TensorRT-LLMs/features/lora.html
2025-10-22 01:55:45 +00:00

932 lines
54 KiB
HTML
Raw Blame History

This file contains invisible Unicode characters

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

<!DOCTYPE html>
<html lang="en" data-content_root="../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>LoRA (Low-Rank Adaptation) &#8212; TensorRT LLM</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!--
this give us a css class that will be invisible only if js is disabled
-->
<noscript>
<style>
.pst-js-only { display: none !important; }
</style>
</noscript>
<!-- Loaded before other Sphinx assets -->
<link href="../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link href="../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../_static/styles/nvidia-sphinx-theme.css?v=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 = 'features/lora';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.2.0rc1';
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="Multimodal Support in TensorRT LLM" href="multi-modality.html" />
<link rel="prev" title="Long Sequences" href="long-sequence.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="1.2.0rc1" />
</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/quick-start-recipe-for-deepseek-r1-on-trtllm.html">Quick Start Recipe for DeepSeek R1 on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/quick-start-recipe-for-llama3.3-70b-on-trtllm.html">Quick Start Recipe for Llama3.3 70B on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/quick-start-recipe-for-llama4-scout-on-trtllm.html">Quick Start Recipe for Llama4 Scout 17B on TensorRT LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.html">Quick Start Recipe for GPT-OSS on TensorRT-LLM - Blackwell Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/quick-start-recipe-for-qwen3-next-on-trtllm.html">Quick Start Recipe for Qwen3 Next on TensorRT LLM - Blackwell &amp; 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="current nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="feature-combination-matrix.html">Feature Combination Matrix</a></li>
<li class="toctree-l1"><a class="reference internal" href="attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
<li class="toctree-l1"><a class="reference internal" href="disagg-serving.html">Disaggregated Serving (Beta)</a></li>
<li class="toctree-l1"><a class="reference internal" href="kvcache.html">KV Cache System</a></li>
<li class="toctree-l1"><a class="reference internal" href="long-sequence.html">Long Sequences</a></li>
<li class="toctree-l1 current active"><a class="current reference internal" href="#">LoRA (Low-Rank Adaptation)</a></li>
<li class="toctree-l1"><a class="reference internal" href="multi-modality.html">Multimodal Support in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="overlap-scheduler.html">Overlap Scheduler</a></li>
<li class="toctree-l1"><a class="reference internal" href="paged-attention-ifb-scheduler.html">Paged Attention, IFB, and Request Scheduling</a></li>
<li class="toctree-l1"><a class="reference internal" href="parallel-strategy.html">Parallelism in TensorRT LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="quantization.html">Quantization</a></li>
<li class="toctree-l1"><a class="reference internal" href="sampling.html">Sampling</a></li>
<li class="toctree-l1"><a class="reference internal" href="speculative-decoding.html">Speculative Decoding</a></li>
<li class="toctree-l1"><a class="reference internal" href="checkpoint-loading.html">Checkpoint Loading</a></li>
<li class="toctree-l1"><a class="reference internal" href="auto_deploy/auto-deploy.html">AutoDeploy (Prototype)</a></li>
<li class="toctree-l1"><a class="reference internal" href="ray-orchestrator.html">Ray Orchestrator (Prototype)</a></li>
</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>
</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-GramSpeculativeDecodingin 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">LoRA (Low-Rank Adaptation)</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section class="tex2jax_ignore mathjax_ignore" id="lora-low-rank-adaptation">
<h1>LoRA (Low-Rank Adaptation)<a class="headerlink" href="#lora-low-rank-adaptation" title="Link to this heading">#</a></h1>
<p>LoRA (Low-Rank Adaptation) is a parameter-efficient fine-tuning technique that enables adapting large language models to specific tasks without modifying the original model weights. Instead of fine-tuning all parameters, LoRA introduces small trainable rank decomposition matrices that are added to existing weights during inference.</p>
<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="#background">Background</a></p></li>
<li><p><a class="reference internal" href="#basic-usage">Basic Usage</a></p>
<ul class="simple">
<li><p><a class="reference internal" href="#single-lora-adapter">Single LoRA Adapter</a></p></li>
<li><p><a class="reference internal" href="#multi-lora-support">Multi-LoRA Support</a></p></li>
</ul>
</li>
<li><p><a class="reference internal" href="#advanced-usage">Advanced Usage</a></p>
<ul class="simple">
<li><p><a class="reference internal" href="#lora-with-quantization">LoRA with Quantization</a></p></li>
<li><p><a class="reference internal" href="#nemo-lora-format">NeMo LoRA Format</a></p></li>
<li><p><a class="reference internal" href="#cache-management">Cache Management</a></p></li>
</ul>
</li>
<li><p><a class="reference internal" href="#trtllm-serve-with-lora">TRTLLM serve with LoRA</a></p>
<ul class="simple">
<li><p><a class="reference internal" href="#yaml-configuration">YAML Configuration</a></p></li>
<li><p><a class="reference internal" href="#starting-the-server">Starting the Server</a></p></li>
<li><p><a class="reference internal" href="#client-usage">Client Usage</a></p></li>
</ul>
</li>
<li><p><a class="reference internal" href="#trtllm-bench-with-lora">TRTLLM bench with LORA</a></p>
<ul class="simple">
<li><p><a class="reference internal" href="#yaml-configuration">YAML Configuration</a></p></li>
<li><p><a class="reference internal" href="#run-trtllm-bench">Run trtllm-bench</a></p></li>
</ul>
</li>
</ol>
</section>
<section id="background">
<h2>Background<a class="headerlink" href="#background" title="Link to this heading">#</a></h2>
<p>The PyTorch backend provides LoRA support, allowing you to:</p>
<ul class="simple">
<li><p>Load and apply multiple LoRA adapters simultaneously</p></li>
<li><p>Switch between different adapters for different requests</p></li>
<li><p>Use LoRA with quantized models</p></li>
<li><p>Support both HuggingFace and NeMo LoRA formats</p></li>
</ul>
</section>
<section id="basic-usage">
<h2>Basic Usage<a class="headerlink" href="#basic-usage" title="Link to this heading">#</a></h2>
<section id="single-lora-adapter">
<h3>Single LoRA Adapter<a class="headerlink" href="#single-lora-adapter" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm</span><span class="w"> </span><span class="kn">import</span> <span class="n">LLM</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.lora_manager</span><span class="w"> </span><span class="kn">import</span> <span class="n">LoraConfig</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.executor.request</span><span class="w"> </span><span class="kn">import</span> <span class="n">LoRARequest</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.sampling_params</span><span class="w"> </span><span class="kn">import</span> <span class="n">SamplingParams</span>
<span class="c1"># Configure LoRA</span>
<span class="n">lora_config</span> <span class="o">=</span> <span class="n">LoraConfig</span><span class="p">(</span>
<span class="n">lora_dir</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;/path/to/lora/adapter&quot;</span><span class="p">],</span>
<span class="n">max_lora_rank</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span>
<span class="n">max_loras</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">max_cpu_loras</span><span class="o">=</span><span class="mi">1</span>
<span class="p">)</span>
<span class="c1"># Initialize LLM with LoRA support</span>
<span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span>
<span class="n">model</span><span class="o">=</span><span class="s2">&quot;/path/to/base/model&quot;</span><span class="p">,</span>
<span class="n">lora_config</span><span class="o">=</span><span class="n">lora_config</span>
<span class="p">)</span>
<span class="c1"># Create LoRA request</span>
<span class="n">lora_request</span> <span class="o">=</span> <span class="n">LoRARequest</span><span class="p">(</span><span class="s2">&quot;my-lora-task&quot;</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;/path/to/lora/adapter&quot;</span><span class="p">)</span>
<span class="c1"># Generate with LoRA</span>
<span class="n">prompts</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;Hello, how are you?&quot;</span><span class="p">]</span>
<span class="n">sampling_params</span> <span class="o">=</span> <span class="n">SamplingParams</span><span class="p">(</span><span class="n">max_tokens</span><span class="o">=</span><span class="mi">50</span><span class="p">)</span>
<span class="n">outputs</span> <span class="o">=</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate</span><span class="p">(</span>
<span class="n">prompts</span><span class="p">,</span>
<span class="n">sampling_params</span><span class="p">,</span>
<span class="n">lora_request</span><span class="o">=</span><span class="p">[</span><span class="n">lora_request</span><span class="p">]</span>
<span class="p">)</span>
</pre></div>
</div>
</section>
<section id="multi-lora-support">
<h3>Multi-LoRA Support<a class="headerlink" href="#multi-lora-support" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># Configure for multiple LoRA adapters</span>
<span class="n">lora_config</span> <span class="o">=</span> <span class="n">LoraConfig</span><span class="p">(</span>
<span class="n">lora_target_modules</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;attn_q&#39;</span><span class="p">,</span> <span class="s1">&#39;attn_k&#39;</span><span class="p">,</span> <span class="s1">&#39;attn_v&#39;</span><span class="p">],</span>
<span class="n">max_lora_rank</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span>
<span class="n">max_loras</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span>
<span class="n">max_cpu_loras</span><span class="o">=</span><span class="mi">8</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="n">model</span><span class="o">=</span><span class="s2">&quot;/path/to/base/model&quot;</span><span class="p">,</span> <span class="n">lora_config</span><span class="o">=</span><span class="n">lora_config</span><span class="p">)</span>
<span class="c1"># Create multiple LoRA requests</span>
<span class="n">lora_req1</span> <span class="o">=</span> <span class="n">LoRARequest</span><span class="p">(</span><span class="s2">&quot;task-1&quot;</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;/path/to/adapter1&quot;</span><span class="p">)</span>
<span class="n">lora_req2</span> <span class="o">=</span> <span class="n">LoRARequest</span><span class="p">(</span><span class="s2">&quot;task-2&quot;</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">&quot;/path/to/adapter2&quot;</span><span class="p">)</span>
<span class="n">prompts</span> <span class="o">=</span> <span class="p">[</span>
<span class="s2">&quot;Translate to French: Hello world&quot;</span><span class="p">,</span>
<span class="s2">&quot;Summarize: This is a long document...&quot;</span>
<span class="p">]</span>
<span class="c1"># Apply different LoRAs to different prompts</span>
<span class="n">outputs</span> <span class="o">=</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate</span><span class="p">(</span>
<span class="n">prompts</span><span class="p">,</span>
<span class="n">sampling_params</span><span class="p">,</span>
<span class="n">lora_request</span><span class="o">=</span><span class="p">[</span><span class="n">lora_req1</span><span class="p">,</span> <span class="n">lora_req2</span><span class="p">]</span>
<span class="p">)</span>
</pre></div>
</div>
</section>
</section>
<section id="advanced-usage">
<h2>Advanced Usage<a class="headerlink" href="#advanced-usage" title="Link to this heading">#</a></h2>
<section id="lora-with-quantization">
<h3>LoRA with Quantization<a class="headerlink" href="#lora-with-quantization" title="Link to this heading">#</a></h3>
<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.models.modeling_utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">QuantConfig</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.quantization.mode</span><span class="w"> </span><span class="kn">import</span> <span class="n">QuantAlgo</span>
<span class="c1"># Configure quantization</span>
<span class="n">quant_config</span> <span class="o">=</span> <span class="n">QuantConfig</span><span class="p">(</span>
<span class="n">quant_algo</span><span class="o">=</span><span class="n">QuantAlgo</span><span class="o">.</span><span class="n">FP8</span><span class="p">,</span>
<span class="n">kv_cache_quant_algo</span><span class="o">=</span><span class="n">QuantAlgo</span><span class="o">.</span><span class="n">FP8</span>
<span class="p">)</span>
<span class="c1"># LoRA works with quantized models</span>
<span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span>
<span class="n">model</span><span class="o">=</span><span class="s2">&quot;/path/to/model&quot;</span><span class="p">,</span>
<span class="n">quant_config</span><span class="o">=</span><span class="n">quant_config</span><span class="p">,</span>
<span class="n">lora_config</span><span class="o">=</span><span class="n">lora_config</span>
<span class="p">)</span>
</pre></div>
</div>
</section>
<section id="nemo-lora-format">
<h3>NeMo LoRA Format<a class="headerlink" href="#nemo-lora-format" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># For NeMo-format LoRA checkpoints</span>
<span class="n">lora_config</span> <span class="o">=</span> <span class="n">LoraConfig</span><span class="p">(</span>
<span class="n">lora_dir</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;/path/to/nemo/lora&quot;</span><span class="p">],</span>
<span class="n">lora_ckpt_source</span><span class="o">=</span><span class="s2">&quot;nemo&quot;</span><span class="p">,</span>
<span class="n">max_lora_rank</span><span class="o">=</span><span class="mi">8</span>
<span class="p">)</span>
<span class="n">lora_request</span> <span class="o">=</span> <span class="n">LoRARequest</span><span class="p">(</span>
<span class="s2">&quot;nemo-task&quot;</span><span class="p">,</span>
<span class="mi">0</span><span class="p">,</span>
<span class="s2">&quot;/path/to/nemo/lora&quot;</span><span class="p">,</span>
<span class="n">lora_ckpt_source</span><span class="o">=</span><span class="s2">&quot;nemo&quot;</span>
<span class="p">)</span>
</pre></div>
</div>
</section>
<section id="cache-management">
<h3>Cache Management<a class="headerlink" href="#cache-management" title="Link to this heading">#</a></h3>
<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.llmapi.llm_args</span><span class="w"> </span><span class="kn">import</span> <span class="n">PeftCacheConfig</span>
<span class="c1"># Fine-tune cache sizes</span>
<span class="n">peft_cache_config</span> <span class="o">=</span> <span class="n">PeftCacheConfig</span><span class="p">(</span>
<span class="n">host_cache_size</span><span class="o">=</span><span class="mi">1024</span><span class="o">*</span><span class="mi">1024</span><span class="o">*</span><span class="mi">1024</span><span class="p">,</span> <span class="c1"># 1GB CPU cache</span>
<span class="n">device_cache_percent</span><span class="o">=</span><span class="mf">0.1</span> <span class="c1"># 10% of free GPU memory</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="n">model</span><span class="o">=</span><span class="s2">&quot;/path/to/model&quot;</span><span class="p">,</span>
<span class="n">lora_config</span><span class="o">=</span><span class="n">lora_config</span><span class="p">,</span>
<span class="n">peft_cache_config</span><span class="o">=</span><span class="n">peft_cache_config</span>
<span class="p">)</span>
</pre></div>
</div>
</section>
</section>
<section id="trtllm-serve-with-lora">
<h2>TRTLLM serve with LoRA<a class="headerlink" href="#trtllm-serve-with-lora" title="Link to this heading">#</a></h2>
<section id="yaml-configuration">
<h3>YAML Configuration<a class="headerlink" href="#yaml-configuration" title="Link to this heading">#</a></h3>
<p>Create an <code class="docutils literal notranslate"><span class="pre">extra_llm_api_options.yaml</span></code> file:</p>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><span class="nt">lora_config</span><span class="p">:</span>
<span class="w"> </span><span class="nt">lora_target_modules</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="s">&#39;attn_q&#39;</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">&#39;attn_k&#39;</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">&#39;attn_v&#39;</span><span class="p p-Indicator">]</span>
<span class="w"> </span><span class="nt">max_lora_rank</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8</span>
</pre></div>
</div>
</section>
<section id="starting-the-server">
<h3>Starting the Server<a class="headerlink" href="#starting-the-server" title="Link to this heading">#</a></h3>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>python<span class="w"> </span>-m<span class="w"> </span>tensorrt_llm.commands.serve
<span class="w"> </span>/path/to/model<span class="w"> </span><span class="se">\</span>
<span class="w"> </span>--extra_llm_api_options<span class="w"> </span>extra_llm_api_options.yaml
</pre></div>
</div>
</section>
<section id="client-usage">
<h3>Client Usage<a class="headerlink" href="#client-usage" title="Link to this heading">#</a></h3>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">openai</span>
<span class="n">client</span> <span class="o">=</span> <span class="n">openai</span><span class="o">.</span><span class="n">OpenAI</span><span class="p">(</span><span class="n">base_url</span><span class="o">=</span><span class="s2">&quot;http://localhost:8000/v1&quot;</span><span class="p">,</span> <span class="n">api_key</span><span class="o">=</span><span class="s2">&quot;dummy&quot;</span><span class="p">)</span>
<span class="n">response</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">completions</span><span class="o">.</span><span class="n">create</span><span class="p">(</span>
<span class="n">model</span><span class="o">=</span><span class="s2">&quot;/path/to/model&quot;</span><span class="p">,</span>
<span class="n">prompt</span><span class="o">=</span><span class="s2">&quot;What is the capital city of France?&quot;</span><span class="p">,</span>
<span class="n">max_tokens</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span>
<span class="n">extra_body</span><span class="o">=</span><span class="p">{</span>
<span class="s2">&quot;lora_request&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;lora_name&quot;</span><span class="p">:</span> <span class="s2">&quot;lora-example-0&quot;</span><span class="p">,</span>
<span class="s2">&quot;lora_int_id&quot;</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span>
<span class="s2">&quot;lora_path&quot;</span><span class="p">:</span> <span class="s2">&quot;/path/to/lora_adapter&quot;</span>
<span class="p">}</span>
<span class="p">},</span>
<span class="p">)</span>
</pre></div>
</div>
</section>
</section>
<section id="trtllm-bench-with-lora">
<h2>TRTLLM bench with LORA<a class="headerlink" href="#trtllm-bench-with-lora" title="Link to this heading">#</a></h2>
<section id="id1">
<h3>YAML Configuration<a class="headerlink" href="#id1" title="Link to this heading">#</a></h3>
<p>Create an <code class="docutils literal notranslate"><span class="pre">extra_llm_api_options.yaml</span></code> file:</p>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><span class="nt">lora_config</span><span class="p">:</span>
<span class="w"> </span><span class="nt">lora_dir</span><span class="p">:</span>
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/workspaces/tensorrt_llm/loras/0</span>
<span class="w"> </span><span class="nt">max_lora_rank</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">64</span>
<span class="w"> </span><span class="nt">max_loras</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8</span>
<span class="w"> </span><span class="nt">max_cpu_loras</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8</span>
<span class="w"> </span><span class="nt">lora_target_modules</span><span class="p">:</span>
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">attn_q</span>
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">attn_k</span>
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">attn_v</span>
<span class="w"> </span><span class="nt">trtllm_modules_to_hf_modules</span><span class="p">:</span>
<span class="w"> </span><span class="nt">attn_q</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">q_proj</span>
<span class="w"> </span><span class="nt">attn_k</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">k_proj</span>
<span class="w"> </span><span class="nt">attn_v</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v_proj</span>
</pre></div>
</div>
</section>
<section id="run-trtllm-bench">
<h3>Run trtllm-bench<a class="headerlink" href="#run-trtllm-bench" title="Link to this heading">#</a></h3>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>trtllm-bench<span class="w"> </span>--model<span class="w"> </span><span class="nv">$model_path</span><span class="w"> </span>throughput<span class="w"> </span>--dataset<span class="w"> </span><span class="nv">$dataset_path</span><span class="w"> </span>--extra_llm_api_options<span class="w"> </span>extra_llm_api_options.yaml<span class="w"> </span>--num_requests<span class="w"> </span><span class="m">64</span><span class="w"> </span>--concurrency<span class="w"> </span><span class="m">16</span>
</pre></div>
</div>
</section>
</section>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="long-sequence.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">Long Sequences</p>
</div>
</a>
<a class="right-next"
href="multi-modality.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Multimodal Support in TensorRT LLM</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="#background">Background</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#basic-usage">Basic Usage</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#single-lora-adapter">Single LoRA Adapter</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#multi-lora-support">Multi-LoRA Support</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#advanced-usage">Advanced Usage</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#lora-with-quantization">LoRA with Quantization</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#nemo-lora-format">NeMo LoRA Format</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#cache-management">Cache Management</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#trtllm-serve-with-lora">TRTLLM serve with LoRA</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#yaml-configuration">YAML Configuration</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#starting-the-server">Starting the Server</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#client-usage">Client Usage</a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#trtllm-bench-with-lora">TRTLLM bench with LORA</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id1">YAML Configuration</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#run-trtllm-bench">Run trtllm-bench</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 October 19, 2025.</p>
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/796891b">796891b</a>.</p>
</div></div>
</div>
</div>
</footer>
</body>
</html>