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
42d0585493
TensorRT-LLMs/blogs/H200launch.html
nv-guomingz 42d0585493
doc:fix llm api reference blank issue. (#2669)
2025-01-08 14:45:46 +08:00

317 lines
20 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>H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM &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=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=9bcbadda"></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="Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100" href="Falcon180B-H200.html" />
<link rel="prev" title="H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token" href="H100vsA100.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>
<li class="toctree-l1"><a class="reference internal" href="../advanced/disaggregated-service.html">Disaggregated-Service (experimental)</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 current"><a class="current reference internal" href="#">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM</a><ul>
<li class="toctree-l2"><a class="reference internal" href="#h200-vs-h100">H200 vs H100</a></li>
<li class="toctree-l2"><a class="reference internal" href="#latest-hbm-memory">Latest HBM Memory</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="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="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">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM</li>
<li class="wy-breadcrumbs-aside">
<a href="../_sources/blogs/H200launch.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">
<p>:loudspeaker: Note: The below data is using TensorRT-LLM v0.5. There have been significant improvements in v0.6 &amp; later. Please see updated Llama performance <a class="reference internal" href="Falcon180B-H200.html"><span class="std std-doc">here</span></a>.</p>
<section id="h200-achieves-nearly-12-000-tokens-sec-on-llama2-13b-with-tensorrt-llm">
<h1>H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM<a class="headerlink" href="#h200-achieves-nearly-12-000-tokens-sec-on-llama2-13b-with-tensorrt-llm" title="Link to this heading"></a></h1>
<p>TensorRT-LLM evaluation of the <a class="reference external" href="https://nvidianews.nvidia.com/news/nvidia-supercharges-hopper-the-worlds-leading-ai-computing-platform">new H200 GPU</a> achieves <strong>11,819 tokens/s on Llama2-13B</strong> on a single GPU. H200 is up to <strong>1.9x faster</strong> than H100. This performance is enabled by H200’s larger, faster <a class="reference internal" href="#latest-hbm-memory">HBM3e memory</a>.</p>
<p><strong>H200 FP8 Max throughput</strong></p>
<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>Batch Size<sup>(1)</sup></p></th>
<th class="head text-left"><p>TP<sup>(2)</sup></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-right"><p>Throughput (out tok/s/GPU)</p></th>
</tr>
</thead>
<tbody>
<tr class="row-even"><td class="text-left"><p>llama_13b</p></td>
<td class="text-left"><p>1024</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-right"><p>11,819</p></td>
</tr>
<tr class="row-odd"><td class="text-left"><p>llama_13b</p></td>
<td class="text-left"><p>128</p></td>
<td class="text-left"><p>1</p></td>
<td class="text-left"><p>128</p></td>
<td class="text-left"><p>2048</p></td>
<td class="text-right"><p>4,750</p></td>
</tr>
<tr class="row-even"><td class="text-left"><p>llama_13b</p></td>
<td class="text-left"><p>64</p></td>
<td class="text-left"><p>1</p></td>
<td class="text-left"><p>2048</p></td>
<td class="text-left"><p>128</p></td>
<td class="text-right"><p>1,349</p></td>
</tr>
<tr class="row-odd"><td class="text-left"><p>llama_70b</p></td>
<td class="text-left"><p>512</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-right"><p>3,014</p></td>
</tr>
<tr class="row-even"><td class="text-left"><p>llama_70b</p></td>
<td class="text-left"><p>512</p></td>
<td class="text-left"><p>2</p></td>
<td class="text-left"><p>128</p></td>
<td class="text-left"><p>2048</p></td>
<td class="text-right"><p>1,654</p></td>
</tr>
<tr class="row-odd"><td class="text-left"><p>llama_70b</p></td>
<td class="text-left"><p>64</p></td>
<td class="text-left"><p>1</p></td>
<td class="text-left"><p>2048</p></td>
<td class="text-left"><p>128</p></td>
<td class="text-right"><p>341</p></td>
</tr>
<tr class="row-even"><td class="text-left"><p>llama_70b</p></td>
<td class="text-left"><p>32</p></td>
<td class="text-left"><p>1</p></td>
<td class="text-left"><p>2048</p></td>
<td class="text-left"><p>128</p></td>
<td class="text-right"><p>303</p></td>
</tr>
</tbody>
</table>
<p><sub>Preliminary measured performance, subject to change. TensorRT-LLM v0.5.0, TensorRT v9.1.0.4 | H200, H100 FP8. </sub></p>
<p><sup><em>(1) Largest batch supported on given TP configuration by power of 2.</em></sup> <sup><em>(2) TP = Tensor Parallelism</em></sup></p>
<p>Additional Performance data is available on the <a class="reference external" href="https://developer.nvidia.com/deep-learning-performance-training-inference/ai-inference">NVIDIA Data Center Deep Learning Product Performance</a> page, &amp; soon in <a class="reference external" href="https://nvidia.github.io/TensorRT-LLM/performance.html">TensorRT-LLM’s Performance Documentation</a>.</p>
<section id="h200-vs-h100">
<h2>H200 vs H100<a class="headerlink" href="#h200-vs-h100" title="Link to this heading"></a></h2>
<p>H200’s HBM3e larger capacity &amp; faster memory enables up to <strong>1.9x</strong> performance on LLMs compared to H100. Max throughput improves due to its dependence on memory capacity and bandwidth, benefitting from the new HBM3e. First token latency is compute bound for most ISLs, meaning H200 retains similar time to first token as H100.</p>
<p>For practical examples of H200’s performance:</p>
<p><strong>Max Throughput TP1:</strong>
an offline summarization scenario (ISL/OSL=2048/128) with Llama-70B on a single H200 is 1.9x more performant than H100.</p>
<p><strong>Max Throughput TP8:</strong>
an online chat agent scenario (ISL/OSL=80/200) with GPT3-175B on a full HGX (TP8) H200 is 1.6x more performant than H100.</p>
<img src="https://github.com/NVIDIA/TensorRT-LLM/blob/rel/docs/source/blogs/media/H200launch_tps.png?raw=true" alt="H200 TPS" width="500" height="auto">
<p><sub>Preliminary measured performance, subject to change.
TensorRT-LLM v0.5.0, TensorRT v9.1.0.4. | Llama-70B: H100 FP8 BS 8, H200 FP8 BS 32 | GPT3-175B: H100 FP8 BS 64, H200 FP8 BS 128 </sub></p>
<p><strong>Max Throughput across TP/BS:</strong>
Max throughput<sup>(3)</sup> on H200 vs H100 varies by model, sequence lengths, BS, and TP. Below results shown for maximum throughput per GPU across all these variables.</p>
<img src="https://github.com/NVIDIA/TensorRT-LLM/blob/rel/docs/source/blogs/media/H200launch_H200vsH100_tps.png?raw=true" alt="max throughput llama sweep" width="500" height="auto">
<p><sub>Preliminary measured performance, subject to change.
TensorRT-LLM v0.5.0, TensorRT v9.1.0.4 | H200, H100 FP8. </sub></p>
<p><sup><em>(3) Max Throughput per GPU is defined as the highest tok/s per GPU, swept across TP configurations &amp; BS powers of 2.</em></sup></p>
</section>
<section id="latest-hbm-memory">
<h2>Latest HBM Memory<a class="headerlink" href="#latest-hbm-memory" title="Link to this heading"></a></h2>
<p>H200 is the newest addition to NVIDIA’s data center GPU portfolio. To maximize that compute performance, H200 is the first GPU with HBM3e memory with 4.8TB/s of memory bandwidth, a 1.4X increase over H100. H200 also expands GPU memory capacity nearly 2X to 141 gigabytes (GB). The combination of faster and larger HBM memory accelerates performance of LLM model inference performance with faster throughput and tokens per second. These results are measured and preliminary, more updates expected as optimizations for H200 continue with TensorRT-LLM.</p>
</section>
</section>
</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="H100vsA100.html" class="btn btn-neutral float-left" title="H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
<a href="Falcon180B-H200.html" class="btn btn-neutral float-right" title="Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100" 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 0x7f1ac76d36e0>
<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