mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
130807da9f
* Update docs * Update windows install version Update gh pages (#2741) update gh pages (#2743) gh pages update (#2746) Update gh-pages (#2764) Update
327 lines
26 KiB
HTML
327 lines
26 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>PyTorch Backend — 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=9a2dae69"></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="Release Notes" href="release-notes.html" />
|
|
<link rel="prev" title="Key Features" href="key-features.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 class="current">
|
|
<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 current"><a class="current reference internal" href="#">PyTorch Backend</a><ul>
|
|
<li class="toctree-l2"><a class="reference internal" href="#quick-start">Quick Start</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="#quantization">Quantization</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="#developer-guide">Developer Guide</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="#key-components">Key Components</a></li>
|
|
</ul>
|
|
</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/performance-tuning-guide/index.html">Performance Tuning Guide</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>
|
|
<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">PyTorch Backend</li>
|
|
<li class="wy-breadcrumbs-aside">
|
|
<a href="_sources/torch.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="pytorch-backend">
|
|
<h1>PyTorch Backend<a class="headerlink" href="#pytorch-backend" title="Link to this heading"></a></h1>
|
|
<div class="admonition note">
|
|
<p class="admonition-title">Note</p>
|
|
<p>Note:
|
|
This feature is currently experimental, and the related API is subjected to change in future versions.</p>
|
|
</div>
|
|
<p>To enhance the usability of the system and improve developer efficiency, TensorRT-LLM launches a new experimental backend based on PyTorch.</p>
|
|
<p>The PyTorch backend of TensorRT-LLM is available in version 0.17 and later. You can try it via importing <code class="docutils literal notranslate"><span class="pre">tensorrt_llm._torch</span></code>.</p>
|
|
<section id="quick-start">
|
|
<h2>Quick Start<a class="headerlink" href="#quick-start" title="Link to this heading"></a></h2>
|
|
<p>Here is a simple example to show how to use <code class="docutils literal notranslate"><span class="pre">tensorrt_llm._torch.LLM</span></code> API with Llama model.</p>
|
|
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="kn">import</span> <span class="nn">argparse</span>
|
|
<span class="linenos"> 2</span>
|
|
<span class="linenos"> 3</span><span class="kn">from</span> <span class="nn">tensorrt_llm</span> <span class="kn">import</span> <span class="n">SamplingParams</span>
|
|
<span class="linenos"> 4</span><span class="kn">from</span> <span class="nn">tensorrt_llm._torch</span> <span class="kn">import</span> <span class="n">LLM</span>
|
|
<span class="linenos"> 5</span><span class="kn">from</span> <span class="nn">tensorrt_llm._torch.pyexecutor.config</span> <span class="kn">import</span> <span class="n">PyTorchConfig</span>
|
|
<span class="linenos"> 6</span>
|
|
<span class="linenos"> 7</span>
|
|
<span class="linenos"> 8</span><span class="k">def</span> <span class="nf">parse_arguments</span><span class="p">():</span>
|
|
<span class="linenos"> 9</span> <span class="n">parser</span> <span class="o">=</span> <span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentParser</span><span class="p">()</span>
|
|
<span class="linenos">10</span> <span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s1">'--model_dir'</span><span class="p">,</span>
|
|
<span class="linenos">11</span> <span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span>
|
|
<span class="linenos">12</span> <span class="n">default</span><span class="o">=</span><span class="s1">'meta-llama/Llama-3.1-8B-Instruct'</span><span class="p">)</span>
|
|
<span class="linenos">13</span> <span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s1">'--tp_size'</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
|
|
<span class="linenos">14</span> <span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s1">'--enable_overlap_scheduler'</span><span class="p">,</span>
|
|
<span class="linenos">15</span> <span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
|
<span class="linenos">16</span> <span class="n">action</span><span class="o">=</span><span class="s1">'store_true'</span><span class="p">)</span>
|
|
<span class="linenos">17</span> <span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s1">'--enable_chunked_prefill'</span><span class="p">,</span>
|
|
<span class="linenos">18</span> <span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
|
<span class="linenos">19</span> <span class="n">action</span><span class="o">=</span><span class="s1">'store_true'</span><span class="p">)</span>
|
|
<span class="linenos">20</span> <span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s1">'--kv_cache_dtype'</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="s1">'auto'</span><span class="p">)</span>
|
|
<span class="linenos">21</span> <span class="n">args</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">parse_args</span><span class="p">()</span>
|
|
<span class="linenos">22</span> <span class="k">return</span> <span class="n">args</span>
|
|
<span class="linenos">23</span>
|
|
<span class="linenos">24</span>
|
|
<span class="linenos">25</span><span class="k">def</span> <span class="nf">main</span><span class="p">():</span>
|
|
<span class="linenos">26</span> <span class="n">args</span> <span class="o">=</span> <span class="n">parse_arguments</span><span class="p">()</span>
|
|
<span class="linenos">27</span>
|
|
<span class="linenos">28</span> <span class="n">pytorch_config</span> <span class="o">=</span> <span class="n">PyTorchConfig</span><span class="p">(</span>
|
|
<span class="linenos">29</span> <span class="n">enable_overlap_scheduler</span><span class="o">=</span><span class="n">args</span><span class="o">.</span><span class="n">enable_overlap_scheduler</span><span class="p">,</span>
|
|
<span class="linenos">30</span> <span class="n">kv_cache_dtype</span><span class="o">=</span><span class="n">args</span><span class="o">.</span><span class="n">kv_cache_dtype</span><span class="p">)</span>
|
|
<span class="linenos">31</span> <span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span><span class="n">model</span><span class="o">=</span><span class="n">args</span><span class="o">.</span><span class="n">model_dir</span><span class="p">,</span>
|
|
<span class="linenos">32</span> <span class="n">tensor_parallel_size</span><span class="o">=</span><span class="n">args</span><span class="o">.</span><span class="n">tp_size</span><span class="p">,</span>
|
|
<span class="linenos">33</span> <span class="n">enable_chunked_prefill</span><span class="o">=</span><span class="n">args</span><span class="o">.</span><span class="n">enable_chunked_prefill</span><span class="p">,</span>
|
|
<span class="linenos">34</span> <span class="n">pytorch_backend_config</span><span class="o">=</span><span class="n">pytorch_config</span><span class="p">)</span>
|
|
<span class="linenos">35</span>
|
|
<span class="linenos">36</span> <span class="n">prompts</span> <span class="o">=</span> <span class="p">[</span>
|
|
<span class="linenos">37</span> <span class="s2">"Hello, my name is"</span><span class="p">,</span>
|
|
<span class="linenos">38</span> <span class="s2">"The president of the United States is"</span><span class="p">,</span>
|
|
<span class="linenos">39</span> <span class="s2">"The capital of France is"</span><span class="p">,</span>
|
|
<span class="linenos">40</span> <span class="s2">"The future of AI is"</span><span class="p">,</span>
|
|
<span class="linenos">41</span> <span class="p">]</span>
|
|
<span class="linenos">42</span> <span class="n">sampling_params</span> <span class="o">=</span> <span class="n">SamplingParams</span><span class="p">(</span><span class="n">max_tokens</span><span class="o">=</span><span class="mi">32</span><span class="p">)</span>
|
|
<span class="linenos">43</span>
|
|
<span class="linenos">44</span> <span class="n">outputs</span> <span class="o">=</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate</span><span class="p">(</span><span class="n">prompts</span><span class="p">,</span> <span class="n">sampling_params</span><span class="p">)</span>
|
|
<span class="linenos">45</span> <span class="c1"># Print the outputs.</span>
|
|
<span class="linenos">46</span> <span class="k">for</span> <span class="n">output</span> <span class="ow">in</span> <span class="n">outputs</span><span class="p">:</span>
|
|
<span class="linenos">47</span> <span class="n">prompt</span> <span class="o">=</span> <span class="n">output</span><span class="o">.</span><span class="n">prompt</span>
|
|
<span class="linenos">48</span> <span class="n">generated_text</span> <span class="o">=</span> <span class="n">output</span><span class="o">.</span><span class="n">outputs</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">text</span>
|
|
<span class="linenos">49</span> <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Prompt: </span><span class="si">{</span><span class="n">prompt</span><span class="si">!r}</span><span class="s2">, Generated text: </span><span class="si">{</span><span class="n">generated_text</span><span class="si">!r}</span><span class="s2">"</span><span class="p">)</span>
|
|
<span class="linenos">50</span>
|
|
<span class="linenos">51</span>
|
|
<span class="linenos">52</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
|
|
<span class="linenos">53</span> <span class="n">main</span><span class="p">()</span>
|
|
</pre></div>
|
|
</div>
|
|
</section>
|
|
<section id="quantization">
|
|
<h2>Quantization<a class="headerlink" href="#quantization" title="Link to this heading"></a></h2>
|
|
<p>The PyTorch backend supports FP8 and NVFP4 quantization. You can pass quantized models in HF model hub,
|
|
which are generated by <a class="reference external" href="https://github.com/NVIDIA/TensorRT-Model-Optimizer">TensorRT Model Optimizer</a>.</p>
|
|
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">tensorrt_llm._torch</span> <span class="kn">import</span> <span class="n">LLM</span>
|
|
<span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span><span class="n">model</span><span class="o">=</span><span class="s1">'nvidia/Llama-3.1-8B-Instruct-FP8'</span><span class="p">)</span>
|
|
<span class="n">llm</span><span class="o">.</span><span class="n">generate</span><span class="p">(</span><span class="s2">"Hello, my name is"</span><span class="p">)</span>
|
|
</pre></div>
|
|
</div>
|
|
<p>Or you can try the following commands to get a quantized model by yourself:</p>
|
|
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>git<span class="w"> </span>clone<span class="w"> </span>https://github.com/NVIDIA/TensorRT-Model-Optimizer.git
|
|
<span class="nb">cd</span><span class="w"> </span>TensorRT-Model-Optimizer/llm_ptq
|
|
scripts/huggingface_example.sh<span class="w"> </span>--model<span class="w"> </span><huggingface_model_card><span class="w"> </span>--quant<span class="w"> </span>fp8<span class="w"> </span>--export_fmt<span class="w"> </span>hf
|
|
</pre></div>
|
|
</div>
|
|
</section>
|
|
<section id="developer-guide">
|
|
<h2>Developer Guide<a class="headerlink" href="#developer-guide" title="Link to this heading"></a></h2>
|
|
<ul class="simple">
|
|
<li><p><a class="reference internal" href="torch/arch_overview.html"><span class="std std-doc">Architecture Overview</span></a></p></li>
|
|
<li><p><a class="reference internal" href="torch/adding_new_model.html"><span class="std std-doc">Adding a New Model</span></a></p></li>
|
|
</ul>
|
|
</section>
|
|
<section id="key-components">
|
|
<h2>Key Components<a class="headerlink" href="#key-components" title="Link to this heading"></a></h2>
|
|
<ul class="simple">
|
|
<li><p><a class="reference internal" href="torch/attention.html"><span class="std std-doc">Attention</span></a></p></li>
|
|
<li><p><a class="reference internal" href="torch/kv_cache_manager.html"><span class="std std-doc">KV Cache Manager</span></a></p></li>
|
|
<li><p><a class="reference internal" href="torch/scheduler.html"><span class="std std-doc">Scheduler</span></a></p></li>
|
|
</ul>
|
|
</section>
|
|
</section>
|
|
|
|
|
|
</div>
|
|
</div>
|
|
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
|
|
<a href="key-features.html" class="btn btn-neutral float-left" title="Key Features" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
|
|
<a href="release-notes.html" class="btn btn-neutral float-right" title="Release Notes" 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 0x7fa25b6e3950>
|
|
|
|
<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> |