mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
190 lines
10 KiB
HTML
190 lines
10 KiB
HTML
<!DOCTYPE html>
|
||
<html class="writer-html5" lang="en" data-content_root="./">
|
||
<head>
|
||
<meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||
<title>Welcome to TensorRT-LLM’s documentation! — tensorrt_llm documentation</title>
|
||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=80d5e7a1" />
|
||
<link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
|
||
|
||
|
||
<!--[if lt IE 9]>
|
||
<script src="_static/js/html5shiv.min.js"></script>
|
||
<![endif]-->
|
||
|
||
<script src="_static/jquery.js?v=5d32c60e"></script>
|
||
<script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
|
||
<script src="_static/documentation_options.js?v=5929fcd5"></script>
|
||
<script src="_static/doctools.js?v=888ff710"></script>
|
||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||
<script src="_static/js/theme.js"></script>
|
||
<link rel="index" title="Index" href="genindex.html" />
|
||
<link rel="search" title="Search" href="search.html" />
|
||
<link rel="next" title="TensorRT-LLM Architecture" href="architecture.html" />
|
||
</head>
|
||
|
||
<body class="wy-body-for-nav">
|
||
<div class="wy-grid-for-nav">
|
||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||
<div class="wy-side-scroll">
|
||
<div class="wy-side-nav-search" >
|
||
|
||
|
||
|
||
<a href="#" class="icon icon-home">
|
||
tensorrt_llm
|
||
</a>
|
||
<div role="search">
|
||
<form id="rtd-search-form" class="wy-form" action="search.html" method="get">
|
||
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
|
||
<input type="hidden" name="check_keywords" value="yes" />
|
||
<input type="hidden" name="area" value="default" />
|
||
</form>
|
||
</div>
|
||
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
|
||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference internal" href="architecture.html">TensorRT-LLM Architecture</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="gpt_runtime.html">C++ GPT Runtime</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="batch_manager.html">The Batch Manager in TensorRT-LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="gpt_attention.html">Multi-head, Multi-query and Group-query Attention</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="installation.html">TensorRT-LLM Installation</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="performance.html">Performance of TensorRT-LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="2023-05-19-how-to-debug.html">How to debug</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="2023-05-17-how-to-add-a-new-model.html">How to add a new model</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="graph-rewriting.html">Graph Rewriting Module</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="memory.html">Memory Usage of TensorRT-LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="new_workflow.html">New Workflow</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">Python API</span></p>
|
||
<ul>
|
||
<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 class="caption" role="heading"><span class="caption-text">C++ API</span></p>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference internal" href="_cpp_gen/runtime.html">Runtime</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">Blogs</span></p>
|
||
<ul>
|
||
<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>
|
||
</ul>
|
||
|
||
</div>
|
||
</div>
|
||
</nav>
|
||
|
||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
|
||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||
<a href="#">tensorrt_llm</a>
|
||
</nav>
|
||
|
||
<div class="wy-nav-content">
|
||
<div class="rst-content">
|
||
<div role="navigation" aria-label="Page navigation">
|
||
<ul class="wy-breadcrumbs">
|
||
<li><a href="#" class="icon icon-home" aria-label="Home"></a></li>
|
||
<li class="breadcrumb-item active">Welcome to TensorRT-LLM’s documentation!</li>
|
||
<li class="wy-breadcrumbs-aside">
|
||
<a href="_sources/index.rst.txt" rel="nofollow"> View page source</a>
|
||
</li>
|
||
</ul>
|
||
<hr/>
|
||
</div>
|
||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||
<div itemprop="articleBody">
|
||
|
||
<section id="welcome-to-tensorrt-llm-s-documentation">
|
||
<h1>Welcome to TensorRT-LLM’s documentation!<a class="headerlink" href="#welcome-to-tensorrt-llm-s-documentation" title="Link to this heading"></a></h1>
|
||
<div class="toctree-wrapper compound">
|
||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference internal" href="architecture.html">TensorRT-LLM Architecture</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="gpt_runtime.html">C++ GPT Runtime</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="batch_manager.html">The Batch Manager in TensorRT-LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="gpt_attention.html">Multi-head, Multi-query and Group-query Attention</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="installation.html">TensorRT-LLM Installation</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="performance.html">Performance of TensorRT-LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="2023-05-19-how-to-debug.html">How to debug</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="2023-05-17-how-to-add-a-new-model.html">How to add a new model</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="graph-rewriting.html">Graph Rewriting Module</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="memory.html">Memory Usage of TensorRT-LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="new_workflow.html">New Workflow</a></li>
|
||
</ul>
|
||
</div>
|
||
<section id="python-api">
|
||
<h2>Python API<a class="headerlink" href="#python-api" title="Link to this heading"></a></h2>
|
||
<ul class="simple">
|
||
<li><p><a class="reference internal" href="python-api/tensorrt_llm.layers.html"><span class="doc">tensorrt_llm.layers</span></a></p></li>
|
||
<li><p><a class="reference internal" href="python-api/tensorrt_llm.functional.html"><span class="doc">tensorrt_llm.functional</span></a></p></li>
|
||
<li><p><a class="reference internal" href="python-api/tensorrt_llm.models.html"><span class="doc">tensorrt_llm.models</span></a></p></li>
|
||
<li><p><a class="reference internal" href="python-api/tensorrt_llm.plugin.html"><span class="doc">tensorrt_llm.plugin</span></a></p></li>
|
||
<li><p><a class="reference internal" href="python-api/tensorrt_llm.quantization.html"><span class="doc">tensorrt_llm.quantization</span></a></p></li>
|
||
<li><p><a class="reference internal" href="python-api/tensorrt_llm.runtime.html"><span class="doc">tensorrt_llm.runtime</span></a></p></li>
|
||
</ul>
|
||
<div class="toctree-wrapper compound">
|
||
</div>
|
||
</section>
|
||
<section id="c-api">
|
||
<h2>C++ API<a class="headerlink" href="#c-api" title="Link to this heading"></a></h2>
|
||
<ul class="simple">
|
||
<li><p><a class="reference internal" href="_cpp_gen/runtime.html"><span class="doc">cpp/runtime</span></a></p></li>
|
||
</ul>
|
||
<div class="toctree-wrapper compound">
|
||
</div>
|
||
</section>
|
||
</section>
|
||
<section id="indices-and-tables">
|
||
<h1>Indices and tables<a class="headerlink" href="#indices-and-tables" title="Link to this heading"></a></h1>
|
||
<ul class="simple">
|
||
<li><p><a class="reference internal" href="genindex.html"><span class="std std-ref">Index</span></a></p></li>
|
||
<li><p><a class="reference internal" href="py-modindex.html"><span class="std std-ref">Module Index</span></a></p></li>
|
||
<li><p><a class="reference internal" href="search.html"><span class="std std-ref">Search Page</span></a></p></li>
|
||
</ul>
|
||
<section id="blogs">
|
||
<h2>Blogs<a class="headerlink" href="#blogs" title="Link to this heading"></a></h2>
|
||
<div class="toctree-wrapper compound">
|
||
</div>
|
||
</section>
|
||
</section>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
|
||
<a href="architecture.html" class="btn btn-neutral float-right" title="TensorRT-LLM Architecture" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
|
||
</div>
|
||
|
||
<hr/>
|
||
|
||
<div role="contentinfo">
|
||
<p>© Copyright 2023, NVidia.</p>
|
||
</div>
|
||
|
||
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
|
||
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
|
||
provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||
|
||
|
||
</footer>
|
||
</div>
|
||
</div>
|
||
</section>
|
||
</div>
|
||
<script>
|
||
jQuery(function () {
|
||
SphinxRtdTheme.Navigation.enable(true);
|
||
});
|
||
</script>
|
||
|
||
</body>
|
||
</html> |