||
</nav></div>
|
||
</div>
|
||
|
||
|
||
<div class="sidebar-primary-items__end sidebar-primary__section">
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
<main id="main-content" class="bd-main" role="main">
|
||
|
||
|
||
<div class="bd-content">
|
||
<div class="bd-article-container">
|
||
|
||
<div class="bd-header-article d-print-none">
|
||
<div class="header-article-items header-article__inner">
|
||
|
||
<div class="header-article-items__start">
|
||
|
||
<div class="header-article-item">
|
||
|
||
<nav aria-label="Breadcrumb" class="d-print-none">
|
||
<ul class="bd-breadcrumbs">
|
||
|
||
<li class="breadcrumb-item breadcrumb-home">
|
||
<a href="../index.html" class="nav-link" aria-label="Home">
|
||
<i class="fa-solid fa-home"></i>
|
||
</a>
|
||
</li>
|
||
<li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">Adding a New Model</span></li>
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<div id="searchbox"></div>
|
||
<article class="bd-article">
|
||
|
||
<section class="tex2jax_ignore mathjax_ignore" id="adding-a-new-model">
|
||
<h1>Adding a New Model<a class="headerlink" href="#adding-a-new-model" title="Link to this heading">#</a></h1>
|
||
<section id="table-of-contents">
|
||
<h2>Table of Contents<a class="headerlink" href="#table-of-contents" title="Link to this heading">#</a></h2>
|
||
<ol class="arabic simple">
|
||
<li><p><a class="reference internal" href="#introduction">Introduction</a></p></li>
|
||
<li><p><a class="reference internal" href="#prerequisites">Prerequisites</a></p></li>
|
||
<li><p><a class="reference internal" href="#step-by-step-guide">Step-by-Step Guide</a></p>
|
||
<ol class="arabic simple">
|
||
<li><p><a class="reference internal" href="#model-configuration">Model Configuration</a></p></li>
|
||
<li><p><a class="reference internal" href="#model-definition">Model Definition</a></p></li>
|
||
<li><p><a class="reference internal" href="#weight-loading">Weight Loading</a></p></li>
|
||
<li><p><a class="reference internal" href="#model-registration">Model Registration</a></p>
|
||
<ol class="arabic simple">
|
||
<li><p><a class="reference internal" href="#core-models">Core Models</a></p></li>
|
||
<li><p><a class="reference internal" href="#out-of-tree-models">Out-of-Tree Models</a></p></li>
|
||
</ol>
|
||
</li>
|
||
</ol>
|
||
</li>
|
||
</ol>
|
||
</section>
|
||
<section id="introduction">
|
||
<h2>Introduction<a class="headerlink" href="#introduction" title="Link to this heading">#</a></h2>
|
||
<p>This guide provides a step-by-step process for adding a new model in PyTorch Backend.</p>
|
||
</section>
|
||
<section id="prerequisites">
|
||
<h2>Prerequisites<a class="headerlink" href="#prerequisites" title="Link to this heading">#</a></h2>
|
||
<p>Before you begin, ensure you have the following:</p>
|
||
<ul class="simple">
|
||
<li><p>A working installation of TensorRT-LLM. Follow these <a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/blob/main/docs/source/installation/build-from-source-linux.md">instructions</a>.</p></li>
|
||
</ul>
|
||
</section>
|
||
<section id="step-by-step-guide">
|
||
<h2>Step-by-Step Guide<a class="headerlink" href="#step-by-step-guide" title="Link to this heading">#</a></h2>
|
||
<section id="model-configuration">
|
||
<h3>Model Configuration<a class="headerlink" href="#model-configuration" title="Link to this heading">#</a></h3>
|
||
<p>Suppose you want to support a new model named <code class="docutils literal notranslate"><span class="pre">MyModel</span></code>. If the model is already supported in HuggingFace’s transformers, you should bring the PyTorch modeling code and reuse HuggingFace’s configuration class. For example, our <code class="docutils literal notranslate"><span class="pre">tensorrt_llm/_torch/models/modeling_llama.py</span></code> was adapted from HuggingFace’s <a class="reference external" href="https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/modeling_llama.py">modeling_llama.py</a>; in the modeling code, we reuse the configuration class:</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">transformers</span><span class="w"> </span><span class="kn">import</span> <span class="n">LlamaConfig</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>If the model is not registered in HuggingFace’s transformers, you need to define the configuration class in your <code class="docutils literal notranslate"><span class="pre">configuration_mymodel.py</span></code> following HuggingFace’s <a class="reference external" href="https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/configuration_llama.py">configuration_llama.py</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">transformers.configuration_utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">PretrainedConfig</span>
|
||
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">MyConfig</span><span class="p">(</span><span class="n">PretrainedConfig</span><span class="p">):</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">...</span><span class="p">):</span>
|
||
<span class="o">...</span>
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
<section id="model-definition">
|
||
<h3>Model Definition<a class="headerlink" href="#model-definition" title="Link to this heading">#</a></h3>
|
||
<p>Remove any unnecessary code (e.g., training-specific code), and then rewrite some PyTorch modules. For a typical Transformer decoder model, you need to implement your <code class="docutils literal notranslate"><span class="pre">modeling_mymodel.py</span></code> like this:</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Optional</span>
|
||
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">torch</span><span class="w"> </span><span class="kn">import</span> <span class="n">nn</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm._torch.attention_backend</span><span class="w"> </span><span class="kn">import</span> <span class="n">AttentionMetadata</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm._torch.model_config</span><span class="w"> </span><span class="kn">import</span> <span class="n">ModelConfig</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm._torch.models.modeling_utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">DecoderModel</span><span class="p">,</span> <span class="n">DecoderModelForCausalLM</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm._torch.modules.attention</span><span class="w"> </span><span class="kn">import</span> <span class="n">Attention</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm._torch.modules.decoder_layer</span><span class="w"> </span><span class="kn">import</span> <span class="n">DecoderLayer</span>
|
||
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">configuration_mymodel</span><span class="w"> </span><span class="kn">import</span> <span class="n">MyConfig</span>
|
||
|
||
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">MyAttention</span><span class="p">(</span><span class="n">Attention</span><span class="p">):</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">model_config</span><span class="p">:</span> <span class="n">ModelConfig</span><span class="p">[</span><span class="n">MyConfig</span><span class="p">],</span> <span class="n">layer_idx</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
|
||
<span class="c1"># Use model_config to initialize the Attention module</span>
|
||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">...</span><span class="p">)</span>
|
||
|
||
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">MyDecoderLayer</span><span class="p">(</span><span class="n">DecoderLayer</span><span class="p">):</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">model_config</span><span class="p">:</span> <span class="n">ModelConfig</span><span class="p">[</span><span class="n">MyConfig</span><span class="p">],</span> <span class="n">layer_idx</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
|
||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
||
<span class="c1"># Use model_config to initialize the submodules</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">input_layernorm</span> <span class="o">=</span> <span class="o">...</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">self_attn</span> <span class="o">=</span> <span class="n">MyAttention</span><span class="p">(</span><span class="n">model_config</span><span class="p">,</span> <span class="n">layer_idx</span><span class="p">)</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">post_attention_layernorm</span> <span class="o">=</span> <span class="o">...</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">mlp</span> <span class="o">=</span> <span class="o">...</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hidden_states</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">attn_metadata</span><span class="p">:</span> <span class="n">AttentionMetadata</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
||
<span class="c1"># Define the forward computation of a single decoder layer</span>
|
||
<span class="o">...</span>
|
||
|
||
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">MyModel</span><span class="p">(</span><span class="n">DecoderModel</span><span class="p">):</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">model_config</span><span class="p">:</span> <span class="n">ModelConfig</span><span class="p">[</span><span class="n">MyConfig</span><span class="p">]):</span>
|
||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">model_config</span><span class="p">)</span>
|
||
<span class="c1"># Use model_config to initialize the submodules</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">embed_tokens</span> <span class="o">=</span> <span class="o">...</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">layers</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">([</span>
|
||
<span class="n">MyDecoderLayer</span><span class="p">(</span><span class="n">model_config</span><span class="p">,</span> <span class="n">layer_idx</span><span class="p">)</span> <span class="k">for</span> <span class="n">layer_idx</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">model_config</span><span class="o">.</span><span class="n">pretrained_config</span><span class="o">.</span><span class="n">num_hidden_layers</span><span class="p">)</span>
|
||
<span class="p">])</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
|
||
<span class="n">attn_metadata</span><span class="p">:</span> <span class="n">AttentionMetadata</span><span class="p">,</span>
|
||
<span class="n">input_ids</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">torch</span><span class="o">.</span><span class="n">IntTensor</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">position_ids</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">torch</span><span class="o">.</span><span class="n">IntTensor</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">inputs_embeds</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">torch</span><span class="o">.</span><span class="n">FloatTensor</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
|
||
<span class="c1"># Define the forward computation of the model</span>
|
||
<span class="o">...</span>
|
||
|
||
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">MyModelForCausalLM</span><span class="p">(</span><span class="n">DecoderModelForCausalLM</span><span class="p">[</span><span class="n">MyModel</span><span class="p">,</span> <span class="n">MyConfig</span><span class="p">]):</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">model_config</span><span class="p">:</span> <span class="n">ModelConfig</span><span class="p">[</span><span class="n">MyConfig</span><span class="p">]):</span>
|
||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">MyModel</span><span class="p">(</span><span class="n">model_config</span><span class="p">),</span>
|
||
<span class="n">config</span><span class="o">=</span><span class="n">model_config</span><span class="p">,</span>
|
||
<span class="n">hidden_size</span><span class="o">=</span><span class="n">model_config</span><span class="o">.</span><span class="n">pretrained_config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
|
||
<span class="n">vocab_size</span><span class="o">=</span><span class="n">model_config</span><span class="o">.</span><span class="n">pretrained_config</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>Note that <code class="docutils literal notranslate"><span class="pre">MyAttention</span></code> inherits from our <code class="docutils literal notranslate"><span class="pre">Attention</span></code> module (in <code class="docutils literal notranslate"><span class="pre">tensorrt_llm/_torch/modules/attention.py</span></code>), so that the attention computation is compatible with our PyTorch runtime. Related to this, module inputs should also be adapted:</p>
|
||
<ul class="simple">
|
||
<li><p>The <code class="docutils literal notranslate"><span class="pre">attn_metadata</span></code> stores the metadata from the batched input and KV cache for the attention backend. It is created by and passed from the runtime, and model developers need to ensure that <code class="docutils literal notranslate"><span class="pre">attn_metadata</span></code> is correctly passed to the attention module.</p></li>
|
||
<li><p>The input tensors (i.e., <code class="docutils literal notranslate"><span class="pre">input_ids</span></code>, <code class="docutils literal notranslate"><span class="pre">position_ids</span></code>, <code class="docutils literal notranslate"><span class="pre">hidden_states</span></code>) are in the packed mode. The first dimension corresponds to the number of tokens in a batch.</p></li>
|
||
</ul>
|
||
<p>Additionally, <code class="docutils literal notranslate"><span class="pre">MyDecoderLayer</span></code>, <code class="docutils literal notranslate"><span class="pre">MyModel</span></code>, and <code class="docutils literal notranslate"><span class="pre">MyModelForCausalLM</span></code> are subclasses of <code class="docutils literal notranslate"><span class="pre">DecoderLayer</span></code>, <code class="docutils literal notranslate"><span class="pre">DecoderModel</span></code>, and <code class="docutils literal notranslate"><span class="pre">DecoderModelForCausalLM</span></code> respectively. The base classes define interfaces and provide a generic scaffolding to define model layers, load weights, etc.</p>
|
||
<p>Optionally, you may replace the native PyTorch modules with our implementations to enable features or achieve higher performance:</p>
|
||
<ul class="simple">
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">Linear</span></code> (in <code class="docutils literal notranslate"><span class="pre">tensorrt_llm/_torch/modules/linear.py</span></code>): Enables tensor parallelism and quantization.</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">Embedding</span></code> (in <code class="docutils literal notranslate"><span class="pre">tensorrt_llm/_torch/modules/embedding.py</span></code>): Enables tensor parallelism for embedding.</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">RotaryEmbedding</span></code> (in <code class="docutils literal notranslate"><span class="pre">tensorrt_llm/_torch/modules/rotary_embedding.py</span></code>): Enables performant rotary embedding.</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">RMSNorm</span></code> (in <code class="docutils literal notranslate"><span class="pre">tensorrt_llm/_torch/modules/rms_norm.py</span></code>): Enables performant RMS norm.</p></li>
|
||
</ul>
|
||
<p>For a concrete reference, check out <code class="docutils literal notranslate"><span class="pre">tensorrt_llm/_torch/models/modeling_llama.py</span></code>.</p>
|
||
</section>
|
||
<section id="weight-loading">
|
||
<h3>Weight Loading<a class="headerlink" href="#weight-loading" title="Link to this heading">#</a></h3>
|
||
<p>The base class <code class="docutils literal notranslate"><span class="pre">DecoderModelForCausalLM</span></code> provides a <code class="docutils literal notranslate"><span class="pre">load_weights</span></code> method that loads the weights from the checkpoint file and assigns them to the corresponding layers in the model. However, if the default method does not work for <code class="docutils literal notranslate"><span class="pre">MyModelForCausalLM</span></code>, you need to implement your own <code class="docutils literal notranslate"><span class="pre">load_weights</span></code>:</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">class</span><span class="w"> </span><span class="nc">MyModelForCausalLM</span><span class="p">(</span><span class="n">DecoderModelForCausalLM</span><span class="p">[</span><span class="n">MyModel</span><span class="p">,</span> <span class="n">MyConfig</span><span class="p">]):</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">load_weights</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">weights</span><span class="p">:</span> <span class="nb">dict</span><span class="p">):</span>
|
||
<span class="c1"># Define the weight loading logic</span>
|
||
<span class="o">...</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>For example, Huggingface’s LLaMA model uses three linear layers for Q/K/V projections, resulting in three weight tensors in the checkpoint:</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">weights</span>
|
||
<span class="go">{</span>
|
||
<span class="go"> ...,</span>
|
||
<span class="go"> "model.layers.0.self_attn.q_proj.weight": torch.Tensor([hidden_size, hidden_size]),</span>
|
||
<span class="go"> "model.layers.0.self_attn.k_proj.weight": torch.Tensor([hidden_size, hidden_size]),</span>
|
||
<span class="go"> "model.layers.0.self_attn.v_proj.weight": torch.Tensor([hidden_size, hidden_size]),</span>
|
||
<span class="go"> ...,</span>
|
||
<span class="go">}</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>However, our LLaMA model fuses the three layers into one linear layer:</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">llama</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">layers</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">self_attn</span><span class="o">.</span><span class="n">qkv_proj</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">data</span>
|
||
<span class="go">torch.Tensor([hidden_size * 3, hidden_size])</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>Hence, <code class="docutils literal notranslate"><span class="pre">load_weights</span></code> needs to collect the three weight tensors from the original checkpoint, concatenate them, and assign them to the fused linear layer. Considering tensor parallelism and quantization, the process would be more complicated. We recommend calling the predefined module-level <code class="docutils literal notranslate"><span class="pre">load_weights</span></code> (e.g., <code class="docutils literal notranslate"><span class="pre">Linear</span></code> and <code class="docutils literal notranslate"><span class="pre">Embedding</span></code>) when implementing your model-level <code class="docutils literal notranslate"><span class="pre">load_weights</span></code> method.</p>
|
||
<p>Overall, <code class="docutils literal notranslate"><span class="pre">load_weights</span></code> should handle any discrepancy between <code class="docutils literal notranslate"><span class="pre">MyModelForCausalLM</span></code> and the weights loaded from the checkpoint, so that <code class="docutils literal notranslate"><span class="pre">MyModelForCausalLM</span></code> can perform forward computation equivalent to the original model.</p>
|
||
</section>
|
||
<section id="model-registration">
|
||
<h3>Model Registration<a class="headerlink" href="#model-registration" title="Link to this heading">#</a></h3>
|
||
<p>The new model needs to be registered so that it can be recognized by the PyTorch runtime. The registration can be done simply by adding the <code class="docutils literal notranslate"><span class="pre">register_auto_model</span></code> decorator for <code class="docutils literal notranslate"><span class="pre">MyModelForCausalLM</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._torch.models.modeling_utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">register_auto_model</span>
|
||
|
||
<span class="nd">@register_auto_model</span><span class="p">(</span><span class="s2">"MyModelForCausalLM"</span><span class="p">)</span>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">MyModelForCausalLM</span><span class="p">(</span><span class="n">DecoderModelForCausalLM</span><span class="p">[</span><span class="n">MyModel</span><span class="p">,</span> <span class="n">MyConfig</span><span class="p">]):</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">model_config</span><span class="p">:</span> <span class="n">ModelConfig</span><span class="p">[</span><span class="n">MyConfig</span><span class="p">]):</span>
|
||
<span class="o">...</span>
|
||
</pre></div>
|
||
</div>
|
||
<section id="core-models">
|
||
<h4>Core Models<a class="headerlink" href="#core-models" title="Link to this heading">#</a></h4>
|
||
<p>To add the new model to core models, <code class="docutils literal notranslate"><span class="pre">modeling_mymodel.py</span></code> (and potentially <code class="docutils literal notranslate"><span class="pre">configuration_mymodel.py</span></code>) should be placed in <code class="docutils literal notranslate"><span class="pre">tensorrt_llm/_torch/models</span></code>. Then, you need to import the modeling code in <code class="docutils literal notranslate"><span class="pre">tensorrt_llm/_torch/models/__init__.py</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">.modeling_mymodel</span><span class="w"> </span><span class="kn">import</span> <span class="n">MyModelForCausalLM</span>
|
||
|
||
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span>
|
||
<span class="o">...</span><span class="p">,</span>
|
||
<span class="s2">"MyModelForCausalLM"</span><span class="p">,</span>
|
||
<span class="p">]</span>
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
<section id="out-of-tree-models">
|
||
<h4>Out-of-Tree Models<a class="headerlink" href="#out-of-tree-models" title="Link to this heading">#</a></h4>
|
||
<p>Alternatively, you can register the new model as an out-of-tree model, so that you can use the new model without touching the TensorRT LLM codebase. To do so, place <code class="docutils literal notranslate"><span class="pre">modeling_mymodel.py</span></code> (and potentially <code class="docutils literal notranslate"><span class="pre">configuration_mymodel.py</span></code>) in your working directory, and import the modeling code in your script:</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">import</span><span class="w"> </span><span class="nn">modeling_mymodel</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">main</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="o">...</span><span class="p">)</span>
|
||
|
||
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
|
||
<span class="n">main</span><span class="p">()</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>We provide an out-of-tree modeling example in <code class="docutils literal notranslate"><span class="pre">examples/pytorch/out_of_tree_example</span></code>. The model is implemented in <code class="docutils literal notranslate"><span class="pre">modeling_opt.py</span></code> and you can run the example by:</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>python<span class="w"> </span>examples/pytorch/out_of_tree_example/main.py
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
</section>
|
||
</section>
|
||
</section>
|
||
|
||
|
||
</article>
|
||
|
||
|
||
|
||
|
||
|
||
<footer class="prev-next-footer d-print-none">
|
||
|
||
<div class="prev-next-area">
|
||
<a class="left-prev"
|
||
href="supported-models.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">Supported Models</p>
|
||
</div>
|
||
</a>
|
||
<a class="right-next"
|
||
href="../commands/trtllm-bench.html"
|
||
title="next page">
|
||
<div class="prev-next-info">
|
||
<p class="prev-next-subtitle">next</p>
|
||
<p class="prev-next-title">trtllm-bench</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="#table-of-contents">Table of Contents</a></li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#introduction">Introduction</a></li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#prerequisites">Prerequisites</a></li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#step-by-step-guide">Step-by-Step Guide</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#model-configuration">Model Configuration</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#model-definition">Model Definition</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#weight-loading">Weight Loading</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#model-registration">Model Registration</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#core-models">Core Models</a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#out-of-tree-models">Out-of-Tree Models</a></li>
|
||
</ul>
|
||
</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 January 04, 2026.</p>
|
||
|
||
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/a65b0d4">a65b0d4</a>.</p>
|
||
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
</footer>
|
||
</body>
|
||
</html> |