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
f8fa42adc3
TensorRT-LLMs/reference/support-matrix.html
石晓伟 ed7d8f3735
Update gh-pages (#2404)
2024-11-01 20:31:15 +08:00

400 lines
28 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!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>Support Matrix &mdash; 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" />
<link rel="stylesheet" type="text/css" href="../_static/copybutton.css?v=76b2166b" />
<!--[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/clipboard.min.js?v=a7894cd8"></script>
<script src="../_static/copybutton.js?v=f281be69"></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="Numerical Precision" href="precision.html" />
<link rel="prev" title="Troubleshooting" href="troubleshooting.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">Getting Started</span></p>
<ul>
<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="../release-notes.html">Release Notes</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Installation</span></p>
<ul>
<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/windows.html">Installing on Windows</a></li>
<li class="toctree-l1"><a class="reference internal" href="../installation/build-from-source-windows.html">Building from Source Code on Windows</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">LLM API</span></p>
<ul>
<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 class="caption" role="heading"><span class="caption-text">LLM API Examples</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../llm-api-examples/index.html">LLM Examples Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="../llm-api-examples/customization.html">Common Customizations</a></li>
<li class="toctree-l1"><a class="reference internal" href="../llm-api-examples/llm_api_examples.html">Examples</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Model Definition 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/executor.html">Executor</a></li>
<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">Command-Line Reference</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-build.html">trtllm-build</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Architecture</span></p>
<ul>
<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/core-concepts.html#compilation">Compilation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../architecture/core-concepts.html#runtime">Runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../architecture/core-concepts.html#multi-gpu-and-multi-node-support">Multi-GPU and Multi-Node Support</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 class="caption" role="heading"><span class="caption-text">Advanced</span></p>
<ul>
<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/batch-manager.html">The Batch Manager in TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/inference-request.html">Inference Request</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/inference-request.html#responses">Responses</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/lora.html">Run gpt-2b + LoRA using GptManager / 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/speculative-decoding.html#lookahead-decoding">Lookahead decoding</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Performance</span></p>
<ul>
<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"><a class="reference internal" href="../performance/perf-best-practices.html">Best Practices</a></li>
<li class="toctree-l1"><a class="reference internal" href="../performance/perf-analysis.html">Performance Analysis</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Reference</span></p>
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="troubleshooting.html">Troubleshooting</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">Support Matrix</a><ul>
<li class="toctree-l2"><a class="reference internal" href="#models">Models</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#llm-models">LLM Models</a></li>
<li class="toctree-l3"><a class="reference internal" href="#multi-modal-models">Multi-Modal Models </a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="#hardware">Hardware</a></li>
<li class="toctree-l2"><a class="reference internal" href="#software">Software</a></li>
</ul>
</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 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>
<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>
</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">Support Matrix</li>
<li class="wy-breadcrumbs-aside">
<a href="../_sources/reference/support-matrix.md.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="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/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/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>[^ReplitCode]</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="id3" role="doc-noteref"><span class="fn-bracket">[</span>2<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="id4" role="doc-noteref"><span class="fn-bracket">[</span>3<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">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>
</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 is not listed, it is important to note that TensorRT-LLM is expected to work on GPUs based on the Volta, Turing, Ampere, Hopper, and Ada Lovelace architectures. Certain limitations may, however, apply.</p>
<table class="docutils align-default">
<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 Windows.</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/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>
<li><p><a class="reference external" href="https://www.nvidia.com/en-us/geforce/turing/">NVIDIA Turing Architecture</a></p></li>
<li><p><a class="reference external" href="https://www.nvidia.com/en-us/data-center/volta-gpu-architecture/">NVIDIA Volta Architecture</a> (experimental)</p></li>
</ul>
</td>
</tr>
</tbody>
</table>
</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>
<table class="docutils align-default">
<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">24.07</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">10.4</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="id5" role="doc-noteref"><span class="fn-bracket">[</span>4<span class="fn-bracket">]</span></a></p></li>
<li><p>Turing (SM75) - FP32, FP16, INT8<a class="footnote-reference brackets" href="#smooth" id="id6" role="doc-noteref"><span class="fn-bracket">[</span>5<span class="fn-bracket">]</span></a>, INT4</p></li>
<li><p>Volta (SM70) - FP32, FP16, INT8<a class="footnote-reference brackets" href="#smooth" id="id7" role="doc-noteref"><span class="fn-bracket">[</span>5<span class="fn-bracket">]</span></a>, INT4<a class="footnote-reference brackets" href="#smlt75" id="id8" role="doc-noteref"><span class="fn-bracket">[</span>6<span class="fn-bracket">]</span></a></p></li>
</ul>
</td>
</tr>
</tbody>
</table>
<p>[^ReplitCode]：Replit Code is not supported with the transformers 4.45+.</p>
<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>
<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="multimod" 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>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="#id4">3</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="#id5">4</a><span class="fn-bracket">]</span></span>
<p>INT4 AWQ and GPTQ with FP8 activations require SM &gt;= 89.</p>
</aside>
<aside class="footnote brackets" id="smooth" role="doc-footnote">
<span class="label"><span class="fn-bracket">[</span>5<span class="fn-bracket">]</span></span>
<span class="backrefs">(<a role="doc-backlink" href="#id6">1</a>,<a role="doc-backlink" href="#id7">2</a>)</span>
<p>INT8 SmoothQuant is not supported on SM70 and SM75.</p>
</aside>
<aside class="footnote brackets" id="smlt75" role="doc-footnote">
<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id8">6</a><span class="fn-bracket">]</span></span>
<p>INT4 AWQ and GPTQ are not supported on SM &lt; 75.</p>
</aside>
</aside>
</section>
</section>
</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="troubleshooting.html" class="btn btn-neutral float-left" title="Troubleshooting" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
<a href="precision.html" class="btn btn-neutral float-right" title="Numerical Precision" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div>
<hr/>
<div role="contentinfo">
<jinja2.runtime.BlockReference object at 0x7fc13f3418a0>
<div class="footer">
<p>
Copyright © 2024 NVIDIA Corporation
</p>
<p>
<a class="Link" href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/" target="_blank" rel="noopener"
data-cms-ai="0">Privacy Policy</a> |
<a class="Link" href="https://www.nvidia.com/en-us/about-nvidia/privacy-center/" target="_blank" rel="noopener"
data-cms-ai="0">Manage My Privacy</a> |
<a class="Link" href="https://www.nvidia.com/en-us/preferences/start/" target="_blank" rel="noopener"
data-cms-ai="0">Do Not Sell or Share My Data</a> |
<a class="Link" href="https://www.nvidia.com/en-us/about-nvidia/terms-of-service/" target="_blank"
rel="noopener" data-cms-ai="0">Terms of Service</a> |
<a class="Link" href="https://www.nvidia.com/en-us/about-nvidia/accessibility/" target="_blank" rel="noopener"
data-cms-ai="0">Accessibility</a> |
<a class="Link" href="https://www.nvidia.com/en-us/about-nvidia/company-policies/" target="_blank"
rel="noopener" data-cms-ai="0">Corporate Policies</a> |
<a class="Link" href="https://www.nvidia.com/en-us/product-security/" target="_blank" rel="noopener"
data-cms-ai="0">Product Security</a> |
<a class="Link" href="https://www.nvidia.com/en-us/contact/" target="_blank" rel="noopener"
data-cms-ai="0">Contact</a>
</p>
</div>
</div>
</footer>
</div>
</div>
</section>
</div>
<script>
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink