kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
5ecf4d1122
TensorRT-LLMs/reference/support-matrix.html
Kaiyu Xie bb9465295f Fix main page 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
2025-04-26 05:56:13 +00:00

832 lines
45 KiB
HTML
Raw Blame History

<!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>Support Matrix &#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" />
<!-- 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>DOCUMENTATION_OPTIONS.pagename = 'reference/support-matrix';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '0.20.0rc0';
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="Numerical Precision" href="precision.html" />
<link rel="prev" title="Troubleshooting" href="troubleshooting.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="0.20.0rc0" />
</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"><a class="reference internal" href="../key-features.html">Key Features</a></li>
<li class="toctree-l1"><a class="reference internal" href="../torch.html">PyTorch Backend</a></li>
<li class="toctree-l1"><a class="reference internal" href="../release-notes.html">Release Notes</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Installation</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../installation/linux.html">Installing on Linux</a></li>
<li class="toctree-l1"><a class="reference internal" href="../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
<li class="toctree-l1"><a class="reference internal" href="../installation/grace-hopper.html">Installing on Grace Hopper</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">LLM API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../llm-api/index.html">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">Examples</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1 has-children"><a class="reference internal" href="../examples/index.html">LLM Examples Introduction</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_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_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_customize.html">Generate text with customization</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_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_quantization.html">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_eagle_decoding.html">Generate Text Using Eagle Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_kv_events.html">Get KV Cache Events</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_auto_parallel.html">Automatic Parallelism with LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../examples/customization.html">LLM Common Customizations</a></li>
<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_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_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_customize.html">Generate text with customization</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_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_quantization.html">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_eagle_decoding.html">Generate Text Using Eagle Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_inference_kv_events.html">Get KV Cache Events</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_auto_parallel.html">Automatic Parallelism with LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</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/genai_perf_client.html">Genai Perf Client</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</a></li>
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Model Definition API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.layers.html">Layers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.functional.html">Functionals</a></li>
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.models.html">Models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.plugin.html">Plugin</a></li>
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.quantization.html">Quantization</a></li>
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">C++ API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../_cpp_gen/executor.html">Executor</a></li>
<li class="toctree-l1"><a class="reference internal" href="../_cpp_gen/runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-build.html">trtllm-build</a></li>
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-serve.html">trtllm-serve</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Architecture</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../architecture/overview.html">TensorRT-LLM Architecture</a></li>
<li class="toctree-l1"><a class="reference internal" href="../architecture/core-concepts.html">Model Definition</a></li>
<li class="toctree-l1"><a class="reference internal" href="../architecture/checkpoint.html">TensorRT-LLM Checkpoint</a></li>
<li class="toctree-l1"><a class="reference internal" href="../architecture/workflow.html">TensorRT-LLM Build Workflow</a></li>
<li class="toctree-l1"><a class="reference internal" href="../architecture/add-model.html">Adding a Model</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Advanced</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../advanced/gpt-attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/gpt-runtime.html">C++ GPT Runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/executor.html">Executor API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/graph-rewriting.html">Graph Rewriting Module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/lora.html">Run gpt-2b + LoRA using Executor / cpp runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/expert-parallelism.html">Expert Parallelism in TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/kv-cache-reuse.html">KV cache reuse</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/speculative-decoding.html">Speculative Sampling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/disaggregated-service.html">Disaggregated-Service (experimental)</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Performance</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../performance/perf-overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../performance/perf-benchmarking.html">Benchmarking</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../performance/performance-tuning-guide/index.html">Performance Tuning Guide</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="../performance/performance-tuning-guide/benchmarking-default-performance.html">Benchmarking Default Performance</a></li>
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/useful-build-time-flags.html">Useful Build-Time Flags</a></li>
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.html">Tuning Max Batch Size and Max Num Tokens</a></li>
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/deciding-model-sharding-strategy.html">Deciding Model Sharding Strategy</a></li>
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/fp8-quantization.html">FP8 Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/useful-runtime-flags.html">Useful Runtime Options</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../performance/perf-analysis.html">Performance Analysis</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Reference</span></p>
<ul class="current nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="troubleshooting.html">Troubleshooting</a></li>
<li class="toctree-l1 current active"><a class="current reference internal" href="#">Support Matrix</a></li>
<li class="toctree-l1"><a class="reference internal" href="precision.html">Numerical Precision</a></li>
<li class="toctree-l1"><a class="reference internal" href="memory.html">Memory Usage of TensorRT-LLM</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/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token</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/Falcon180B-H200.html">Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/quantization-in-TRT-LLM.html">Speed up inference with SOTA quantization techniques in TRT-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>
</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">Support Matrix</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="support-matrix">
<span id="id1"></span><h1>Support Matrix<a class="headerlink" href="#support-matrix" title="Link to this heading">#</a></h1>
<p>TensorRT-LLM optimizes the performance of a range of well-known models on NVIDIA GPUs. The following sections provide a list of supported GPU architectures as well as important features implemented in TensorRT-LLM.</p>
<section id="models">
<h2>Models<a class="headerlink" href="#models" title="Link to this heading">#</a></h2>
<section id="llm-models">
<h3>LLM Models<a class="headerlink" href="#llm-models" title="Link to this heading">#</a></h3>
<ul class="simple">
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/arctic">Arctic</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/baichuan">Baichuan/Baichuan2</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/enc_dec">BART</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/bert">BERT</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/bloom">BLOOM</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/enc_dec">ByT5</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/chatglm">GLM/ChatGLM/ChatGLM2/ChatGLM3/GLM-4</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/llama">Code LLaMA</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/dbrx">DBRX</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/exaone">Exaone</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/enc_dec">FairSeq NMT</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/falcon">Falcon</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/enc_dec">Flan-T5</a> <a class="footnote-reference brackets" href="#encdec" id="id2" role="doc-noteref"><span class="fn-bracket">[</span>1<span class="fn-bracket">]</span></a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/gemma">Gemma/Gemma2</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/gpt">GPT</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/gptj">GPT-J</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/gpt">GPT-Nemo</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/gptneox">GPT-NeoX</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/granite">Granite-3.0</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/grok">Grok-1</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/internlm">InternLM</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/internlm2">InternLM2</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/llama">LLaMA/LLaMA 2/LLaMA 3/LLaMA 3.1</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/mamba">Mamba</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/enc_dec">mBART</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/nemotron">Minitron</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/llama">Mistral</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/llama">Mistral NeMo</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/mixtral">Mixtral</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/mpt">MPT</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/nemotron">Nemotron</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/enc_dec">mT5</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/opt">OPT</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/phi">Phi-1.5/Phi-2/Phi-3</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/qwen">Qwen/Qwen1.5/Qwen2</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/qwenvl">Qwen-VL</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/recurrentgemma">RecurrentGemma</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/mpt">Replit Code</a> <a class="footnote-reference brackets" href="#replitcode" id="id3" role="doc-noteref"><span class="fn-bracket">[</span>2<span class="fn-bracket">]</span></a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/bert">RoBERTa</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/gpt">SantaCoder</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/skywork">Skywork</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/smaug">Smaug</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/gpt">StarCoder</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/enc_dec">T5</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/whisper">Whisper</a></p></li>
</ul>
</section>
<section id="multi-modal-models">
<h3>Multi-Modal Models <a class="footnote-reference brackets" href="#multimod" id="id4" role="doc-noteref"><span class="fn-bracket">[</span>3<span class="fn-bracket">]</span></a><a class="headerlink" href="#multi-modal-models" title="Link to this heading">#</a></h3>
<ul class="simple">
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">BLIP2 w/ OPT</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">BLIP2 w/ T5</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">CogVLM</a> <a class="footnote-reference brackets" href="#bf16only" id="id5" role="doc-noteref"><span class="fn-bracket">[</span>4<span class="fn-bracket">]</span></a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">Deplot</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">Fuyu</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">Kosmos</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">LLaVA-v1.5</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">LLaVa-Next</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">LLaVa-OneVision</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">NeVA</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">Nougat</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">Phi-3-vision</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">Video NeVA</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">VILA</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">MLLaMA</a></p></li>
<li><p><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/multimodal">LLama 3.2 VLM</a></p></li>
</ul>
</section>
</section>
<section id="hardware">
<span id="support-matrix-hardware"></span><h2>Hardware<a class="headerlink" href="#hardware" title="Link to this heading">#</a></h2>
<p>The following table shows the supported hardware for TensorRT-LLM.</p>
<p>If a GPU architecture is not listed, the TensorRT-LLM team does not develop or test the software on the architecture and support is limited to community support.
In addition, older architectures can have limitations for newer software releases.</p>
<div class="pst-scrollable-table-container"><table class="table">
<colgroup>
<col style="width: 20.0%" />
<col style="width: 80.0%" />
</colgroup>
<thead>
<tr class="row-odd"><th class="head"></th>
<th class="head"><p>Hardware Compatibility</p></th>
</tr>
</thead>
<tbody>
<tr class="row-even"><td><p>Operating System</p></td>
<td><p>TensorRT-LLM requires Linux x86_64 or Linux aarch64.</p></td>
</tr>
<tr class="row-odd"><td><p>GPU Model Architectures</p></td>
<td><ul class="simple">
<li><p><a class="reference external" href="https://www.nvidia.com/en-us/data-center/technologies/blackwell-architecture/">NVIDIA Blackwell Architecture</a></p></li>
<li><p><a class="reference external" href="https://www.nvidia.com/en-us/data-center/grace-hopper-superchip/">NVIDIA Grace Hopper Superchip</a></p></li>
<li><p><a class="reference external" href="https://www.nvidia.com/en-us/data-center/technologies/hopper-architecture/">NVIDIA Hopper Architecture</a></p></li>
<li><p><a class="reference external" href="https://www.nvidia.com/en-us/technologies/ada-architecture/">NVIDIA Ada Lovelace Architecture</a></p></li>
<li><p><a class="reference external" href="https://www.nvidia.com/en-us/data-center/ampere-architecture/">NVIDIA Ampere Architecture</a></p></li>
</ul>
</td>
</tr>
</tbody>
</table>
</div>
</section>
<section id="software">
<span id="support-matrix-software"></span><h2>Software<a class="headerlink" href="#software" title="Link to this heading">#</a></h2>
<p>The following table shows the supported software for TensorRT-LLM.</p>
<div class="pst-scrollable-table-container"><table class="table">
<colgroup>
<col style="width: 20.0%" />
<col style="width: 80.0%" />
</colgroup>
<thead>
<tr class="row-odd"><th class="head"></th>
<th class="head"><p>Software Compatibility</p></th>
</tr>
</thead>
<tbody>
<tr class="row-even"><td><p>Container</p></td>
<td><p><a class="reference external" href="https://docs.nvidia.com/deeplearning/frameworks/support-matrix/index.html">25.03</a></p></td>
</tr>
<tr class="row-odd"><td><p>TensorRT</p></td>
<td><p><a class="reference external" href="https://docs.nvidia.com/deeplearning/tensorrt/release-notes/index.html">10.9</a></p></td>
</tr>
<tr class="row-even"><td><p>Precision</p></td>
<td><ul class="simple">
<li><p>Hopper (SM90) - FP32, FP16, BF16, FP8, INT8, INT4</p></li>
<li><p>Ada Lovelace (SM89) - FP32, FP16, BF16, FP8, INT8, INT4</p></li>
<li><p>Ampere (SM80, SM86) - FP32, FP16, BF16, INT8, INT4<a class="footnote-reference brackets" href="#smgte89" id="id6" role="doc-noteref"><span class="fn-bracket">[</span>5<span class="fn-bracket">]</span></a></p></li>
</ul>
</td>
</tr>
</tbody>
</table>
</div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Support for FP8 and quantized data types (INT8 or INT4) is not implemented for all the models. Refer to <a class="reference internal" href="precision.html#precision"><span class="std std-ref">Numerical Precision</span></a> and <a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples">examples</a> folder for additional information.</p>
</div>
</section>
</section>
<hr class="footnotes docutils" />
<aside class="footnote-list brackets">
<aside class="footnote brackets" id="encdec" role="doc-footnote">
<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id2">1</a><span class="fn-bracket">]</span></span>
<p>Encoder-Decoder provides general encoder-decoder functionality that supports many encoder-decoder models such as T5 family, BART family, Whisper family, NMT family, and so on.</p>
</aside>
<aside class="footnote brackets" id="replitcode" role="doc-footnote">
<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id3">2</a><span class="fn-bracket">]</span></span>
<p>Replit Code is not supported with the transformers 4.45+.</p>
</aside>
<aside class="footnote brackets" id="multimod" role="doc-footnote">
<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id4">3</a><span class="fn-bracket">]</span></span>
<p>Multi-modal provides general multi-modal functionality that supports many multi-modal architectures such as BLIP2 family, LLaVA family, and so on.</p>
</aside>
<aside class="footnote brackets" id="bf16only" role="doc-footnote">
<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id5">4</a><span class="fn-bracket">]</span></span>
<p>Only supports bfloat16 precision.</p>
</aside>
<aside class="footnote brackets" id="smgte89" role="doc-footnote">
<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id6">5</a><span class="fn-bracket">]</span></span>
<p>INT4 AWQ and GPTQ with FP8 activations require SM &gt;= 89.</p>
</aside>
</aside>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="troubleshooting.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">Troubleshooting</p>
</div>
</a>
<a class="right-next"
href="precision.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Numerical Precision</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="#models">Models</a><ul class="nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#llm-models">LLM Models</a></li>
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#multi-modal-models">Multi-Modal Models </a></li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#hardware">Hardware</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#software">Software</a></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>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink