mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-24 12:42:54 +08:00
372 lines
22 KiB
HTML
372 lines
22 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>Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100 — 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=e59714d7" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/copybutton.css?v=76b2166b" />
|
||
|
||
|
||
<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=65e89d2a"></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="Speed up inference with SOTA quantization techniques in TRT-LLM" href="quantization-in-TRT-LLM.html" />
|
||
<link rel="prev" title="H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM" href="H200launch.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>
|
||
<li class="toctree-l1"><a class="reference internal" href="../installation/grace-hopper.html">Installing on Grace Hopper</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>
|
||
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-serve.html">trtllm-serve</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/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>
|
||
</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>
|
||
<li class="toctree-l1"><a class="reference internal" href="../reference/troubleshooting.html">Troubleshooting</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../reference/support-matrix.html">Support Matrix</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../reference/precision.html">Numerical Precision</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../reference/memory.html">Memory Usage of TensorRT-LLM</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">Blogs</span></p>
|
||
<ul class="current">
|
||
<li class="toctree-l1"><a class="reference internal" href="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="H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM</a></li>
|
||
<li class="toctree-l1 current"><a class="current reference internal" href="#">Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100</a><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="#falcon-180b-on-a-single-h200-with-int4-awq">Falcon-180B on a single H200 with INT4 AWQ</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#llama-70b-on-h200-up-to-6-7x-a100">Llama-70B on H200 up to 6.7x A100</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#closing">Closing</a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="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="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">Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100</li>
|
||
<li class="wy-breadcrumbs-aside">
|
||
<a href="../_sources/blogs/Falcon180B-H200.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="falcon-180b-on-a-single-h200-gpu-with-int4-awq-and-6-7x-faster-llama-70b-over-a100">
|
||
<h1>Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100<a class="headerlink" href="#falcon-180b-on-a-single-h200-gpu-with-int4-awq-and-6-7x-faster-llama-70b-over-a100" title="Link to this heading"></a></h1>
|
||
<p>H200’s large capacity & high memory bandwidth, paired with TensorRT-LLM’s
|
||
optimizations, maximizes inference performance.</p>
|
||
<section id="falcon-180b-on-a-single-h200-with-int4-awq">
|
||
<h2>Falcon-180B on a single H200 with INT4 AWQ<a class="headerlink" href="#falcon-180b-on-a-single-h200-with-int4-awq" title="Link to this heading"></a></h2>
|
||
<p><a class="reference external" href="https://huggingface.co/tiiuae/falcon-180B">Falcon-180B</a>, one of the largest &
|
||
most accurate open source models available, can run on a <em>single</em> H200 GPU.</p>
|
||
<p>The 141GB of memory on H200, paired with TensorRT-LLM running INT4 AWQ with
|
||
FP8, allows for the entire large language model to fit on a single GPU, where
|
||
previously eight A100s were required. H200 Falcon-180B provides up to <strong>800</strong>
|
||
tok/s and retains high accuracy.</p>
|
||
<p><strong>Model Performance:</strong>
|
||
H200’s large capacity & high memory bandwidth, utilizing INT4 AWQ to reduce
|
||
memory footprint, allows for great performance on Falcon-180B on a single GPU.</p>
|
||
<img src="https://github.com/NVIDIA/TensorRT-LLM/blob/rel/docs/source/blogs/media/Falcon180B-H200_tps.png?raw=true" alt="Falcon-180B performance comparison" width="450" height="auto">
|
||
<p><sup>Preliminary measured Performance, subject to change. TP1 does not represent peak performance on H200. </sup>
|
||
<sup>
|
||
TensorRT-LLM v0.7a |
|
||
Falcon-180B |
|
||
1xH200 TP1 |
|
||
INT4 AWQ |
|
||
BS: (in order) 256, 128 </sup></p>
|
||
<p><strong>Model Accuracy:</strong>
|
||
Often quantization can have adverse impacts on the accuracy of the model,
|
||
however, TensorRT-LLM’s AWQ decreases memory footprint of the model by <strong>4x</strong>
|
||
while maintaining high accuracy.</p>
|
||
<img src="https://github.com/NVIDIA/TensorRT-LLM/blob/rel/docs/source/blogs/media/Falcon180B-H200_acc.png?raw=true" alt="Falcon-180B accuracy comparison" width="600" height="auto">
|
||
<p><sup>Preliminary measured accuracy, subject to change. </sup>
|
||
<sup>
|
||
TensorRT-LLM v0.7a |
|
||
Falcon-180B |
|
||
1xH200 TP1 |
|
||
INT4 AWQ
|
||
</sup></p>
|
||
<p><a class="reference external" href="https://arxiv.org/abs/2306.00978"><strong>INT4 Activation-aware Weight Quantization
|
||
(AWQ)</strong></a> (Lin et al., 2023) is a quantization
|
||
technique which compresses the weights of an LLM down to 4bits based on their
|
||
relative importance, and performs computation in FP16. This allows for AWQ to
|
||
retain higher accuracy than other 4bit methods and reduce memory usage, but
|
||
requires special kernels capable of handling the change in precision
|
||
performantly.</p>
|
||
<p>TensorRT-LLM has implemented custom kernels for AWQ, and taken the technique a
|
||
step further by performing FP8 computation on Hopper GPUs instead of the
|
||
standard FP16.</p>
|
||
<p>Similar examples running Falcon-180B with quantization in TensorRT-LLM are
|
||
available in <a class="reference internal" href="#/examples/falcon"><span class="xref myst">examples/falcon</span></a>.</p>
|
||
</section>
|
||
<section id="llama-70b-on-h200-up-to-6-7x-a100">
|
||
<h2>Llama-70B on H200 up to 6.7x A100<a class="headerlink" href="#llama-70b-on-h200-up-to-6-7x-a100" title="Link to this heading"></a></h2>
|
||
<p>TensorRT-LLM has improved its Group Query Attention (GQA) kernels, in the
|
||
generation phase, providing up to 2.4x improvement on Llama-70B over
|
||
TensorRT-LLM v0.5, achieving over <strong>3,800</strong> tok/s/gpu at up to <strong>6.7x</strong> faster
|
||
than A100.</p>
|
||
<p><strong>H200 6.7x A100</strong></p>
|
||
<img src="https://github.com/NVIDIA/TensorRT-LLM/blob/rel/docs/source/blogs/media/Falcon180B-H200_H200vA100.png?raw=true" alt="Llama-70B H200 vs A100 comparison" width="600" height="auto">
|
||
<table class="docutils align-default">
|
||
<thead>
|
||
<tr class="row-odd"><th class="head text-left"><p>Model</p></th>
|
||
<th class="head text-left"><p>GPUs</p></th>
|
||
<th class="head text-left"><p>Input Length</p></th>
|
||
<th class="head text-left"><p>Output Length</p></th>
|
||
<th class="head text-left"><p>Throughput (out tok/s/GPU)</p></th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr class="row-even"><td class="text-left"><p>Llama-70B</p></td>
|
||
<td class="text-left"><p>1</p></td>
|
||
<td class="text-left"><p>128</p></td>
|
||
<td class="text-left"><p>128</p></td>
|
||
<td class="text-left"><p>3,803</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td class="text-left"><p></p></td>
|
||
<td class="text-left"><p>8</p></td>
|
||
<td class="text-left"><p></p></td>
|
||
<td class="text-left"><p></p></td>
|
||
<td class="text-left"><p>3,803</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td class="text-left"><p></p></td>
|
||
<td class="text-left"><p>1</p></td>
|
||
<td class="text-left"><p></p></td>
|
||
<td class="text-left"><p>2048</p></td>
|
||
<td class="text-left"><p>2,941</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td class="text-left"><p></p></td>
|
||
<td class="text-left"><p>8</p></td>
|
||
<td class="text-left"><p></p></td>
|
||
<td class="text-left"><p></p></td>
|
||
<td class="text-left"><p>3,163</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td class="text-left"><p></p></td>
|
||
<td class="text-left"><p>1</p></td>
|
||
<td class="text-left"><p></p></td>
|
||
<td class="text-left"><p>4096</p></td>
|
||
<td class="text-left"><p>1,946</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td class="text-left"><p></p></td>
|
||
<td class="text-left"><p>8</p></td>
|
||
<td class="text-left"><p></p></td>
|
||
<td class="text-left"><p></p></td>
|
||
<td class="text-left"><p>2,263</p></td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
<p><sup>Preliminary measured performance, subject to change. </sup>
|
||
<sup>
|
||
TensorRT-LLM v0.7a |
|
||
Llama2-70B |
|
||
1xH200 = TP1, 8xH200 = max TP/PP/DP config |
|
||
FP8 |
|
||
BS: (in order) 960, 960, 192, 560, 96, 640 </sup></p>
|
||
<p><strong>TensorRT-LLM GQA now 2.4x faster on H200</strong></p>
|
||
<img src="https://github.com/NVIDIA/TensorRT-LLM/blob/rel/docs/source/blogs/media/Falcon180B-H200_DecvOct.png?raw=true" alt="Llama-70B H200 December vs Oct." width="400" height="auto">
|
||
<p><sup>Preliminary measured performance, subject to change.</sup>
|
||
<sup>
|
||
TensorRT-LLM v0.7a vs TensorRT-LLM v0.6a |
|
||
Llama2-70B |
|
||
1xH200 TP1 |
|
||
FP8 |
|
||
BS 192 </sup></p>
|
||
<p><a class="reference external" href="https://arxiv.org/abs/2305.13245v2"><strong>Grouped Query Attention (GQA)</strong></a>
|
||
(Ainslie et al., 2023), used in Llama-70B, is a variant of Multihead Attention
|
||
(MHA) which groups key-value (KV) heads together, resulting in fewer KV heads
|
||
than query (Q) heads. TensorRT-LLM has a custom implementation of MHA which
|
||
supports GQA, multi-query attention (MQA) and standard MHA. It leverages Tensor
|
||
Cores, including in the generation phase, and delivers great performance on
|
||
NVIDIA GPUs.</p>
|
||
<section id="closing">
|
||
<h3>Closing<a class="headerlink" href="#closing" title="Link to this heading"></a></h3>
|
||
<p>These improvements will be published in the <code class="docutils literal notranslate"><span class="pre">main</span></code> branch soon, and will be
|
||
included in the v0.7 & v0.8 releases.</p>
|
||
<p>Similar examples running Llama-70B in TensorRT-LLM are published in
|
||
<a class="reference internal" href="#/examples/llama"><span class="xref myst">examples/llama</span></a>.</p>
|
||
<p>For more information about H200, please see the <a class="reference internal" href="H200launch.html"><span class="std std-doc">H200 announcement blog</span></a>.</p>
|
||
<p>Throughput is calculated as output tokens per second per gpu.
|
||
<code class="docutils literal notranslate"><span class="pre">out_tps=output_seqlen*batch_size/total_latency/tp</span></code></p>
|
||
<p><sub> <strong>Glossary:</strong>
|
||
| DP = Data Parallel
|
||
ISL = Input Sequence Length
|
||
| PP = Pipeline Parallel
|
||
| OSL = Output Sequence Length
|
||
| OOM = Out of Memory
|
||
| TP = Tensor Parallel <sub/></p>
|
||
</section>
|
||
</section>
|
||
</section>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
|
||
<a href="H200launch.html" class="btn btn-neutral float-left" title="H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
|
||
<a href="quantization-in-TRT-LLM.html" class="btn btn-neutral float-right" title="Speed up inference with SOTA quantization techniques in TRT-LLM" 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 0x7fed9c6d5d60>
|
||
|
||
<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> |