mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
172 lines
10 KiB
HTML
172 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=1.0" />
|
|
<title>Overview: module code — 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" />
|
|
</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="../index.html" 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="../inference_request.html">Inference Request</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="../build_from_source.html">Build from Source</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>
|
|
<li class="toctree-l1"><a class="reference internal" href="../lora.html">Run gpt-2b + LoRA using GptManager / cpp runtime</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../perf_best_practices.html">Best Practices for Tuning the Performance of TensorRT-LLM</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../performance_analysis.html">Performance Analysis of TensorRT-LLM</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>
|
|
<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>
|
|
</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="../index.html">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="../index.html" class="icon icon-home" aria-label="Home"></a></li>
|
|
<li class="breadcrumb-item active">Overview: module code</li>
|
|
<li class="wy-breadcrumbs-aside">
|
|
</li>
|
|
</ul>
|
|
<hr/>
|
|
</div>
|
|
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
|
<div itemprop="articleBody">
|
|
|
|
<h1>All modules for which code is available</h1>
|
|
<ul><li><a href="tensorrt_llm/functional.html">tensorrt_llm.functional</a></li>
|
|
<li><a href="tensorrt_llm/layers/activation.html">tensorrt_llm.layers.activation</a></li>
|
|
<li><a href="tensorrt_llm/layers/attention.html">tensorrt_llm.layers.attention</a></li>
|
|
<li><a href="tensorrt_llm/layers/cast.html">tensorrt_llm.layers.cast</a></li>
|
|
<li><a href="tensorrt_llm/layers/conv.html">tensorrt_llm.layers.conv</a></li>
|
|
<li><a href="tensorrt_llm/layers/embedding.html">tensorrt_llm.layers.embedding</a></li>
|
|
<li><a href="tensorrt_llm/layers/linear.html">tensorrt_llm.layers.linear</a></li>
|
|
<li><a href="tensorrt_llm/layers/mlp.html">tensorrt_llm.layers.mlp</a></li>
|
|
<li><a href="tensorrt_llm/layers/normalization.html">tensorrt_llm.layers.normalization</a></li>
|
|
<li><a href="tensorrt_llm/layers/pooling.html">tensorrt_llm.layers.pooling</a></li>
|
|
<li><a href="tensorrt_llm/models/baichuan/model.html">tensorrt_llm.models.baichuan.model</a></li>
|
|
<li><a href="tensorrt_llm/models/bert/model.html">tensorrt_llm.models.bert.model</a></li>
|
|
<li><a href="tensorrt_llm/models/bloom/model.html">tensorrt_llm.models.bloom.model</a></li>
|
|
<li><a href="tensorrt_llm/models/chatglm/model.html">tensorrt_llm.models.chatglm.model</a></li>
|
|
<li><a href="tensorrt_llm/models/enc_dec/model.html">tensorrt_llm.models.enc_dec.model</a></li>
|
|
<li><a href="tensorrt_llm/models/falcon/model.html">tensorrt_llm.models.falcon.model</a></li>
|
|
<li><a href="tensorrt_llm/models/gpt/model.html">tensorrt_llm.models.gpt.model</a></li>
|
|
<li><a href="tensorrt_llm/models/gptj/model.html">tensorrt_llm.models.gptj.model</a></li>
|
|
<li><a href="tensorrt_llm/models/gptneox/model.html">tensorrt_llm.models.gptneox.model</a></li>
|
|
<li><a href="tensorrt_llm/models/llama/model.html">tensorrt_llm.models.llama.model</a></li>
|
|
<li><a href="tensorrt_llm/models/mamba/model.html">tensorrt_llm.models.mamba.model</a></li>
|
|
<li><a href="tensorrt_llm/models/medusa/model.html">tensorrt_llm.models.medusa.model</a></li>
|
|
<li><a href="tensorrt_llm/models/modeling_utils.html">tensorrt_llm.models.modeling_utils</a></li>
|
|
<li><a href="tensorrt_llm/models/mpt/model.html">tensorrt_llm.models.mpt.model</a></li>
|
|
<li><a href="tensorrt_llm/models/opt/model.html">tensorrt_llm.models.opt.model</a></li>
|
|
<li><a href="tensorrt_llm/models/phi/model.html">tensorrt_llm.models.phi.model</a></li>
|
|
<li><a href="tensorrt_llm/models/quantized/quant.html">tensorrt_llm.models.quantized.quant</a></li>
|
|
<li><a href="tensorrt_llm/models/qwen/model.html">tensorrt_llm.models.qwen.model</a></li>
|
|
<li><a href="tensorrt_llm/models/skywork/model.html">tensorrt_llm.models.skywork.model</a></li>
|
|
<li><a href="tensorrt_llm/plugin/plugin.html">tensorrt_llm.plugin.plugin</a></li>
|
|
<li><a href="tensorrt_llm/quantization/mode.html">tensorrt_llm.quantization.mode</a></li>
|
|
<li><a href="tensorrt_llm/runtime/generation.html">tensorrt_llm.runtime.generation</a></li>
|
|
<li><a href="tensorrt_llm/runtime/kv_cache_manager.html">tensorrt_llm.runtime.kv_cache_manager</a></li>
|
|
<li><a href="tensorrt_llm/runtime/model_runner.html">tensorrt_llm.runtime.model_runner</a></li>
|
|
<li><a href="tensorrt_llm/runtime/session.html">tensorrt_llm.runtime.session</a></li>
|
|
</ul>
|
|
|
|
</div>
|
|
</div>
|
|
<footer>
|
|
|
|
<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> |