mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
6528 lines
1.4 MiB
6528 lines
1.4 MiB
<!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>Runtime — tensorrt_llm documentation</title>
|
||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=80d5e7a1" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/css/theme.css?v=19f00094" />
|
||
|
||
|
||
<!--[if lt IE 9]>
|
||
<script src="../_static/js/html5shiv.min.js"></script>
|
||
<![endif]-->
|
||
|
||
<script src="../_static/jquery.js?v=5d32c60e"></script>
|
||
<script src="../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
|
||
<script src="../_static/documentation_options.js?v=5929fcd5"></script>
|
||
<script src="../_static/doctools.js?v=888ff710"></script>
|
||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||
<script src="../_static/js/theme.js"></script>
|
||
<link rel="index" title="Index" href="../genindex.html" />
|
||
<link rel="search" title="Search" href="../search.html" />
|
||
<link rel="next" title="H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token" href="../blogs/H100vsA100.html" />
|
||
<link rel="prev" title="Runtime" href="../python-api/tensorrt_llm.runtime.html" />
|
||
</head>
|
||
|
||
<body class="wy-body-for-nav">
|
||
<div class="wy-grid-for-nav">
|
||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||
<div class="wy-side-scroll">
|
||
<div class="wy-side-nav-search" >
|
||
|
||
|
||
|
||
<a href="../index.html" class="icon icon-home">
|
||
tensorrt_llm
|
||
</a>
|
||
<div role="search">
|
||
<form id="rtd-search-form" class="wy-form" action="../search.html" method="get">
|
||
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
|
||
<input type="hidden" name="check_keywords" value="yes" />
|
||
<input type="hidden" name="area" value="default" />
|
||
</form>
|
||
</div>
|
||
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
|
||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference internal" href="../architecture.html">TensorRT-LLM Architecture</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../gpt_runtime.html">C++ GPT Runtime</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../batch_manager.html">The Batch Manager in TensorRT-LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../gpt_attention.html">Multi-head, Multi-query and Group-query Attention</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../precision.html">Numerical Precision</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../installation.html">TensorRT-LLM Installation</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../performance.html">Performance of TensorRT-LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../2023-05-19-how-to-debug.html">How to debug</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../2023-05-17-how-to-add-a-new-model.html">How to add a new model</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../graph-rewriting.html">Graph Rewriting Module</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../memory.html">Memory Usage of TensorRT-LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../new_workflow.html">New Workflow</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">Python API</span></p>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.layers.html">Layers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.functional.html">Functionals</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.models.html">Models</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.plugin.html">Plugin</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.quantization.html">Quantization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.runtime.html">Runtime</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">C++ API</span></p>
|
||
<ul class="current">
|
||
<li class="toctree-l1 current"><a class="current reference internal" href="#">Runtime</a><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="#buffermanager-h">bufferManager.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv412tensorrt_llm"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#common-h">common.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SizeType</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TokenIdTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TokenIdType</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime12StringPtrMapE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::StringPtrMap</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#cudaevent-h">cudaEvent.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaEvent</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaEvent::pointer</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventEj"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaEvent::CudaEvent()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaEvent::CudaEvent()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime9CudaEvent3getEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaEvent::get()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime9CudaEvent11synchronizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaEvent::synchronize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent12element_typeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaEvent::element_type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent8EventPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaEvent::EventPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent6mEventE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaEvent::mEvent</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7DeleterE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaEvent::Deleter</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#cudastream-h">cudaStream.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStreamE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::CudaStream()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::CudaStream()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream9getDeviceEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::getDevice()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream3getEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::get()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream11synchronizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::synchronize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::record()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::record()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::wait()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::wait()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream9StreamPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::StreamPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream7mStreamE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::mStream</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream7mDeviceE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::mDevice</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream7DeleterE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::CudaStream::Deleter</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#decodinginput-h">decodingInput.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputE8SizeType8SizeType8SizeType9TensorPtr9TensorPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::DecodingInput()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput4stepE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::step</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9maxLengthE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::maxLength</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput18maxAttentionWindowE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::maxAttentionWindow</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9batchSizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::batchSize</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput6logitsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::logits</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput6endIdsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::endIds</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput8finishedE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::finished</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput19sequenceLimitLengthE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::sequenceLimitLength</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput13embeddingBiasE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::embeddingBias</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput7lengthsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::lengths</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsListE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::badWordsList</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsListE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::stopWordsList</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput17noRepeatNgramSizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::noRepeatNgramSize</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput16cacheIndirectionE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingInput::cacheIndirection</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#decodingoutput-h">decodingOutput.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputE9TensorPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::DecodingOutput()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput3idsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::ids</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14newTokensStepsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::newTokensSteps</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9newTokensE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::newTokens</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput12newTokensVecE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::newTokensVec</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput8finishedE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::finished</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput11finishedSumE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::finishedSum</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput8logProbsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::logProbs</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput11cumLogProbsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::cumLogProbs</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9parentIdsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::parentIds</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput7lengthsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::lengths</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput16cacheIndirectionE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::cacheIndirection</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14beamHypothesesE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::beamHypotheses</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput17kNegativeInfinityE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::kNegativeInfinity</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DecodingOutput::BeamHypotheses</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#generationinput-h">generationInput.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I00EN12tensorrt_llm7runtime22GenericGenerationInputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput22GenericGenerationInputEK8SizeTypeK8SizeType9TensorPtr9TensorPtrb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput::GenericGenerationInput()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput5endIdE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput::endId</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput5padIdE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput::padId</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput3idsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput::ids</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput7lengthsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput::lengths</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput6packedE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput::packed</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput13embeddingBiasE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput::embeddingBias</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput12badWordsListE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput::badWordsList</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput13stopWordsListE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput::stopWordsList</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput12maxNewTokensE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput::maxNewTokens</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput18promptTuningParamsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationInput::promptTuningParams</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenerationInput</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInput4BaseE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenerationInput::Base</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInput9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenerationInput::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInput15GenerationInputEK8SizeTypeK8SizeType9TensorPtr9TensorPtrb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenerationInput::GenerationInput()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#generationoutput-h">generationOutput.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime23GenericGenerationOutputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationOutput</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationOutput::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput8CallbackE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationOutput::Callback</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput23GenericGenerationOutputE9TensorPtr9TensorPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationOutput::GenericGenerationOutput()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput3idsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationOutput::ids</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput7lengthsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationOutput::lengths</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput11cumLogProbsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationOutput::cumLogProbs</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput8logProbsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationOutput::logProbs</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput13contextLogitsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationOutput::contextLogits</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput16generationLogitsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationOutput::generationLogits</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput16onTokenGeneratedE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericGenerationOutput::onTokenGenerated</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenerationOutput</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutput4BaseE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenerationOutput::Base</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutput9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenerationOutput::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutput16GenerationOutputE9TensorPtr9TensorPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenerationOutput::GenerationOutput()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#gptdecoder-h">gptDecoder.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm6layersE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::layers</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoderE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoder</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoderD0Ev"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoder::~IGptDecoder()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_t8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoder::setup()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder7forwardER14DecodingOutputRK13DecodingInput"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoder::forward()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoder::forwardAsync()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder10gatherTreeER7ITensorRK14DecodingOutputRK13DecodingInputRK13BufferManager"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoder::gatherTree()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder17getSamplingConfigEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoder::getSamplingConfig()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRKN13BufferManager13CudaStreamPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensor8SizeType8SizeTypebfP13curandState_tRKN13BufferManager13CudaStreamPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createEN8nvinfer18DataTypeE6size_t6size_tRKN13BufferManager13CudaStreamPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoder::create()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime10GptDecoderE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder13CudaStreamPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::CudaStreamPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderE6size_t6size_tRK13CudaStreamPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::GptDecoder()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_t8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::setup()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder7forwardER14DecodingOutputRK13DecodingInput"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::forward()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::forwardAsync()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder10gatherTreeER7ITensorRK14DecodingOutputRK13DecodingInputRK13BufferManager"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::gatherTree()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder17getSamplingConfigEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::getSamplingConfig()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder8mManagerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::mManager</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder10mAllocatorE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::mAllocator</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder19mDynamicDecodeLayerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::mDynamicDecodeLayer</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder14mLogProbsTiledE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::mLogProbsTiled</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder15mSamplingConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoder::mSamplingConfig</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#gptdecoderbatch-h">gptDecoderBatch.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatchE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13CudaStreamPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::CudaStreamPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch15GptDecoderBatchENSt6size_tENSt6size_tE13CudaStreamPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::GptDecoderBatch()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch5setupE8SizeType8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::setup()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch10newRequestE8SizeTypeRKN13decoder_batch7RequestERK14SamplingConfig"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::newRequest()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::newBatch()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::forwardAsync()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch11forwardSyncERKN13decoder_batch5TokenE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::forwardSync()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12forwardAsyncERN7decoder6OutputERKN7decoder5InputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::forwardAsync()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch11forwardSyncEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::forwardSync()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch11getFinishedEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::getFinished()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch12getOutputIdsE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::getOutputIds()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch12getOutputIdsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::getOutputIds()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch8finalizeE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::finalize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch8finalizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::finalize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch12getParentIdsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::getParentIds()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch14getCumLogProbsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::getCumLogProbs()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch14getCumLogProbsE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::getCumLogProbs()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch11getLogProbsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::getLogProbs()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch11getLogProbsE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::getLogProbs()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch15getAllNewTokensEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::getAllNewTokens()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch12getNewTokensE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::getNewTokens()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch10getNbStepsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::getNbSteps()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch13getNbFinishedEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::getNbFinished()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13GptDecoderPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::GptDecoderPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16DecodingInputPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::DecodingInputPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch17DecodingOutputPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::DecodingOutputPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch18postProcessRequestE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::postProcessRequest()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch10mVocabSizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mVocabSize</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16mVocabSizePaddedE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mVocabSizePadded</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch7mStreamE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mStream</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch14mBufferManagerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mBufferManager</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13mForwardTokenE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mForwardToken</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13mForwardEventE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mForwardEvent</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch8mStreamsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mStreams</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9mDecodersE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mDecoders</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch15mDecodingInputsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mDecodingInputs</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16mDecodingOutputsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mDecodingOutputs</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch19mJointDecodingInputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mJointDecodingInput</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch20mJointDecodingOutputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mJointDecodingOutput</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch14mDraftTokenIdsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mDraftTokenIds</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12mDraftLogitsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mDraftLogits</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch15mAcceptByLogitsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mAcceptByLogits</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch15mNumDraftTokensE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mNumDraftTokens</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13mCurandStatesE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mCurandStates</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch8mNbStepsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mNbSteps</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9mFinishedE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mFinished</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12mFinishedSumE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mFinishedSum</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13mMaxNewTokensE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mMaxNewTokens</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch11mBeamWidthsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mBeamWidths</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch23mGeneratedTokensPerStepE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mGeneratedTokensPerStep</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch14mFinishedStepsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mFinishedSteps</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch11mDraftProbsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mDraftProbs</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12mTargetProbsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mTargetProbs</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch18mMaxSequenceLengthE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mMaxSequenceLength</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch19mMaxAttentionWindowE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mMaxAttentionWindow</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16mActualBatchSizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mActualBatchSize</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch17mMaxTokensPerStepE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptDecoderBatch::mMaxTokensPerStep</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#gptjsonconfig-h">gptJsonConfig.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE8SizeType8SizeTypeRK14GptModelConfig"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getModelConfigEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::getModelConfig()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig7getNameEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::getName()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig10getVersionEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::getVersion()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getPrecisionEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::getPrecision()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig20getTensorParallelismEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::getTensorParallelism()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig22getPipelineParallelismEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::getPipelineParallelism()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getWorldSizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::getWorldSize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::engineFilename()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::engineFilename()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::parse()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::parse()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::parse()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5mNameE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::mName</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig8mVersionE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::mVersion</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig10mPrecisionE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::mPrecision</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig18mTensorParallelismE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::mTensorParallelism</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig20mPipelineParallelismE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::mPipelineParallelism</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig15mGptModelConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptJsonConfig::mGptModelConfig</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#gptmodelconfig-h">gptModelConfig.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12ModelVariantE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::ModelVariant</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig14GptModelConfigE8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::GptModelConfig()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig12getVocabSizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getVocabSize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig18getVocabSizePaddedE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getVocabSizePadded()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig11getNbLayersE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getNbLayers()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig10getNbHeadsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getNbHeads()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig12getNbKvHeadsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getNbKvHeads()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12setNbKvHeadsE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setNbKvHeads()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig13getHiddenSizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getHiddenSize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig14getSizePerHeadEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getSizePerHead()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig11getDataTypeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getDataType()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig21useGptAttentionPluginEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::useGptAttentionPlugin()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig21useGptAttentionPluginEb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::useGptAttentionPlugin()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig14usePackedInputEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::usePackedInput()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig14usePackedInputEb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::usePackedInput()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15usePagedKvCacheEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::usePagedKvCache()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15usePagedKvCacheEb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::usePagedKvCache()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig17getTokensPerBlockEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getTokensPerBlock()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig17setTokensPerBlockE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setTokensPerBlock()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig12getQuantModeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getQuantMode()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12setQuantModeEN6common9QuantModeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setQuantMode()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig24supportsInflightBatchingEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::supportsInflightBatching()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getMaxBatchSizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getMaxBatchSize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setMaxBatchSizeE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setMaxBatchSize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getMaxBeamWidthEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getMaxBeamWidth()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setMaxBeamWidthE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setMaxBeamWidth()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig14getMaxInputLenEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getMaxInputLen()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig14setMaxInputLenE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setMaxInputLen()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getMaxOutputLenEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getMaxOutputLen()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setMaxOutputLenE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setMaxOutputLen()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getMaxNumTokensEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getMaxNumTokens()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setMaxNumTokensENSt8optionalI8SizeTypeEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setMaxNumTokens()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15usePromptTuningEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::usePromptTuning()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig30getMaxPromptEmbeddingTableSizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getMaxPromptEmbeddingTableSize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig30setMaxPromptEmbeddingTableSizeE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setMaxPromptEmbeddingTableSize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig20computeContextLogitsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::computeContextLogits()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig20computeContextLogitsEb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::computeContextLogits()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig23computeGenerationLogitsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::computeGenerationLogits()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig23computeGenerationLogitsEb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::computeGenerationLogits()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getModelVariantEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getModelVariant()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setModelVariantE12ModelVariant"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setModelVariant()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig18useCustomAllReduceEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::useCustomAllReduce()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig18useCustomAllReduceEb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::useCustomAllReduce()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig14setMaxDraftLenE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setMaxDraftLen()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig14getMaxDraftLenEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getMaxDraftLen()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig19getMaxTokensPerStepEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getMaxTokensPerStep()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig30setUseContextFMHAForGenerationEb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setUseContextFMHAForGeneration()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig27getContextFMHAForGenerationEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getContextFMHAForGeneration()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig19setPagedContextFMHAEb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::setPagedContextFMHA()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig19getPagedContextFMHAEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::getPagedContextFMHA()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig10mVocabSizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mVocabSize</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig9mNbLayersE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mNbLayers</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig8mNbHeadsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mNbHeads</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig10mNbKvHeadsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mNbKvHeads</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig11mHiddenSizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mHiddenSize</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig9mDataTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mDataType</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig22mUseGptAttentionPluginE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mUseGptAttentionPlugin</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12mInputPackedE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mInputPacked</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mPagedKvCacheE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mPagedKvCache</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15mTokensPerBlockE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mTokensPerBlock</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig10mQuantModeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mQuantMode</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mMaxBatchSizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mMaxBatchSize</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mMaxBeamWidthE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mMaxBeamWidth</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12mMaxInputLenE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mMaxInputLen</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mMaxOutputLenE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mMaxOutputLen</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mMaxNumTokensE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mMaxNumTokens</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig21mComputeContextLogitsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mComputeContextLogits</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig24mComputeGenerationLogitsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mComputeGenerationLogits</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mModelVariantE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mModelVariant</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig19mUseCustomAllReduceE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mUseCustomAllReduce</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig28mMaxPromptEmbeddingTableSizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mMaxPromptEmbeddingTableSize</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12mMaxDraftLenE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mMaxDraftLen</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig28mUseContextFMHAForGenerationE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mUseContextFMHAForGeneration</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig17mPagedContextFMHAE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptModelConfig::mPagedContextFMHA</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#gptsession-h">gptSession.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm13batch_managerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::batch_manager</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm13batch_manager16kv_cache_managerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::batch_manager::kv_cache_manager</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSessionE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession9LoggerPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::LoggerPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::GptSession()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigRKNSt6vectorI7uint8_tEE9LoggerPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::GptSession()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigRKNSt6stringE9LoggerPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::GptSession()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession9getLoggerEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::getLogger()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession16getBufferManagerEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::getBufferManager()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession14getModelConfigEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::getModelConfig()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession14getWorldConfigEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::getWorldConfig()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession9getDeviceEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::getDevice()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession8generateER16GenerationOutputRK15GenerationInputRK14SamplingConfig"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::generate()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14KvCacheManagerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::KvCacheManager</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession13KvCacheConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::KvCacheConfig</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession22TokenGeneratedCallbackE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::TokenGeneratedCallback</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession13useCudaGraphsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::useCudaGraphs()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession15generateBatchedERNSt6vectorI16GenerationOutputEERKNSt6vectorI15GenerationInputEERK14SamplingConfigRK22TokenGeneratedCallback"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::generateBatched()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession5setupERK6Config"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::setup()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14createContextsE8SizeType8SizeTypeb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::createContexts()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession13createBuffersE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::createBuffers()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeEb8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::createDecoders()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE8SizeType8SizeType8SizeType8SizeTypeRK13KvCacheConfig"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::createKvCacheManager()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession30createCustomAllReduceWorkspaceE8SizeType8SizeType8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::createCustomAllReduceWorkspace()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession18executeContextStepERKNSt6vectorI15GenerationInputEERKNSt6vectorI8SizeTypeEEPK14KvCacheManager"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::executeContextStep()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession21executeGenerationStepE8SizeTypeRKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI8SizeTypeEEP14KvCacheManagerRNSt6vectorIbEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::executeGenerationStep()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession16decoderStepAsyncE8SizeType8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::decoderStepAsync()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14shouldStopSyncE8SizeType8SizeType8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::shouldStopSync()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession8finalizeE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::finalize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession19kvCacheAddSequencesE8SizeType8SizeType8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::kvCacheAddSequences()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession11initDecoderER7ITensorRK15GenerationInputRK16GenerationOutputRK14SamplingConfig8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::initDecoder()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession30createOnTokenGeneratedCallbackER16GenerationOutput"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::createOnTokenGeneratedCallback()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession12mModelConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mModelConfig</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession12mWorldConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mWorldConfig</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession7mDeviceE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mDevice</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession13mPipelineCommE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mPipelineComm</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession11mCommStreamE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mCommStream</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession10mCommEventE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mCommEvent</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession9mCommPtrsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mCommPtrs</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17mIpcMemoryHandlesE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mIpcMemoryHandles</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession25mDecoderMaxSequenceLengthE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mDecoderMaxSequenceLength</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession26mDecoderMaxAttentionWindowE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mDecoderMaxAttentionWindow</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession7mLoggerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mLogger</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession8mRuntimeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mRuntime</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession15mKvCacheManagerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mKvCacheManager</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17mMicroBatchConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mMicroBatchConfig</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession9mDecodersE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mDecoders</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession8mBuffersE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mBuffers</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession15mReceivedEventsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mReceivedEvents</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14mCudaGraphModeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mCudaGraphMode</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession19mCudaGraphInstancesE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::mCudaGraphInstances</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6ConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::Config</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::CudaGraphExecutor</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GptSession::MicroBatchConfig</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime5utilsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::utils</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime5utils10loadEngineERKNSt6stringE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::utils::loadEngine()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#ibuffer-h">iBuffer.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEEE"><code class="docutils literal notranslate"><span class="pre">MemoryTypeString</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEE5valueE"><code class="docutils literal notranslate"><span class="pre">MemoryTypeString::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEEE"><code class="docutils literal notranslate"><span class="pre">MemoryTypeString</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEE5valueE"><code class="docutils literal notranslate"><span class="pre">MemoryTypeString::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEEE"><code class="docutils literal notranslate"><span class="pre">MemoryTypeString</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEE5valueE"><code class="docutils literal notranslate"><span class="pre">MemoryTypeString::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEEE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4typeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4nameE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::name</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4sizeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::size</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEEE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4typeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4nameE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::name</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4sizeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::size</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EEE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4typeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4nameE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::name</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4sizeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::size</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EEE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4typeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4nameE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::name</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4sizeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::size</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EEE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4typeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4nameE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::name</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4sizeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::size</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEEE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4typeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4nameE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::name</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4sizeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::size</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEEE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4typeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4nameE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::name</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4sizeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::size</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4typeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4nameE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::name</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4sizeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::size</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4typeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4nameE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::name</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4sizeE"><code class="docutils literal notranslate"><span class="pre">DataTypeTraits::size</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEEE"><code class="docutils literal notranslate"><span class="pre">TRTDataType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEE5valueE"><code class="docutils literal notranslate"><span class="pre">TRTDataType::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEEE"><code class="docutils literal notranslate"><span class="pre">TRTDataType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEE5valueE"><code class="docutils literal notranslate"><span class="pre">TRTDataType::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEEE"><code class="docutils literal notranslate"><span class="pre">TRTDataType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEE5valueE"><code class="docutils literal notranslate"><span class="pre">TRTDataType::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEEE"><code class="docutils literal notranslate"><span class="pre">TRTDataType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEE5valueE"><code class="docutils literal notranslate"><span class="pre">TRTDataType::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEEE"><code class="docutils literal notranslate"><span class="pre">TRTDataType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEE5valueE"><code class="docutils literal notranslate"><span class="pre">TRTDataType::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEEE"><code class="docutils literal notranslate"><span class="pre">TRTDataType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEE5valueE"><code class="docutils literal notranslate"><span class="pre">TRTDataType::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::PointerElementType</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryType4kGPUE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryType::kGPU</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryType4kCPUE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryType::kCPU</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryType7kPINNEDE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryType::kPINNED</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::constPointerCast()</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::constPointerCast()</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::bufferCast()</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::bufferCast()</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::operator<<()</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryTypeString</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::PhonyNameDueToError::value</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DataTypeTraits</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::PhonyNameDueToError::type</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::PhonyNameDueToError::name</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::PhonyNameDueToError::size</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DataTypeTraits</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4typeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DataTypeTraits::type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4nameE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DataTypeTraits::name</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4sizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::DataTypeTraits::size</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferDataType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferDataType::BufferDataType()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14BufferDataTypecvN8nvinfer18DataTypeEEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferDataType::operator</span> <span class="pre">nvinfer1::DataType()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14BufferDataType11getDataTypeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferDataType::getDataType()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14BufferDataType9isPointerEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferDataType::isPointer()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14BufferDataType10isUnsignedEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferDataType::isUnsigned()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14BufferDataType7getSizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferDataType::getSize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataType15kTrtPointerTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferDataType::kTrtPointerType</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataType9mDataTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferDataType::mDataType</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataType9mUnsignedE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferDataType::mUnsigned</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataType8mPointerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferDataType::mPointer</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I0_bEN12tensorrt_llm7runtime11TRTDataTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TRTDataType</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIfEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TRTDataType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIfE5valueE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TRTDataType::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeI4halfEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TRTDataType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeI4halfE5valueE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TRTDataType::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIbEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TRTDataType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIbE5valueE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TRTDataType::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIPvEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TRTDataType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIPvE5valueE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TRTDataType::value</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TRTDataType</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE5valueE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TRTDataType::value</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TRTDataType::kUnderlyingType</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::UniquePtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::SharedPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::UniqueConstPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer14SharedConstPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::SharedConstPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer8DataTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::DataType</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer4dataEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::data()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::data()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::data()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::data()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer7getSizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::getSize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer14getSizeInBytesEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::getSizeInBytes()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer11getCapacityEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::getCapacity()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer11getDataTypeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::getDataType()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer15getDataTypeNameEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::getDataTypeName()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer13getMemoryTypeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::getMemoryType()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer17getMemoryTypeNameEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::getMemoryTypeName()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::resize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer7releaseEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::release()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferD0Ev"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::~IBuffer()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferERK7IBuffer"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::IBuffer()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferaSERK7IBuffer"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::operator=()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::slice()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::slice()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::slice()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::slice()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::view()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::view()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::view()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::wrap()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::wrap()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::wrap()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::wrap()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::wrap()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::memoryType()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::IBuffer()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IBuffer::toBytes()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange10value_typeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::value_type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange9size_typeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::size_type</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange9referenceE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::reference</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange15const_referenceE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::const_reference</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange7pointerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::pointer</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange13const_pointerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::const_pointer</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange8iteratorE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::iterator</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange14const_iteratorE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::const_iterator</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::BufferRange()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange5beginEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::begin()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange3endEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::end()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11BufferRange5beginEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::begin()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11BufferRange3endEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::end()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange6cbeginEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::cbegin()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange4cendEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::cend()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11BufferRange6cbeginEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::cbegin()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11BufferRange4cendEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::cend()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11BufferRange4sizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::size()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRangeixE9size_type"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::operator[]()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11BufferRangeixE9size_type"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::operator[]()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange5mDataE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::mData</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange5mSizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::BufferRange::mSize</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#igptdecoderbatch-h">iGptDecoderBatch.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatchE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch13CudaStreamPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::CudaStreamPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch8TokenPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::TokenPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch10newRequestE8SizeTypeRKN13decoder_batch7RequestERK14SamplingConfig"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::newRequest()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::forwardAsync()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch11forwardSyncERKN13decoder_batch5TokenE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::forwardSync()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch7forwardERN13decoder_batch6OutputERKN13decoder_batch5InputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::forward()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch12getOutputIdsE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::getOutputIds()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch8finalizeE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::finalize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch11getFinishedEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::getFinished()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch14getCumLogProbsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::getCumLogProbs()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch14getCumLogProbsE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::getCumLogProbs()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch11getLogProbsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::getLogProbs()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch11getLogProbsE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::getLogProbs()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch12getParentIdsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::getParentIds()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch10getNbStepsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::getNbSteps()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch16IGptDecoderBatchEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IGptDecoderBatch::IGptDecoderBatch()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::decoder_batch</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch6OutputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::decoder_batch::Output</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7RequestE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::decoder_batch::Request</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5InputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::decoder_batch::Input</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5TokenE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::decoder_batch::Token</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#istatefulgptdecoder-h">iStatefulGptDecoder.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoderE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder13CudaStreamPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::CudaStreamPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupE8SizeType8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::setup()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::newBatch()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder12forwardAsyncERN7decoder6OutputERKN7decoder5InputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::forwardAsync()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder11forwardSyncEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::forwardSync()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder7forwardERN7decoder6OutputERKN7decoder5InputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::forward()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder8finalizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::finalize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder12getOutputIdsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::getOutputIds()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder14getCumLogProbsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::getCumLogProbs()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder11getLogProbsEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::getLogProbs()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder12getNewTokensE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::getNewTokens()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder15getAllNewTokensEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::getAllNewTokens()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder13getNbFinishedEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::getNbFinished()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoderD0Ev"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::~IStatefulGptDecoder()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder19IStatefulGptDecoderEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IStatefulGptDecoder::IStatefulGptDecoder()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoderE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::decoder</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder5InputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::decoder::Input</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder6OutputE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::decoder::Output</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#itensor-h">iTensor.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv48nvinfer1"><code class="docutils literal notranslate"><span class="pre">nvinfer1</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::operator<<()</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::operator<<()</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::UniquePtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::SharedPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::UniqueConstPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor14SharedConstPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::SharedConstPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::Shape</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7DimTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::DimType</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorD0Ev"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::~ITensor()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7ITensor8getShapeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::getShape()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::reshape()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::resize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorERK7ITensor"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::ITensor()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensoraSERK7ITensor"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::operator=()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::squeeze()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::unsqueeze()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::shapeEquals()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI8SizeTypeEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::shapeEquals()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::shapeEquals()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor6volumeERK5Shape"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::volume()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::volumeNonNegative()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::squeeze()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::unsqueeze()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::slice()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::slice()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::slice()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::slice()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::view()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::view()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::view()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::wrap()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::wrap()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::wrap()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::wrap()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::wrap()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI8SizeTypeEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::makeShape()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor8toStringERK5Shape"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::toString()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::shapeEquals()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::shapeEquals()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::ITensor()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor8castSizeE6size_t"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::ITensor::castSize()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#ipcutils-h">ipcUtils.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13setPeerAccessE11WorldConfigb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::setPeerAccess()</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemoryE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IpcMemory</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IpcMemory::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryE11WorldConfigNSt6size_tE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IpcMemory::IpcMemory()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemoryD0Ev"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IpcMemory::~IpcMemory()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime9IpcMemory17getCommPtrsTensorEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IpcMemory::getCommPtrsTensor()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory10FLAGS_SIZEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IpcMemory::FLAGS_SIZE</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IpcMemory::allocateIpcMemory()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory16destroyIpcMemoryEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IpcMemory::destroyIpcMemory()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory12mWorldConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IpcMemory::mWorldConfig</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory9mCommPtrsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IpcMemory::mCommPtrs</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory11mBufferSizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IpcMemory::mBufferSize</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory10mBufferPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::IpcMemory::mBufferPtr</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#memorycounters-h">memoryCounters.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCountersE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::SizeType</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::DiffType</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters14MemoryCountersEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::MemoryCounters()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getGpuEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::getGpu()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getCpuEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::getCpu()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters9getPinnedEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::getPinned()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getGpuDiffEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::getGpuDiff()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getCpuDiffEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::getCpuDiff()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedDiffEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::getPinnedDiff()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::allocate()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::allocate()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::deallocate()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::deallocate()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters8toStringEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::toString()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters11getInstanceEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::getInstance()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8SizeTypei"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::bytesToString()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::bytesToString()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mGpuE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::mGpu</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mCpuE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::mCpu</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters7mPinnedE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::mPinned</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mGpuDiffE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::mGpuDiff</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mCpuDiffE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::mCpuDiff</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedDiffE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::mPinnedDiff</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters9mInstanceE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::MemoryCounters::mInstance</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#prompttuningparams-h">promptTuningParams.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericPromptTuningParams</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericPromptTuningParams::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams8SizeTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericPromptTuningParams::SizeType</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams14embeddingTableE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericPromptTuningParams::embeddingTable</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams5tasksE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericPromptTuningParams::tasks</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9vocabSizeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericPromptTuningParams::vocabSize</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams19promptTuningEnabledE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::GenericPromptTuningParams::promptTuningEnabled</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParamsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::PromptTuningParams</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::PromptTuningParams::TensorPtr</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams8SizeTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::PromptTuningParams::SizeType</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK8SizeTypeK8SizeTypeRKNSt6vectorI8SizeTypeEERKNSt6vectorI8SizeTypeEERK13BufferManagerb"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#samplingconfig-h">samplingConfig.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::SamplingConfig()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9beamWidthE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::beamWidth</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig11temperatureE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::temperature</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9minLengthE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::minLength</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig17repetitionPenaltyE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::repetitionPenalty</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig15presencePenaltyE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::presencePenalty</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topKE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::topK</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topPE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::topP</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig10randomSeedE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::randomSeed</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9topPDecayE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::topPDecay</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig7topPMinE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::topPMin</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig12topPResetIdsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::topPResetIds</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig23beamSearchDiversityRateE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::beamSearchDiversityRate</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig13lengthPenaltyE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::lengthPenalty</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig24draftAcceptanceThresholdE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::draftAcceptanceThreshold</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::FloatType</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::SamplingConfig::OptVec</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#tllmlogger-h">tllmLogger.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10TllmLoggerE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TllmLogger</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TllmLogger::log()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10TllmLogger8getLevelEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TllmLogger::getLevel()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::TllmLogger::setLevel()</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#worldconfig-h">worldConfig.h</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig</span></code></a><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE8SizeType8SizeType8SizeType8SizeTypeNSt6vectorI8SizeTypeEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::WorldConfig()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getSizeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::getSize()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig20getTensorParallelismEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::getTensorParallelism()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig16isTensorParallelEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::isTensorParallel()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getPipelineParallelismEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::getPipelineParallelism()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig18isPipelineParallelEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::isPipelineParallel()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getRankEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::getRank()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig14getGpusPerNodeEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::getGpusPerNode()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig9getDeviceEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::getDevice()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getPipelineParallelRankEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::getPipelineParallelRank()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getTensorParallelRankEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::getTensorParallelRank()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig27isFirstPipelineParallelRankEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::isFirstPipelineParallelRank()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isLastPipelineParallelRankEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::isLastPipelineParallelRank()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getLastRankEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::getLastRank()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig24getPipelineParallelGroupEv"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::getPipelineParallelGroup()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig11validConfigERN8nvinfer17ILoggerE8SizeType8SizeType"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::validConfig()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiERN8nvinfer17ILoggerE8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEENSt8optionalINSt6vectorI8SizeTypeEEEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::mpi()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEENSt8optionalINSt6vectorI8SizeTypeEEEE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::mpi()</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::kDefaultGpusPerNode</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig18mTensorParallelismE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::mTensorParallelism</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig20mPipelineParallelismE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::mPipelineParallelism</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig5mRankE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::mRank</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig12mGpusPerNodeE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::mGpusPerNode</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig10mDeviceIdsE"><code class="docutils literal notranslate"><span class="pre">tensorrt_llm::runtime::WorldConfig::mDeviceIds</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</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>
|
||
</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">Runtime</li>
|
||
<li class="wy-breadcrumbs-aside">
|
||
<a href="../_sources/_cpp_gen/runtime.rst.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="runtime">
|
||
<h1>Runtime<a class="headerlink" href="#runtime" title="Link to this heading"></a></h1>
|
||
<section id="buffermanager-h">
|
||
<h2>bufferManager.h<a class="headerlink" href="#buffermanager-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv412tensorrt_llm">
|
||
<span id="_CPPv312tensorrt_llm"></span><span id="_CPPv212tensorrt_llm"></span><span id="tensorrt_llm"></span><span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><a class="headerlink" href="#_CPPv412tensorrt_llm" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtimeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtimeE"></span><span id="_CPPv2N12tensorrt_llm7runtimeE"></span><span id="tensorrt_llm::runtime"></span><span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtimeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManagerE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManagerE"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManagerE"></span><span id="tensorrt_llm::runtime::BufferManager"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">BufferManager</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="docutils container">
|
||
<em>#include <bufferManager.h></em></div>
|
||
<p>A helper class for managing memory on host and device. </p>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager10IBufferPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager10IBufferPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a0bd5b422b1e3a5d2171f66532f27f413"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">IBufferPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE" title="tensorrt_llm::runtime::IBuffer::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager10ITensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager10ITensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a5f8cccf8f635cf3cfbec353e1a7317b9"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">ITensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE" title="tensorrt_llm::runtime::ITensor::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1ae977afd5a423417ac57f3bffa8162b33"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">CudaStreamPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStreamE" title="tensorrt_llm::runtime::CudaStream"><span class="n"><span class="pre">CudaStream</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtr"></span><span id="tensorrt_llm::runtime::BufferManager::BufferManager__CudaStreamPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1ac641ea2cdcc436ed29ce3bacc42d549a"></span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">BufferManager</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE" title="tensorrt_llm::runtime::BufferManager::CudaStreamPtr"><span class="n"><span class="pre">CudaStreamPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">stream</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager13BufferManagerE13CudaStreamPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Construct a <a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1BufferManager"><span class="std std-ref">BufferManager</span></a>. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p><strong>cudaStream</strong> – <strong>[in]</strong> The cuda stream to use for all operations on GPU (allocation, de-allocation, copying, etc.). </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::BufferManager::gpu__std::s.nvinfer1::DataTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a2cf0e00fd6ac0cfe8b593749583a7a03"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE" title="tensorrt_llm::runtime::BufferManager::IBufferPtr"><span class="n"><span class="pre">IBufferPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">gpu</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE" title="tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"><span class="n"><span class="pre">kBYTE_TYPE</span></span></a><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuENSt6size_tEN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Allocates an <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IBuffer"><span class="std std-ref"><span class="pre">IBuffer</span></span></a></code> of the given size on the GPU. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::BufferManager::gpu__nvinfer1::Dims.nvinfer1::DataTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a5a023b2d5f629bc86e262f9733a12a59"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE" title="tensorrt_llm::runtime::BufferManager::ITensorPtr"><span class="n"><span class="pre">ITensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">gpu</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">Dims</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">dims</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE" title="tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"><span class="n"><span class="pre">kBYTE_TYPE</span></span></a><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager3gpuEN8nvinfer14DimsEN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Allocates an <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1ITensor"><span class="std std-ref"><span class="pre">ITensor</span></span></a></code> of the given dimensions on the GPU. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::BufferManager::allocate__MemoryType.std::s.nvinfer1::DataTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a1bdafec3fa633fdb0d321f5e748b3174"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE" title="tensorrt_llm::runtime::BufferManager::IBufferPtr"><span class="n"><span class="pre">IBufferPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">allocate</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">memoryType</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE" title="tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"><span class="n"><span class="pre">kBYTE_TYPE</span></span></a><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeNSt6size_tEN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Allocates an <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IBuffer"><span class="std std-ref"><span class="pre">IBuffer</span></span></a></code> of the given size and memory type. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::BufferManager::allocate__MemoryType.nvinfer1::Dims.nvinfer1::DataTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a0e4e4c0e248e95e19061a61fadec30cc"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE" title="tensorrt_llm::runtime::BufferManager::ITensorPtr"><span class="n"><span class="pre">ITensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">allocate</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">memoryType</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">Dims</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">dims</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE" title="tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"><span class="n"><span class="pre">kBYTE_TYPE</span></span></a><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager8allocateE10MemoryTypeN8nvinfer14DimsEN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Allocates an <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1ITensor"><span class="std std-ref"><span class="pre">ITensor</span></span></a></code> of the given dimensions and memory type. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::BufferManager::emptyBuffer__MemoryType.nvinfer1::DataTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a0e78e3aa2aa1d635ae230996b449f9a4"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE" title="tensorrt_llm::runtime::BufferManager::IBufferPtr"><span class="n"><span class="pre">IBufferPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">emptyBuffer</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">memoryType</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE" title="tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"><span class="n"><span class="pre">kBYTE_TYPE</span></span></a><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyBufferE10MemoryTypeN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Create an empty <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IBuffer"><span class="std std-ref"><span class="pre">IBuffer</span></span></a></code> of the given memory type. It may be resized later. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::BufferManager::emptyTensor__MemoryType.nvinfer1::DataTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a1d0157fa19df03ba561d15d5b64de259"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE" title="tensorrt_llm::runtime::BufferManager::ITensorPtr"><span class="n"><span class="pre">ITensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">emptyTensor</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">memoryType</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE" title="tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"><span class="n"><span class="pre">kBYTE_TYPE</span></span></a><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager11emptyTensorE10MemoryTypeN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Create an empty <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1ITensor"><span class="std std-ref"><span class="pre">ITensor</span></span></a></code> of the given memory type. It may be reshaped later. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer"></span><span id="tensorrt_llm::runtime::BufferManager::setZero__IBufferRC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1afe66c31bfc8e00ebbdb8405194be0db9"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setZero</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">buffer</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager7setZeroER7IBuffer" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Set the contents of the given <code class="docutils literal notranslate"><span class="pre">buffer</span></code> to zero. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType"></span><span id="tensorrt_llm::runtime::BufferManager::copy__voidCP.IBufferR.MemoryTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a1adc12c1388e8a3392ac39a3ae64d518"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">copy</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">src</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">dst</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">srcType</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer10MemoryType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Copy <code class="docutils literal notranslate"><span class="pre">src</span></code> to <code class="docutils literal notranslate"><span class="pre">dst</span></code>. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType"></span><span id="tensorrt_llm::runtime::BufferManager::copy__IBufferCR.voidP.MemoryTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a313f2bd39b26e568c97f092a98ac20f9"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">copy</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">src</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">dst</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">dstType</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv10MemoryType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Copy <code class="docutils literal notranslate"><span class="pre">src</span></code> to <code class="docutils literal notranslate"><span class="pre">dst</span></code>. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer"></span><span id="tensorrt_llm::runtime::BufferManager::copy__voidCP.IBufferRC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a3086524a384108c45199076f536d4d9c"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">copy</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">src</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">dst</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyEPKvR7IBuffer" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Copy <code class="docutils literal notranslate"><span class="pre">src</span></code> to <code class="docutils literal notranslate"><span class="pre">dst</span></code>. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv"></span><span id="tensorrt_llm::runtime::BufferManager::copy__IBufferCR.voidPC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a583c0a02dcd51050b5b4273a19c0bde7"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">copy</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">src</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">dst</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferPv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Copy <code class="docutils literal notranslate"><span class="pre">src</span></code> to <code class="docutils literal notranslate"><span class="pre">dst</span></code>. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer"></span><span id="tensorrt_llm::runtime::BufferManager::copy__IBufferCR.IBufferRC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a406d3f69a661d5a3bcb5dded51626c44"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">copy</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">src</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">dst</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager4copyERK7IBufferR7IBuffer" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Copy <code class="docutils literal notranslate"><span class="pre">src</span></code> to <code class="docutils literal notranslate"><span class="pre">dst</span></code>. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType"></span><span id="tensorrt_llm::runtime::BufferManager::copyFrom__IBufferCR.MemoryTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a3101d71e18fa84154b687236487dfc5f"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE" title="tensorrt_llm::runtime::BufferManager::IBufferPtr"><span class="n"><span class="pre">IBufferPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">copyFrom</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">src</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">memoryType</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7IBuffer10MemoryType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Copy <code class="docutils literal notranslate"><span class="pre">src</span></code> into a new <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IBuffer"><span class="std std-ref"><span class="pre">IBuffer</span></span></a></code> with a potentially different memory type. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType"></span><span id="tensorrt_llm::runtime::BufferManager::copyFrom__ITensorCR.MemoryTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a80a336bdfbd0faf2d76e470354bcddf0"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE" title="tensorrt_llm::runtime::BufferManager::ITensorPtr"><span class="n"><span class="pre">ITensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">copyFrom</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">src</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">memoryType</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager8copyFromERK7ITensor10MemoryType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Copy <code class="docutils literal notranslate"><span class="pre">src</span></code> into a new <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1ITensor"><span class="std std-ref"><span class="pre">ITensor</span></span></a></code> with a potentially different memory type. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType">
|
||
<span id="_CPPv3I0ENK12tensorrt_llm7runtime13BufferManager8copyFromERKNSt6vectorI1TEE10MemoryType"></span><span id="_CPPv2I0ENK12tensorrt_llm7runtime13BufferManager8copyFromERKNSt6vectorI1TEE10MemoryType"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a51f44f1cf97f9c0b686048d37291ea5a"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE" title="tensorrt_llm::runtime::BufferManager::IBufferPtr"><span class="n"><span class="pre">IBufferPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">copyFrom</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType" title="tensorrt_llm::runtime::BufferManager::copyFrom::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">src</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">memoryType</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10IBufferPtrRKNSt6vectorI1TEE10MemoryType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Copy <code class="docutils literal notranslate"><span class="pre">src</span></code> into a new <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IBuffer"><span class="std std-ref"><span class="pre">IBuffer</span></span></a></code> with a potentially different memory type. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType">
|
||
<span id="_CPPv3I0ENK12tensorrt_llm7runtime13BufferManager8copyFromEP1TN8nvinfer14DimsE10MemoryType"></span><span id="_CPPv2I0ENK12tensorrt_llm7runtime13BufferManager8copyFromEP1TN8nvinfer14DimsE10MemoryType"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1ac42305510a739c47d3c4358b97560f3e"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE" title="tensorrt_llm::runtime::BufferManager::ITensorPtr"><span class="n"><span class="pre">ITensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">copyFrom</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType" title="tensorrt_llm::runtime::BufferManager::copyFrom::T"><span class="n"><span class="pre">T</span></span></a><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">src</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">Dims</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">dims</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">memoryType</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrP1TN8nvinfer14DimsE10MemoryType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Copy <code class="docutils literal notranslate"><span class="pre">src</span></code> into a new <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1ITensor"><span class="std std-ref"><span class="pre">ITensor</span></span></a></code> with a potentially different memory type. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType">
|
||
<span id="_CPPv3I0ENK12tensorrt_llm7runtime13BufferManager8copyFromERKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType"></span><span id="_CPPv2I0ENK12tensorrt_llm7runtime13BufferManager8copyFromERKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a8feac5727a72ee0d1c50b3ff5ee4e979"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE" title="tensorrt_llm::runtime::BufferManager::ITensorPtr"><span class="n"><span class="pre">ITensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">copyFrom</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType" title="tensorrt_llm::runtime::BufferManager::copyFrom::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">src</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">Dims</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">dims</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">memoryType</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4I0ENK12tensorrt_llm7runtime13BufferManager8copyFromE10ITensorPtrRKNSt6vectorI1TEEN8nvinfer14DimsE10MemoryType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Copy <code class="docutils literal notranslate"><span class="pre">src</span></code> into a new <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1ITensor"><span class="std std-ref"><span class="pre">ITensor</span></span></a></code> with a potentially different memory type. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager9getStreamEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager9getStreamEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager9getStreamEv"></span><span id="tensorrt_llm::runtime::BufferManager::getStreamC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1aa8eb6eafae45f681f082cab5daa26029"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStreamE" title="tensorrt_llm::runtime::CudaStream"><span class="n"><span class="pre">CudaStream</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getStream</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager9getStreamEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Get the underlying cuda stream. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEv"></span><span id="tensorrt_llm::runtime::BufferManager::memoryPoolReservedC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a92a21be0a954deb04c9c6e8540a2141b"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">memoryPoolReserved</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>The current size of the memory reserved by the memory pool. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEv"></span><span id="tensorrt_llm::runtime::BufferManager::memoryPoolUsedC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a73ae2808af584ba85c1a61134f025659"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">memoryPoolUsed</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>The current size of the memory used by the memory pool. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEv"></span><span id="tensorrt_llm::runtime::BufferManager::memoryPoolFreeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a822c7eaa19d0bdebd460fdc4cf6ee82a"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">memoryPoolFree</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>The current size of the memory free in the memory pool. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE"></span><span id="tensorrt_llm::runtime::BufferManager::memoryPoolTrimTo__std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a5e74ccf0e2e2132ae5834c31209f87d3"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">memoryPoolTrimTo</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToENSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Try to trim the memory reserved by the pool to <code class="docutils literal notranslate"><span class="pre">size</span></code> bytes. This synchronizes implicitly with the stream. </p>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-functions">Public Static Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::BufferManager::cpu__std::s.nvinfer1::DataType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a7edb3cdde9b85c01fec18f3f4f34282f"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE" title="tensorrt_llm::runtime::BufferManager::IBufferPtr"><span class="n"><span class="pre">IBufferPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cpu</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE" title="tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"><span class="n"><span class="pre">kBYTE_TYPE</span></span></a><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuENSt6size_tEN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Allocates an <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IBuffer"><span class="std std-ref"><span class="pre">IBuffer</span></span></a></code> of the given size on the CPU. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::BufferManager::cpu__nvinfer1::Dims.nvinfer1::DataType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a3beb40d9ddabd96774167df148efc676"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE" title="tensorrt_llm::runtime::BufferManager::ITensorPtr"><span class="n"><span class="pre">ITensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cpu</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">Dims</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">dims</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE" title="tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"><span class="n"><span class="pre">kBYTE_TYPE</span></span></a><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager3cpuEN8nvinfer14DimsEN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Allocates an <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1ITensor"><span class="std std-ref"><span class="pre">ITensor</span></span></a></code> of the given dimensions on the CPU. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::BufferManager::pinned__std::s.nvinfer1::DataType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a6a58588cfc27c05c1d7dbb2f043672d3"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10IBufferPtrE" title="tensorrt_llm::runtime::BufferManager::IBufferPtr"><span class="n"><span class="pre">IBufferPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">pinned</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE" title="tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"><span class="n"><span class="pre">kBYTE_TYPE</span></span></a><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedENSt6size_tEN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Allocates a pinned <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IBuffer"><span class="std std-ref"><span class="pre">IBuffer</span></span></a></code> of the given size on the CPU. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::BufferManager::pinned__nvinfer1::Dims.nvinfer1::DataType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a3cfc4376c5e62876586e1e07e08d3069"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10ITensorPtrE" title="tensorrt_llm::runtime::BufferManager::ITensorPtr"><span class="n"><span class="pre">ITensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">pinned</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">Dims</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">dims</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE" title="tensorrt_llm::runtime::BufferManager::kBYTE_TYPE"><span class="n"><span class="pre">kBYTE_TYPE</span></span></a><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager6pinnedEN8nvinfer14DimsEN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Allocates a pinned <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1ITensor"><span class="std std-ref"><span class="pre">ITensor</span></span></a></code> of the given dimensions on the CPU. </p>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE"></span><span id="tensorrt_llm::runtime::BufferManager::kBYTE_TYPE__auto"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1af4254e3a9525a8051face3c7ca729b65"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kBYTE_TYPE</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kUINT8</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager10kBYTE_TYPEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager7mStreamE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager7mStreamE"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager7mStreamE"></span><span id="tensorrt_llm::runtime::BufferManager::mStream__CudaStreamPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1aeab688938251784e88b66cff01a0dde3"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE" title="tensorrt_llm::runtime::BufferManager::CudaStreamPtr"><span class="n"><span class="pre">CudaStreamPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mStream</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager7mStreamE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-static-functions">Private Static Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager14initMemoryPoolEi">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager14initMemoryPoolEi"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager14initMemoryPoolEi"></span><span id="tensorrt_llm::runtime::BufferManager::initMemoryPool__i"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1aba8fe4df93bbf829d0cefa8bcc63e657"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">initMemoryPool</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">device</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager14initMemoryPoolEi" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEi">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEi"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEi"></span><span id="tensorrt_llm::runtime::BufferManager::memoryPoolReserved__i"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a76510e249e79d5ad43ca5cccf587cbec"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">memoryPoolReserved</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">device</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager18memoryPoolReservedEi" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEi">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEi"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEi"></span><span id="tensorrt_llm::runtime::BufferManager::memoryPoolUsed__i"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a32130ebd3537d477a5002edfacd19058"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">memoryPoolUsed</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">device</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager14memoryPoolUsedEi" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEi">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEi"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEi"></span><span id="tensorrt_llm::runtime::BufferManager::memoryPoolFree__i"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a198cac633154050fbb500d3abae689d7"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">memoryPoolFree</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">device</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager14memoryPoolFreeEi" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToEiNSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToEiNSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToEiNSt6size_tE"></span><span id="tensorrt_llm::runtime::BufferManager::memoryPoolTrimTo__i.std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferManager_1a9702f3969f11fa908f4b24662bd8ff63"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">memoryPoolTrimTo</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">device</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager16memoryPoolTrimToEiNSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="common-h">
|
||
<h2>common.h<a class="headerlink" href="#common-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-typedefs">Typedefs</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime8SizeTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime8SizeTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime8SizeTypeE"></span><span class="target" id="common_8h_1a8da5a8de61b5f096333bdd15d5a16875"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">SizeType</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int32_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TokenIdTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TokenIdTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TokenIdTypeE"></span><span class="target" id="common_8h_1a1de916f1c3f3c8d1f9c66320afc6df17"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TokenIdType</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int32_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TokenIdTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime12StringPtrMapE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime12StringPtrMapE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime12StringPtrMapE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="common_8h_1a43946c471b82feb36a6350de9cde277d"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">StringPtrMap</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unordered_map</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime12StringPtrMapE" title="tensorrt_llm::runtime::StringPtrMap::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime12StringPtrMapE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="cudaevent-h">
|
||
<h2>cudaEvent.h<a class="headerlink" href="#cudaevent-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9CudaEventE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9CudaEventE"></span><span id="_CPPv2N12tensorrt_llm7runtime9CudaEventE"></span><span id="tensorrt_llm::runtime::CudaEvent"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">CudaEvent</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9CudaEvent7pointerE"></span><span id="_CPPv2N12tensorrt_llm7runtime9CudaEvent7pointerE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1a765323cdb24844d31c8f9e354a5194f8"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">pointer</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">cudaEvent_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventEj">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9CudaEvent9CudaEventEj"></span><span id="_CPPv2N12tensorrt_llm7runtime9CudaEvent9CudaEventEj"></span><span id="tensorrt_llm::runtime::CudaEvent::CudaEvent__unsigned-i"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1aae9d65fd3cc3d42763c1219710dcd6ac"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">CudaEvent</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">unsigned</span></span><span class="w"> </span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">flags</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">cudaEventDisableTiming</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventEj" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Creates a new cuda event. The event will be destroyed in the destructor.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p><strong>flags</strong> – Flags for event creation. By default, event timing is disabled. </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb"></span><span id="_CPPv2N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb"></span><span id="tensorrt_llm::runtime::CudaEvent::CudaEvent__pointer.b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1a8ac4cb3f5ac924e72862c1c5fd033cbd"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">CudaEvent</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE" title="tensorrt_llm::runtime::CudaEvent::pointer"><span class="n"><span class="pre">pointer</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">event</span></span>, <span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">ownsEvent</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">true</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent9CudaEventE7pointerb" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Pass an existing cuda event to this object.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>event</strong> – The event to pass to this object. </p></li>
|
||
<li><p><strong>ownsEvent</strong> – Whether this object owns the event and destroys it in the destructor. </p></li>
|
||
</ul>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime9CudaEvent3getEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime9CudaEvent3getEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime9CudaEvent3getEv"></span><span id="tensorrt_llm::runtime::CudaEvent::getC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1a530c756fe9e6ad149b813659b3644f16"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE" title="tensorrt_llm::runtime::CudaEvent::pointer"><span class="n"><span class="pre">pointer</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">get</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime9CudaEvent3getEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns the event associated with this object. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime9CudaEvent11synchronizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime9CudaEvent11synchronizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime9CudaEvent11synchronizeEv"></span><span id="tensorrt_llm::runtime::CudaEvent::synchronizeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1a9216cdfafea99849fb47b1be60fb1a7e"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">synchronize</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime9CudaEvent11synchronizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Synchronizes the event. </p>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-types">Private Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9CudaEvent12element_typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9CudaEvent12element_typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime9CudaEvent12element_typeE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1a411326cde2f9f947c5d92abe724ebb34"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">element_type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">remove_pointer_t</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE" title="tensorrt_llm::runtime::CudaEvent::pointer"><span class="n"><span class="pre">pointer</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent12element_typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9CudaEvent8EventPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9CudaEvent8EventPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime9CudaEvent8EventPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1ac5468fc310bab51276ed6d6212e7240f"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">EventPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unique_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent12element_typeE" title="tensorrt_llm::runtime::CudaEvent::element_type"><span class="n"><span class="pre">element_type</span></span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7DeleterE" title="tensorrt_llm::runtime::CudaEvent::Deleter"><span class="n"><span class="pre">Deleter</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent8EventPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9CudaEvent6mEventE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9CudaEvent6mEventE"></span><span id="_CPPv2N12tensorrt_llm7runtime9CudaEvent6mEventE"></span><span id="tensorrt_llm::runtime::CudaEvent::mEvent__EventPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1a3231de6317de1857e5f699a94d59dcf2"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent8EventPtrE" title="tensorrt_llm::runtime::CudaEvent::EventPtr"><span class="n"><span class="pre">EventPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mEvent</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent6mEventE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9CudaEvent7DeleterE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9CudaEvent7DeleterE"></span><span id="_CPPv2N12tensorrt_llm7runtime9CudaEvent7DeleterE"></span><span id="tensorrt_llm::runtime::CudaEvent::Deleter"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1_1Deleter"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Deleter</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7DeleterE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb"></span><span id="_CPPv2N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb"></span><span id="tensorrt_llm::runtime::CudaEvent::Deleter::Deleter__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1_1Deleter_1a7807c6a0240c9d01f09dbde19b422d05"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Deleter</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">ownsEvent</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEv"></span><span id="_CPPv2N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEv"></span><span id="tensorrt_llm::runtime::CudaEvent::Deleter::Deleter"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1_1Deleter_1aec3a7bdb695dc6598d6c6b8c5cbd4598"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Deleter</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter7DeleterEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime9CudaEvent7DeleterclE7pointer">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime9CudaEvent7DeleterclE7pointer"></span><span id="_CPPv2NK12tensorrt_llm7runtime9CudaEvent7DeleterclE7pointer"></span><span id="tensorrt_llm::runtime::CudaEvent::Deleter::call-operator__pointerCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1_1Deleter_1a82af09350919fceb1f0f4c43d1822d37"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="k"><span class="pre">operator</span></span><span class="o"><span class="pre">()</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE" title="tensorrt_llm::runtime::CudaEvent::pointer"><span class="n"><span class="pre">pointer</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">event</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime9CudaEvent7DeleterclE7pointer" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter10mOwnsEventE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9CudaEvent7Deleter10mOwnsEventE"></span><span id="_CPPv2N12tensorrt_llm7runtime9CudaEvent7Deleter10mOwnsEventE"></span><span id="tensorrt_llm::runtime::CudaEvent::Deleter::mOwnsEvent__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaEvent_1_1Deleter_1a4df7640a97930eaf43a1ca952f3f919f"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mOwnsEvent</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7Deleter10mOwnsEventE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="cudastream-h">
|
||
<h2>cudaStream.h<a class="headerlink" href="#cudastream-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10CudaStreamE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10CudaStreamE"></span><span id="_CPPv2N12tensorrt_llm7runtime10CudaStreamE"></span><span id="tensorrt_llm::runtime::CudaStream"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">CudaStream</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10CudaStreamE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10CudaStream10CudaStreamEji"></span><span id="_CPPv2N12tensorrt_llm7runtime10CudaStream10CudaStreamEji"></span><span id="tensorrt_llm::runtime::CudaStream::CudaStream__unsigned-i.i"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1a2ba13a61587813c68c018a64ed2967fe"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">CudaStream</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">unsigned</span></span><span class="w"> </span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">flags</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">cudaStreamNonBlocking</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">priority</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamEji" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Creates a new cuda stream on the current device. The stream will be destroyed in the destructor.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>flags</strong> – Flags for stream creation. See ::cudaStreamCreateWithFlags for a list of valid flags that can be passed. </p></li>
|
||
<li><p><strong>priority</strong> – Priority of the stream. Lower numbers represent higher priorities. See ::cudaDeviceGetStreamPriorityRange for more information about the meaningful stream priorities that can be passed. </p></li>
|
||
</ul>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib"></span><span id="_CPPv2N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib"></span><span id="tensorrt_llm::runtime::CudaStream::CudaStream__cudaStream_t.i.b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1a4ff09ea22fc6679e2d93b772e148d19e"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">CudaStream</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">cudaStream_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">stream</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">device</span></span>, <span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">ownsStream</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">true</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream10CudaStreamE12cudaStream_tib" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Pass an existing cuda stream to this object.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>stream</strong> – The stream to pass to this object. </p></li>
|
||
<li><p><strong>device</strong> – The device on which the stream was created. </p></li>
|
||
<li><p><strong>ownsStream</strong> – Whether this object owns the stream and destroys it in the destructor. </p></li>
|
||
</ul>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10CudaStream9getDeviceEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10CudaStream9getDeviceEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime10CudaStream9getDeviceEv"></span><span id="tensorrt_llm::runtime::CudaStream::getDeviceC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1a2209ae12d3b5a27740d66bec35e686c9"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getDevice</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream9getDeviceEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns the device on which the stream was created. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10CudaStream3getEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10CudaStream3getEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime10CudaStream3getEv"></span><span id="tensorrt_llm::runtime::CudaStream::getC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1a9ba739eedb71b18bc4a58ff480c82a27"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="n"><span class="pre">cudaStream_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">get</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream3getEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns the stream associated with this object. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10CudaStream11synchronizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10CudaStream11synchronizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime10CudaStream11synchronizeEv"></span><span id="tensorrt_llm::runtime::CudaStream::synchronizeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1a3e3def9cc0e09e9724e9e68232ed2679"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">synchronize</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream11synchronizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Synchronizes the stream. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE"></span><span id="_CPPv2NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE"></span><span id="tensorrt_llm::runtime::CudaStream::record__CudaEvent::pointerC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1acc03555968e2361dc08d28f2228a1e31"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">record</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="tensorrt_llm::runtime::CudaEvent"><span class="n"><span class="pre">CudaEvent</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE" title="tensorrt_llm::runtime::CudaEvent::pointer"><span class="n"><span class="pre">pointer</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">event</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordEN9CudaEvent7pointerE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Record an event on the stream. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent"></span><span id="_CPPv2NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent"></span><span id="tensorrt_llm::runtime::CudaStream::record__CudaEventCRC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1ace6075f1266bdefe0b2033717dd8b14a"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">record</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="tensorrt_llm::runtime::CudaEvent"><span class="n"><span class="pre">CudaEvent</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">event</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream6recordERK9CudaEvent" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Record an event on the stream. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE"></span><span id="_CPPv2NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE"></span><span id="tensorrt_llm::runtime::CudaStream::wait__CudaEvent::pointerC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1a97622ff55b119c5eec1b096115462098"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">wait</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="tensorrt_llm::runtime::CudaEvent"><span class="n"><span class="pre">CudaEvent</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEvent7pointerE" title="tensorrt_llm::runtime::CudaEvent::pointer"><span class="n"><span class="pre">pointer</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">event</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitEN9CudaEvent7pointerE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Wait for an event. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent"></span><span id="_CPPv2NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent"></span><span id="tensorrt_llm::runtime::CudaStream::wait__CudaEventCRC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1a60cfbc942ee8d5f787ae66f891d91766"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">wait</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="tensorrt_llm::runtime::CudaEvent"><span class="n"><span class="pre">CudaEvent</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">event</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream4waitERK9CudaEvent" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Wait for an event. </p>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-types">Private Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10CudaStream9StreamPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10CudaStream9StreamPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime10CudaStream9StreamPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1a42e6eb53f179659c51fbd8981383af64"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">StreamPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unique_ptr</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">remove_pointer_t</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">cudaStream_t</span></span><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream7DeleterE" title="tensorrt_llm::runtime::CudaStream::Deleter"><span class="n"><span class="pre">Deleter</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream9StreamPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10CudaStream7mStreamE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10CudaStream7mStreamE"></span><span id="_CPPv2N12tensorrt_llm7runtime10CudaStream7mStreamE"></span><span id="tensorrt_llm::runtime::CudaStream::mStream__StreamPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1a21588e234ee724b69f92d1ef26779334"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream9StreamPtrE" title="tensorrt_llm::runtime::CudaStream::StreamPtr"><span class="n"><span class="pre">StreamPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mStream</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream7mStreamE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10CudaStream7mDeviceE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10CudaStream7mDeviceE"></span><span id="_CPPv2N12tensorrt_llm7runtime10CudaStream7mDeviceE"></span><span id="tensorrt_llm::runtime::CudaStream::mDevice__i"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1a5dc4aea4b9abfa576f166ce152b675e0"></span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDevice</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="o"><span class="pre">-</span></span><span class="m"><span class="pre">1</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream7mDeviceE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10CudaStream7DeleterE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10CudaStream7DeleterE"></span><span id="_CPPv2N12tensorrt_llm7runtime10CudaStream7DeleterE"></span><span id="tensorrt_llm::runtime::CudaStream::Deleter"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1_1Deleter"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Deleter</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream7DeleterE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb"></span><span id="_CPPv2N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb"></span><span id="tensorrt_llm::runtime::CudaStream::Deleter::Deleter__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1_1Deleter_1aa03f43a2e696a0433dd1a1c14ce129c2"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Deleter</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">ownsStream</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEv"></span><span id="_CPPv2N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEv"></span><span id="tensorrt_llm::runtime::CudaStream::Deleter::Deleter"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1_1Deleter_1adae80ccd16ccabd753f118cdb4111a51"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Deleter</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter7DeleterEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t"></span><span id="_CPPv2NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t"></span><span id="tensorrt_llm::runtime::CudaStream::Deleter::call-operator__cudaStream_tCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1_1Deleter_1a077db80f4a8d30a5f2e0adde1ec6372a"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="k"><span class="pre">operator</span></span><span class="o"><span class="pre">()</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">cudaStream_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">stream</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10CudaStream7DeleterclE12cudaStream_t" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter11mOwnsStreamE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10CudaStream7Deleter11mOwnsStreamE"></span><span id="_CPPv2N12tensorrt_llm7runtime10CudaStream7Deleter11mOwnsStreamE"></span><span id="tensorrt_llm::runtime::CudaStream::Deleter::mOwnsStream__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1CudaStream_1_1Deleter_1a71b80a1570697e35d7b5edb51904d9bd"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mOwnsStream</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10CudaStream7Deleter11mOwnsStreamE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="decodinginput-h">
|
||
<h2>decodingInput.h<a class="headerlink" href="#decodinginput-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInputE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInputE"></span><span id="tensorrt_llm::runtime::DecodingInput"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DecodingInput</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1a8e97b9538b8259558b0c15cbe2a59d15"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputE8SizeType8SizeType8SizeType9TensorPtr9TensorPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput13DecodingInputE8SizeType8SizeType8SizeType9TensorPtr9TensorPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput13DecodingInputE8SizeType8SizeType8SizeType9TensorPtr9TensorPtr"></span><span id="tensorrt_llm::runtime::DecodingInput::DecodingInput__SizeType.SizeType.SizeType.TensorPtr.TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1a5a3de3b9f69ab8ae6cfa6c1611212d76"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DecodingInput</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxLength</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxAttentionWindow</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="tensorrt_llm::runtime::DecodingInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">logits</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="tensorrt_llm::runtime::DecodingInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">endIds</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput13DecodingInputE8SizeType8SizeType8SizeType9TensorPtr9TensorPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput4stepE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput4stepE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput4stepE"></span><span id="tensorrt_llm::runtime::DecodingInput::step__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1a82755273657729ca89f9186abeeb713c"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">step</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput4stepE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput9maxLengthE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput9maxLengthE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput9maxLengthE"></span><span id="tensorrt_llm::runtime::DecodingInput::maxLength__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1ac4e6e64f43c3994f785a7047afd4578e"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">maxLength</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9maxLengthE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput18maxAttentionWindowE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput18maxAttentionWindowE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput18maxAttentionWindowE"></span><span id="tensorrt_llm::runtime::DecodingInput::maxAttentionWindow__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1a91a2c2672f9d9e2732caaf3ea3c1661a"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">maxAttentionWindow</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput18maxAttentionWindowE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput9batchSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput9batchSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput9batchSizeE"></span><span id="tensorrt_llm::runtime::DecodingInput::batchSize__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1a5d6979ade3dcff577fcf46c70c887917"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">batchSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9batchSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput6logitsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput6logitsE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput6logitsE"></span><span id="tensorrt_llm::runtime::DecodingInput::logits__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1aafadc431e8d06615d8425d82b1afaaa8"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="tensorrt_llm::runtime::DecodingInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">logits</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput6logitsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput6endIdsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput6endIdsE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput6endIdsE"></span><span id="tensorrt_llm::runtime::DecodingInput::endIds__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1a6bb630897ccbb4f437cf9ec517912d25"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="tensorrt_llm::runtime::DecodingInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">endIds</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput6endIdsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput8finishedE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput8finishedE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput8finishedE"></span><span id="tensorrt_llm::runtime::DecodingInput::finished__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1a8538e4b4b0f7c4e9cf495fba7fb9e648"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="tensorrt_llm::runtime::DecodingInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">finished</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput8finishedE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput19sequenceLimitLengthE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput19sequenceLimitLengthE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput19sequenceLimitLengthE"></span><span id="tensorrt_llm::runtime::DecodingInput::sequenceLimitLength__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1aa14e54120b58626beca8705ced84a79c"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="tensorrt_llm::runtime::DecodingInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">sequenceLimitLength</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput19sequenceLimitLengthE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput13embeddingBiasE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput13embeddingBiasE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput13embeddingBiasE"></span><span id="tensorrt_llm::runtime::DecodingInput::embeddingBias__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1a132486f973befa6c1c54bb0c22aab289"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="tensorrt_llm::runtime::DecodingInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">embeddingBias</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput13embeddingBiasE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput7lengthsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput7lengthsE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput7lengthsE"></span><span id="tensorrt_llm::runtime::DecodingInput::lengths__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1ad44428022172d330f631c81a712ce206"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="tensorrt_llm::runtime::DecodingInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">lengths</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput7lengthsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsListE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput12badWordsListE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput12badWordsListE"></span><span id="tensorrt_llm::runtime::DecodingInput::badWordsList__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1acfc2ebcd8202fc2330466a8773b1ab6d"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="tensorrt_llm::runtime::DecodingInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">badWordsList</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput12badWordsListE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsListE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput13stopWordsListE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput13stopWordsListE"></span><span id="tensorrt_llm::runtime::DecodingInput::stopWordsList__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1a6979dbc3a119fefd9f50c2132c1c95e7"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="tensorrt_llm::runtime::DecodingInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">stopWordsList</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput13stopWordsListE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput17noRepeatNgramSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput17noRepeatNgramSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput17noRepeatNgramSizeE"></span><span id="tensorrt_llm::runtime::DecodingInput::noRepeatNgramSize__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1a764f889cfac79873d7c88978e9d42df4"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="tensorrt_llm::runtime::DecodingInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">noRepeatNgramSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput17noRepeatNgramSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13DecodingInput16cacheIndirectionE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13DecodingInput16cacheIndirectionE"></span><span id="_CPPv2N12tensorrt_llm7runtime13DecodingInput16cacheIndirectionE"></span><span id="tensorrt_llm::runtime::DecodingInput::cacheIndirection__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingInput_1a6eccbda69f8c35e1eda57e9eb24ca930"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput9TensorPtrE" title="tensorrt_llm::runtime::DecodingInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cacheIndirection</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInput16cacheIndirectionE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="decodingoutput-h">
|
||
<h2>decodingOutput.h<a class="headerlink" href="#decodingoutput-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutputE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutputE"></span><span id="tensorrt_llm::runtime::DecodingOutput"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DecodingOutput</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1aeb215aae60278c44bcdbd17ae5f7c8e1"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputE9TensorPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputE9TensorPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputE9TensorPtr"></span><span id="tensorrt_llm::runtime::DecodingOutput::DecodingOutput__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a33bcc26e94af9077c4c8d1ba65acd39c"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DecodingOutput</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">ids</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14DecodingOutputE9TensorPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput3idsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput3idsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput3idsE"></span><span id="tensorrt_llm::runtime::DecodingOutput::ids__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a9937790aaf8c5cbb5230236afc7656be"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">ids</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput3idsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14newTokensStepsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14newTokensStepsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14newTokensStepsE"></span><span id="tensorrt_llm::runtime::DecodingOutput::newTokensSteps__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a6e42e3b0fd2b24ba8a04f78f837b207a"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">newTokensSteps</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14newTokensStepsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput9newTokensE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput9newTokensE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput9newTokensE"></span><span id="tensorrt_llm::runtime::DecodingOutput::newTokens__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a1c92d23772ed90b78f9ac8c86f46d9fd"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">newTokens</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9newTokensE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput12newTokensVecE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput12newTokensVecE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput12newTokensVecE"></span><span id="tensorrt_llm::runtime::DecodingOutput::newTokensVec__std::vector:TensorPtr:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a0df2485f70ab5959e706840f7635e4c3"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">newTokensVec</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput12newTokensVecE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput8finishedE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput8finishedE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput8finishedE"></span><span id="tensorrt_llm::runtime::DecodingOutput::finished__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a721bfb18d093d881f2f3a7d288dfb0e4"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">finished</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput8finishedE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput11finishedSumE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput11finishedSumE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput11finishedSumE"></span><span id="tensorrt_llm::runtime::DecodingOutput::finishedSum__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a2bb2c2cc930598e59363a8d61e2f0fc3"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">finishedSum</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput11finishedSumE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput8logProbsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput8logProbsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput8logProbsE"></span><span id="tensorrt_llm::runtime::DecodingOutput::logProbs__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a4abf75dc398349212b15b93f843fc03c"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">logProbs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput8logProbsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput11cumLogProbsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput11cumLogProbsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput11cumLogProbsE"></span><span id="tensorrt_llm::runtime::DecodingOutput::cumLogProbs__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a428f7d981f0617bda37e6f64bb4f0007"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cumLogProbs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput11cumLogProbsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput9parentIdsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput9parentIdsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput9parentIdsE"></span><span id="tensorrt_llm::runtime::DecodingOutput::parentIds__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a9f518ec59bd0df527432074008d974a6"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">parentIds</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9parentIdsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput7lengthsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput7lengthsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput7lengthsE"></span><span id="tensorrt_llm::runtime::DecodingOutput::lengths__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a7425f953e704cffb2b917d475fc90c12"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">lengths</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput7lengthsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput16cacheIndirectionE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput16cacheIndirectionE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput16cacheIndirectionE"></span><span id="tensorrt_llm::runtime::DecodingOutput::cacheIndirection__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a6ee6dfc4bf8f6f7ae17e0fc8d11ea56d"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cacheIndirection</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput16cacheIndirectionE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14beamHypothesesE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14beamHypothesesE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14beamHypothesesE"></span><span id="tensorrt_llm::runtime::DecodingOutput::beamHypotheses__BeamHypotheses"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1a1e1c48231792a45618deff974b48b4ee"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE" title="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses"><span class="n"><span class="pre">BeamHypotheses</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">beamHypotheses</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14beamHypothesesE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput17kNegativeInfinityE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput17kNegativeInfinityE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput17kNegativeInfinityE"></span><span id="tensorrt_llm::runtime::DecodingOutput::kNegativeInfinity__float"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1afad8e90f48ab5da093fdbb84b801f6da"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kNegativeInfinity</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="o"><span class="pre">-</span></span><span class="m"><span class="pre">1e20f</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput17kNegativeInfinityE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">BeamHypotheses</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyER13BufferManager">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyER13BufferManager"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyER13BufferManager"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::empty__BufferManagerR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1a00c82796e448818892e94f8a064a74cd"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">empty</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="tensorrt_llm::runtime::BufferManager"><span class="n"><span class="pre">BufferManager</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">manager</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5emptyER13BufferManager" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE8SizeType8SizeType8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE8SizeType8SizeType8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE8SizeType8SizeType8SizeType"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::reshape__SizeType.SizeType.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1a5ca4a3c3e34fe1f94224866821a2c352"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">reshape</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">beamWidth</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxSequenceLength</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7reshapeE8SizeType8SizeType8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7releaseEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7releaseEv"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7releaseEv"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::release"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1a6c10ab322d436f29ce99f0f0cb4e1e1a"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">release</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses7releaseEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initER13BufferManager11TokenIdType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initER13BufferManager11TokenIdType"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initER13BufferManager11TokenIdType"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::init__BufferManagerR.TokenIdType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1ab42b472a1d818532cd173ba69ad6097e"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">init</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="tensorrt_llm::runtime::BufferManager"><span class="n"><span class="pre">BufferManager</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">manager</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TokenIdTypeE" title="tensorrt_llm::runtime::TokenIdType"><span class="n"><span class="pre">TokenIdType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">endId</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses4initER13BufferManager11TokenIdType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE8SizeType8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE8SizeType8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE8SizeType8SizeType"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::slice__SizeType.SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1a35faed30b9315b8e1890c64d77561ac1"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypothesesE" title="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses"><span class="n"><span class="pre">BeamHypotheses</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">slice</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchIndex</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses5sliceE8SizeType8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12outputIdsTgtE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12outputIdsTgtE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12outputIdsTgtE"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::outputIdsTgt__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1aaeebc4faabecf671bd786c5ff44e2364"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">outputIdsTgt</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12outputIdsTgtE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18sequenceLengthsTgtE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18sequenceLengthsTgtE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18sequenceLengthsTgtE"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::sequenceLengthsTgt__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1a42ed879ae2b5475b54aa7d3328b5357b"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">sequenceLengthsTgt</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses18sequenceLengthsTgtE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11cumLogProbsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11cumLogProbsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11cumLogProbsE"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::cumLogProbs__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1ad2aaa38891d139affc6713f4d1a6e207"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cumLogProbs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses11cumLogProbsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12normedScoresE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12normedScoresE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12normedScoresE"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::normedScores__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1af97b849bf039b95020a3e9d7601b77f0"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">normedScores</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses12normedScoresE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses8logProbsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses8logProbsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses8logProbsE"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::logProbs__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1a51b9823628bb1388d261bbd18b4e141e"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">logProbs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses8logProbsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses15minNormedScoresE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses15minNormedScoresE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses15minNormedScoresE"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::minNormedScores__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1a545ce50c9d6ba29ebd84bbe1c7379648"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">minNormedScores</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses15minNormedScoresE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses8numBeamsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses8numBeamsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses8numBeamsE"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::numBeams__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1a207a33747d2474bc9252b6105e1cf7e9"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">numBeams</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses8numBeamsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses6isDoneE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses6isDoneE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses6isDoneE"></span><span id="tensorrt_llm::runtime::DecodingOutput::BeamHypotheses::isDone__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1DecodingOutput_1_1BeamHypotheses_1a75ad5911c7aa09ed3214d0d2ee2e4bad"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput9TensorPtrE" title="tensorrt_llm::runtime::DecodingOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">isDone</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutput14BeamHypotheses6isDoneE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="generationinput-h">
|
||
<h2>generationInput.h<a class="headerlink" href="#generationinput-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I00EN12tensorrt_llm7runtime22GenericGenerationInputE">
|
||
<span id="_CPPv3I00EN12tensorrt_llm7runtime22GenericGenerationInputE"></span><span id="_CPPv2I00EN12tensorrt_llm7runtime22GenericGenerationInputE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TTensor</span></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">PromptTuningParams</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GenericGenerationInput</span></span></span><a class="headerlink" href="#_CPPv4I00EN12tensorrt_llm7runtime22GenericGenerationInputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput_1a9697fefb8d30d140fb950c041cd3c86b"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I00EN12tensorrt_llm7runtime22GenericGenerationInputE" title="tensorrt_llm::runtime::GenericGenerationInput::TTensor"><span class="n"><span class="pre">TTensor</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput22GenericGenerationInputEK8SizeTypeK8SizeType9TensorPtr9TensorPtrb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime22GenericGenerationInput22GenericGenerationInputEK8SizeTypeK8SizeType9TensorPtr9TensorPtrb"></span><span id="_CPPv2N12tensorrt_llm7runtime22GenericGenerationInput22GenericGenerationInputEK8SizeTypeK8SizeType9TensorPtr9TensorPtrb"></span><span id="tensorrt_llm::runtime::GenericGenerationInput::GenericGenerationInput__SizeTypeC.SizeTypeC.TensorPtr.TensorPtr.b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput_1a1fa8815906f92b622267f523a81597c0"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GenericGenerationInput</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">endId</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">padId</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">ids</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">lengths</span></span>, <span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">packed</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">false</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput22GenericGenerationInputEK8SizeTypeK8SizeType9TensorPtr9TensorPtrb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput5endIdE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime22GenericGenerationInput5endIdE"></span><span id="_CPPv2N12tensorrt_llm7runtime22GenericGenerationInput5endIdE"></span><span id="tensorrt_llm::runtime::GenericGenerationInput::endId__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput_1a5623edc94ce2e11f4df7aad8a0c84ad9"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">endId</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput5endIdE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput5padIdE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime22GenericGenerationInput5padIdE"></span><span id="_CPPv2N12tensorrt_llm7runtime22GenericGenerationInput5padIdE"></span><span id="tensorrt_llm::runtime::GenericGenerationInput::padId__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput_1adf1b22c075502a3a0556897cc1b6c91e"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">padId</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput5padIdE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput3idsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime22GenericGenerationInput3idsE"></span><span id="_CPPv2N12tensorrt_llm7runtime22GenericGenerationInput3idsE"></span><span id="tensorrt_llm::runtime::GenericGenerationInput::ids__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput_1a33a188aa66efd03ca14459152178d6dd"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">ids</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput3idsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput7lengthsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime22GenericGenerationInput7lengthsE"></span><span id="_CPPv2N12tensorrt_llm7runtime22GenericGenerationInput7lengthsE"></span><span id="tensorrt_llm::runtime::GenericGenerationInput::lengths__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput_1a6e25b8ca6502844fa99acc5ed8cb4cf0"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">lengths</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput7lengthsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput6packedE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime22GenericGenerationInput6packedE"></span><span id="_CPPv2N12tensorrt_llm7runtime22GenericGenerationInput6packedE"></span><span id="tensorrt_llm::runtime::GenericGenerationInput::packed__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput_1a1251ffbef413840f81dc59bdedb88ee1"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">packed</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput6packedE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput13embeddingBiasE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime22GenericGenerationInput13embeddingBiasE"></span><span id="_CPPv2N12tensorrt_llm7runtime22GenericGenerationInput13embeddingBiasE"></span><span id="tensorrt_llm::runtime::GenericGenerationInput::embeddingBias__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput_1a69f8b8593ce1a89fd78f907b4c17cf55"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">embeddingBias</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput13embeddingBiasE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput12badWordsListE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime22GenericGenerationInput12badWordsListE"></span><span id="_CPPv2N12tensorrt_llm7runtime22GenericGenerationInput12badWordsListE"></span><span id="tensorrt_llm::runtime::GenericGenerationInput::badWordsList__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput_1a7fdba88ec2c4ef3a749bf6730a8427f4"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">badWordsList</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput12badWordsListE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput13stopWordsListE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime22GenericGenerationInput13stopWordsListE"></span><span id="_CPPv2N12tensorrt_llm7runtime22GenericGenerationInput13stopWordsListE"></span><span id="tensorrt_llm::runtime::GenericGenerationInput::stopWordsList__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput_1a13e840f74710c9ac836c64797652ebbe"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">stopWordsList</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput13stopWordsListE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput12maxNewTokensE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime22GenericGenerationInput12maxNewTokensE"></span><span id="_CPPv2N12tensorrt_llm7runtime22GenericGenerationInput12maxNewTokensE"></span><span id="tensorrt_llm::runtime::GenericGenerationInput::maxNewTokens__std::optional:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput_1aa56894695f6cdf383655e1e01fe8c3a3"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">maxNewTokens</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput12maxNewTokensE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput18promptTuningParamsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime22GenericGenerationInput18promptTuningParamsE"></span><span id="_CPPv2N12tensorrt_llm7runtime22GenericGenerationInput18promptTuningParamsE"></span><span id="tensorrt_llm::runtime::GenericGenerationInput::promptTuningParams__PromptTuningParams"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationInput_1a4da27c7a8e7b4bdd90c87c4bf9a08b46"></span><a class="reference internal" href="#_CPPv4I00EN12tensorrt_llm7runtime22GenericGenerationInputE" title="tensorrt_llm::runtime::GenericGenerationInput::PromptTuningParams"><span class="n"><span class="pre">PromptTuningParams</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">promptTuningParams</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime22GenericGenerationInput18promptTuningParamsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GenerationInputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GenerationInputE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GenerationInputE"></span><span id="tensorrt_llm::runtime::GenerationInput"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenerationInput"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GenerationInput</span></span></span><span class="w"> </span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="k"><span class="pre">public</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv412tensorrt_llm" title="tensorrt_llm"><span class="n"><span class="pre">tensorrt_llm</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimeE" title="tensorrt_llm::runtime"><span class="n"><span class="pre">runtime</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4I00EN12tensorrt_llm7runtime22GenericGenerationInputE" title="tensorrt_llm::runtime::GenericGenerationInput"><span class="n"><span class="pre">GenericGenerationInput</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParamsE" title="tensorrt_llm::runtime::PromptTuningParams"><span class="n"><span class="pre">PromptTuningParams</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GenerationInput4BaseE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GenerationInput4BaseE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GenerationInput4BaseE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenerationInput_1ac4231ce739fe28958d51d834024d92cd"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Base</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I00EN12tensorrt_llm7runtime22GenericGenerationInputE" title="tensorrt_llm::runtime::GenericGenerationInput"><span class="n"><span class="pre">GenericGenerationInput</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParamsE" title="tensorrt_llm::runtime::PromptTuningParams"><span class="n"><span class="pre">PromptTuningParams</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInput4BaseE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GenerationInput9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GenerationInput9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GenerationInput9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenerationInput_1ad525a655e0d2658c3f99dabb572acf1a"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInput4BaseE" title="tensorrt_llm::runtime::GenerationInput::Base"><span class="n"><span class="pre">Base</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">TensorPtr</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInput9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GenerationInput15GenerationInputEK8SizeTypeK8SizeType9TensorPtr9TensorPtrb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GenerationInput15GenerationInputEK8SizeTypeK8SizeType9TensorPtr9TensorPtrb"></span><span id="_CPPv2N12tensorrt_llm7runtime15GenerationInput15GenerationInputEK8SizeTypeK8SizeType9TensorPtr9TensorPtrb"></span><span id="tensorrt_llm::runtime::GenerationInput::GenerationInput__SizeTypeC.SizeTypeC.TensorPtr.TensorPtr.b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenerationInput_1a919fd8de0e3905a059b746f1e9e35dbe"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GenerationInput</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">endId</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">padId</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInput9TensorPtrE" title="tensorrt_llm::runtime::GenerationInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">ids</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInput9TensorPtrE" title="tensorrt_llm::runtime::GenerationInput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">lengths</span></span>, <span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">packed</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">false</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInput15GenerationInputEK8SizeTypeK8SizeType9TensorPtr9TensorPtrb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="generationoutput-h">
|
||
<h2>generationOutput.h<a class="headerlink" href="#generationoutput-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime23GenericGenerationOutputE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime23GenericGenerationOutputE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime23GenericGenerationOutputE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TTensor</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationOutput"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GenericGenerationOutput</span></span></span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime23GenericGenerationOutputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationOutput_1a739b5cbc24692f24b77a467612857e35"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime23GenericGenerationOutputE" title="tensorrt_llm::runtime::GenericGenerationOutput::TTensor"><span class="n"><span class="pre">TTensor</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput8CallbackE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime23GenericGenerationOutput8CallbackE"></span><span id="_CPPv2N12tensorrt_llm7runtime23GenericGenerationOutput8CallbackE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationOutput_1a6baa6c81999b6ed0748db81b7c820c78"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Callback</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">function</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">void</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n"><span class="pre">ids</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n"><span class="pre">step</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n"><span class="pre">finished</span></span><span class="p"><span class="pre">)</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput8CallbackE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput23GenericGenerationOutputE9TensorPtr9TensorPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime23GenericGenerationOutput23GenericGenerationOutputE9TensorPtr9TensorPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime23GenericGenerationOutput23GenericGenerationOutputE9TensorPtr9TensorPtr"></span><span id="tensorrt_llm::runtime::GenericGenerationOutput::GenericGenerationOutput__TensorPtr.TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationOutput_1a3ed16459b1913958c761070564be3754"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GenericGenerationOutput</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">ids</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">lengths</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput23GenericGenerationOutputE9TensorPtr9TensorPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput3idsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime23GenericGenerationOutput3idsE"></span><span id="_CPPv2N12tensorrt_llm7runtime23GenericGenerationOutput3idsE"></span><span id="tensorrt_llm::runtime::GenericGenerationOutput::ids__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationOutput_1a7ff8e99b46a473dbfc53aecc127449bd"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">ids</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput3idsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput7lengthsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime23GenericGenerationOutput7lengthsE"></span><span id="_CPPv2N12tensorrt_llm7runtime23GenericGenerationOutput7lengthsE"></span><span id="tensorrt_llm::runtime::GenericGenerationOutput::lengths__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationOutput_1a53bb028de3dd943d7d0913753e522aae"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">lengths</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput7lengthsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput11cumLogProbsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime23GenericGenerationOutput11cumLogProbsE"></span><span id="_CPPv2N12tensorrt_llm7runtime23GenericGenerationOutput11cumLogProbsE"></span><span id="tensorrt_llm::runtime::GenericGenerationOutput::cumLogProbs__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationOutput_1a3f7b1e14ccdaa0c7525f90d32e1c43d6"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cumLogProbs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput11cumLogProbsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput8logProbsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime23GenericGenerationOutput8logProbsE"></span><span id="_CPPv2N12tensorrt_llm7runtime23GenericGenerationOutput8logProbsE"></span><span id="tensorrt_llm::runtime::GenericGenerationOutput::logProbs__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationOutput_1ae28cb59770ea150c435484b4f7f453d3"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">logProbs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput8logProbsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput13contextLogitsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime23GenericGenerationOutput13contextLogitsE"></span><span id="_CPPv2N12tensorrt_llm7runtime23GenericGenerationOutput13contextLogitsE"></span><span id="tensorrt_llm::runtime::GenericGenerationOutput::contextLogits__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationOutput_1a884e4fabdeb57a635f796ddc36274abc"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">contextLogits</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput13contextLogitsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput16generationLogitsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime23GenericGenerationOutput16generationLogitsE"></span><span id="_CPPv2N12tensorrt_llm7runtime23GenericGenerationOutput16generationLogitsE"></span><span id="tensorrt_llm::runtime::GenericGenerationOutput::generationLogits__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationOutput_1ad76f135de78a3ab89804cbf3f7175d0f"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput9TensorPtrE" title="tensorrt_llm::runtime::GenericGenerationOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">generationLogits</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput16generationLogitsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput16onTokenGeneratedE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime23GenericGenerationOutput16onTokenGeneratedE"></span><span id="_CPPv2N12tensorrt_llm7runtime23GenericGenerationOutput16onTokenGeneratedE"></span><span id="tensorrt_llm::runtime::GenericGenerationOutput::onTokenGenerated__Callback"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericGenerationOutput_1a35249ba2dc1990149ddc5895c2e3a1f7"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput8CallbackE" title="tensorrt_llm::runtime::GenericGenerationOutput::Callback"><span class="n"><span class="pre">Callback</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">onTokenGenerated</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime23GenericGenerationOutput16onTokenGeneratedE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16GenerationOutputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16GenerationOutputE"></span><span id="_CPPv2N12tensorrt_llm7runtime16GenerationOutputE"></span><span id="tensorrt_llm::runtime::GenerationOutput"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenerationOutput"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GenerationOutput</span></span></span><span class="w"> </span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="k"><span class="pre">public</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv412tensorrt_llm" title="tensorrt_llm"><span class="n"><span class="pre">tensorrt_llm</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimeE" title="tensorrt_llm::runtime"><span class="n"><span class="pre">runtime</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime23GenericGenerationOutputE" title="tensorrt_llm::runtime::GenericGenerationOutput"><span class="n"><span class="pre">GenericGenerationOutput</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16GenerationOutput4BaseE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16GenerationOutput4BaseE"></span><span id="_CPPv2N12tensorrt_llm7runtime16GenerationOutput4BaseE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenerationOutput_1ad51e9ff641b7853ab71d1aa3d584bc68"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Base</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime23GenericGenerationOutputE" title="tensorrt_llm::runtime::GenericGenerationOutput"><span class="n"><span class="pre">GenericGenerationOutput</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutput4BaseE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16GenerationOutput9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16GenerationOutput9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime16GenerationOutput9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenerationOutput_1a5c7e8fe9eade02e97e6576ecfe16b0df"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutput4BaseE" title="tensorrt_llm::runtime::GenerationOutput::Base"><span class="n"><span class="pre">Base</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">TensorPtr</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutput9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16GenerationOutput16GenerationOutputE9TensorPtr9TensorPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16GenerationOutput16GenerationOutputE9TensorPtr9TensorPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime16GenerationOutput16GenerationOutputE9TensorPtr9TensorPtr"></span><span id="tensorrt_llm::runtime::GenerationOutput::GenerationOutput__TensorPtr.TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenerationOutput_1a0c21ff4190e449fe91a596650c8d2146"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GenerationOutput</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutput9TensorPtrE" title="tensorrt_llm::runtime::GenerationOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">ids</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutput9TensorPtrE" title="tensorrt_llm::runtime::GenerationOutput::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">lengths</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutput16GenerationOutputE9TensorPtr9TensorPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="gptdecoder-h">
|
||
<h2>gptDecoder.h<a class="headerlink" href="#gptdecoder-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm6layersE">
|
||
<span id="_CPPv3N12tensorrt_llm6layersE"></span><span id="_CPPv2N12tensorrt_llm6layersE"></span><span id="tensorrt_llm::layers"></span><span class="target" id="namespacetensorrt__llm_1_1layers"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">layers</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm6layersE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11IGptDecoderE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11IGptDecoderE"></span><span id="_CPPv2N12tensorrt_llm7runtime11IGptDecoderE"></span><span id="tensorrt_llm::runtime::IGptDecoder"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoder"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">IGptDecoder</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoderE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Subclassed by <a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1GptDecoder"><span class="std std-ref">tensorrt_llm::runtime::GptDecoder< T ></span></a></p>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11IGptDecoderD0Ev">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11IGptDecoderD0Ev"></span><span id="_CPPv2N12tensorrt_llm7runtime11IGptDecoderD0Ev"></span><span id="tensorrt_llm::runtime::IGptDecoder::~IGptDecoder"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoder_1a5ad01b4d1a088b47e56ce6bed969cb57"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">~IGptDecoder</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">default</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoderD0Ev" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_t8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_t8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_t8SizeType"></span><span id="tensorrt_llm::runtime::IGptDecoder::setup__SamplingConfigCR.s.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoder_1ab380759fa6e6e33a4a741d876e97298f"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setup</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="tensorrt_llm::runtime::SamplingConfig"><span class="n"><span class="pre">SamplingConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">samplingConfig</span></span>, <span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">batchSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxSequenceLength</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder5setupERK14SamplingConfig6size_t8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11IGptDecoder7forwardER14DecodingOutputRK13DecodingInput">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11IGptDecoder7forwardER14DecodingOutputRK13DecodingInput"></span><span id="_CPPv2N12tensorrt_llm7runtime11IGptDecoder7forwardER14DecodingOutputRK13DecodingInput"></span><span id="tensorrt_llm::runtime::IGptDecoder::forward__DecodingOutputR.DecodingInputCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoder_1a892c655936e25a38a7f0737fbfadfc1d"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forward</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutputE" title="tensorrt_llm::runtime::DecodingOutput"><span class="n"><span class="pre">DecodingOutput</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInputE" title="tensorrt_llm::runtime::DecodingInput"><span class="n"><span class="pre">DecodingInput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">input</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder7forwardER14DecodingOutputRK13DecodingInput" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput"></span><span id="_CPPv2N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput"></span><span id="tensorrt_llm::runtime::IGptDecoder::forwardAsync__DecodingOutputR.DecodingInputCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoder_1a8f87707fea456a6decd013b6b831d336"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forwardAsync</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutputE" title="tensorrt_llm::runtime::DecodingOutput"><span class="n"><span class="pre">DecodingOutput</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInputE" title="tensorrt_llm::runtime::DecodingInput"><span class="n"><span class="pre">DecodingInput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">input</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11IGptDecoder10gatherTreeER7ITensorRK14DecodingOutputRK13DecodingInputRK13BufferManager">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11IGptDecoder10gatherTreeER7ITensorRK14DecodingOutputRK13DecodingInputRK13BufferManager"></span><span id="_CPPv2N12tensorrt_llm7runtime11IGptDecoder10gatherTreeER7ITensorRK14DecodingOutputRK13DecodingInputRK13BufferManager"></span><span id="tensorrt_llm::runtime::IGptDecoder::gatherTree__ITensorR.DecodingOutputCR.DecodingInputCR.BufferManagerCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoder_1a3b5ff6b13809e1049979ce441c249fca"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">gatherTree</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">finalOutputIds</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutputE" title="tensorrt_llm::runtime::DecodingOutput"><span class="n"><span class="pre">DecodingOutput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">decodingOutput</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInputE" title="tensorrt_llm::runtime::DecodingInput"><span class="n"><span class="pre">DecodingInput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">decodingInput</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="tensorrt_llm::runtime::BufferManager"><span class="n"><span class="pre">BufferManager</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">manager</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder10gatherTreeER7ITensorRK14DecodingOutputRK13DecodingInputRK13BufferManager" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11IGptDecoder17getSamplingConfigEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11IGptDecoder17getSamplingConfigEv"></span><span id="_CPPv2N12tensorrt_llm7runtime11IGptDecoder17getSamplingConfigEv"></span><span id="tensorrt_llm::runtime::IGptDecoder::getSamplingConfig"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoder_1a15f6c7ed57d546c2bb0b1a50f3a6b9c7"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="tensorrt_llm::runtime::SamplingConfig"><span class="n"><span class="pre">SamplingConfig</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getSamplingConfig</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder17getSamplingConfigEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-functions">Public Static Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRKN13BufferManager13CudaStreamPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRKN13BufferManager13CudaStreamPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRKN13BufferManager13CudaStreamPtrE"></span><span id="tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByIds__ITensorCR.ITensorCR.ITensorCR.ITensorCR.ITensorR.ITensorCR.ITensorR.ITensorR.BufferManager::CudaStreamPtrCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoder_1a3be6cbd2637cebdae881fa260755acef"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">acceptDraftTokensByIds</span></span></span><span class="sig-paren">(</span><span class="k"><span class="pre">const</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">targetTokenIds</span></span>, <span class="k"><span class="pre">const</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">draftTokenIds</span></span>, <span class="k"><span class="pre">const</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">contextLengths</span></span>, <span class="k"><span class="pre">const</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">numDraftTokens</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">sequenceLengths</span></span>, <span class="k"><span class="pre">const</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">finishedVec</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">finishedFinal</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">finishedSum</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="tensorrt_llm::runtime::BufferManager"><span class="n"><span class="pre">BufferManager</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE" title="tensorrt_llm::runtime::BufferManager::CudaStreamPtr"><span class="n"><span class="pre">CudaStreamPtr</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">stream</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder22acceptDraftTokensByIdsERK7ITensorRK7ITensorRK7ITensorRK7ITensorR7ITensorRK7ITensorR7ITensorR7ITensorRKN13BufferManager13CudaStreamPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensor8SizeType8SizeTypebfP13curandState_tRKN13BufferManager13CudaStreamPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensor8SizeType8SizeTypebfP13curandState_tRKN13BufferManager13CudaStreamPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensor8SizeType8SizeTypebfP13curandState_tRKN13BufferManager13CudaStreamPtrE"></span><span id="tensorrt_llm::runtime::IGptDecoder::acceptDraftTokensByLogits__ITensorR.ITensorCR.ITensorR.ITensorR.ITensorCR.ITensorR.SizeType.SizeType.b.float.curandState_tP.BufferManager::CudaStreamPtrCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoder_1ac0e6eecf4416a6bdd1e176fedb0a86f1"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">acceptDraftTokensByLogits</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">draftLogits</span></span>, <span class="k"><span class="pre">const</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">targetLogits</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">draftProbs</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">targetProbs</span></span>, <span class="k"><span class="pre">const</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">numDraftTokens</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">finished</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">vocabSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">vocabSizePadded</span></span>, <span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">useRandomAcceptThreshold</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">randomAcceptThreshold</span></span>, <span class="n"><span class="pre">curandState_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">curandState</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="tensorrt_llm::runtime::BufferManager"><span class="n"><span class="pre">BufferManager</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE" title="tensorrt_llm::runtime::BufferManager::CudaStreamPtr"><span class="n"><span class="pre">CudaStreamPtr</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">stream</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder25acceptDraftTokensByLogitsER7ITensorRK7ITensorR7ITensorR7ITensorRK7ITensorR7ITensor8SizeType8SizeTypebfP13curandState_tRKN13BufferManager13CudaStreamPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createEN8nvinfer18DataTypeE6size_t6size_tRKN13BufferManager13CudaStreamPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11IGptDecoder6createEN8nvinfer18DataTypeE6size_t6size_tRKN13BufferManager13CudaStreamPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime11IGptDecoder6createEN8nvinfer18DataTypeE6size_t6size_tRKN13BufferManager13CudaStreamPtrE"></span><span id="tensorrt_llm::runtime::IGptDecoder::create__nvinfer1::DataType.s.s.BufferManager::CudaStreamPtrCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoder_1af9c668b9e5cdd2e0a65bfd55ba9b8b98"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unique_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoderE" title="tensorrt_llm::runtime::IGptDecoder"><span class="n"><span class="pre">IGptDecoder</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">create</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">dtype</span></span>, <span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">vocabSize</span></span>, <span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">vocabSizePadded</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="tensorrt_llm::runtime::BufferManager"><span class="n"><span class="pre">BufferManager</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE" title="tensorrt_llm::runtime::BufferManager::CudaStreamPtr"><span class="n"><span class="pre">CudaStreamPtr</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">stream</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoder6createEN8nvinfer18DataTypeE6size_t6size_tRKN13BufferManager13CudaStreamPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime10GptDecoderE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime10GptDecoderE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime10GptDecoderE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GptDecoder</span></span></span><span class="w"> </span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="k"><span class="pre">public</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv412tensorrt_llm" title="tensorrt_llm"><span class="n"><span class="pre">tensorrt_llm</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimeE" title="tensorrt_llm::runtime"><span class="n"><span class="pre">runtime</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoderE" title="tensorrt_llm::runtime::IGptDecoder"><span class="n"><span class="pre">IGptDecoder</span></span></a><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime10GptDecoderE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder13CudaStreamPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder13CudaStreamPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder13CudaStreamPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1a8b5c0f02247cc75b5d121681c1990d3b"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">CudaStreamPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="tensorrt_llm::runtime::BufferManager"><span class="n"><span class="pre">BufferManager</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManager13CudaStreamPtrE" title="tensorrt_llm::runtime::BufferManager::CudaStreamPtr"><span class="n"><span class="pre">CudaStreamPtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder13CudaStreamPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1ac3e1b92c75c404260a36d3d7e873231b"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderE6size_t6size_tRK13CudaStreamPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder10GptDecoderE6size_t6size_tRK13CudaStreamPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder10GptDecoderE6size_t6size_tRK13CudaStreamPtr"></span><span id="tensorrt_llm::runtime::GptDecoder::GptDecoder__s.s.CudaStreamPtrCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1a0cbdae7bd365d6175f9fe78a0237cc7c"></span><span class="sig-name descname"><span class="n"><span class="pre">GptDecoder</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">vocabSize</span></span>, <span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">vocabSizePadded</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder13CudaStreamPtrE" title="tensorrt_llm::runtime::GptDecoder::CudaStreamPtr"><span class="n"><span class="pre">CudaStreamPtr</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">stream</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder10GptDecoderE6size_t6size_tRK13CudaStreamPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_t8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_t8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_t8SizeType"></span><span id="tensorrt_llm::runtime::GptDecoder::setup__SamplingConfigCR.s.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1a54668226efcc5825da42b2f21c80e7b4"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setup</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="tensorrt_llm::runtime::SamplingConfig"><span class="n"><span class="pre">SamplingConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">samplingConfig</span></span>, <span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">batchSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxSequenceLength</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder5setupERK14SamplingConfig6size_t8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder7forwardER14DecodingOutputRK13DecodingInput">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder7forwardER14DecodingOutputRK13DecodingInput"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder7forwardER14DecodingOutputRK13DecodingInput"></span><span id="tensorrt_llm::runtime::GptDecoder::forward__DecodingOutputR.DecodingInputCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1a687dcb28ec2d720be9c35694250d346f"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forward</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutputE" title="tensorrt_llm::runtime::DecodingOutput"><span class="n"><span class="pre">DecodingOutput</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInputE" title="tensorrt_llm::runtime::DecodingInput"><span class="n"><span class="pre">DecodingInput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">input</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder7forwardER14DecodingOutputRK13DecodingInput" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput"></span><span id="tensorrt_llm::runtime::GptDecoder::forwardAsync__DecodingOutputR.DecodingInputCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1af707cd75a441ad7c639536c75459c65e"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forwardAsync</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutputE" title="tensorrt_llm::runtime::DecodingOutput"><span class="n"><span class="pre">DecodingOutput</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInputE" title="tensorrt_llm::runtime::DecodingInput"><span class="n"><span class="pre">DecodingInput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">input</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder12forwardAsyncER14DecodingOutputRK13DecodingInput" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder10gatherTreeER7ITensorRK14DecodingOutputRK13DecodingInputRK13BufferManager">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder10gatherTreeER7ITensorRK14DecodingOutputRK13DecodingInputRK13BufferManager"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder10gatherTreeER7ITensorRK14DecodingOutputRK13DecodingInputRK13BufferManager"></span><span id="tensorrt_llm::runtime::GptDecoder::gatherTree__ITensorR.DecodingOutputCR.DecodingInputCR.BufferManagerCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1ab5f5fba8712f080a59ae530dd8f9936b"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">gatherTree</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">finalOutputIds</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutputE" title="tensorrt_llm::runtime::DecodingOutput"><span class="n"><span class="pre">DecodingOutput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">decodingOutput</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInputE" title="tensorrt_llm::runtime::DecodingInput"><span class="n"><span class="pre">DecodingInput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">decodingInput</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="tensorrt_llm::runtime::BufferManager"><span class="n"><span class="pre">BufferManager</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">manager</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder10gatherTreeER7ITensorRK14DecodingOutputRK13DecodingInputRK13BufferManager" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder17getSamplingConfigEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder17getSamplingConfigEv"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder17getSamplingConfigEv"></span><span id="tensorrt_llm::runtime::GptDecoder::getSamplingConfig"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1a92d573f397311075a0c0f121bf774f60"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="tensorrt_llm::runtime::SamplingConfig"><span class="n"><span class="pre">SamplingConfig</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getSamplingConfig</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder17getSamplingConfigEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder8mManagerE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder8mManagerE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder8mManagerE"></span><span id="tensorrt_llm::runtime::GptDecoder::mManager__BufferManager"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1a8602244879ca7e9a83ccb7811cea26a8"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="tensorrt_llm::runtime::BufferManager"><span class="n"><span class="pre">BufferManager</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mManager</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder8mManagerE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder10mAllocatorE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder10mAllocatorE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder10mAllocatorE"></span><span id="tensorrt_llm::runtime::GptDecoder::mAllocator__common::CudaAllocator"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1a51093c91db9709a5cdb1d6004c19ae57"></span><span class="n"><span class="pre">common</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">CudaAllocator</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mAllocator</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder10mAllocatorE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder19mDynamicDecodeLayerE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder19mDynamicDecodeLayerE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder19mDynamicDecodeLayerE"></span><span id="tensorrt_llm::runtime::GptDecoder::mDynamicDecodeLayer__std::shared_ptr:tensorrt_llm::layers::DynamicDecodeLayer:T::"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1ae47acd96842e4ebc4f34af4fc4370746"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv412tensorrt_llm" title="tensorrt_llm"><span class="n"><span class="pre">tensorrt_llm</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm6layersE" title="tensorrt_llm::layers"><span class="n"><span class="pre">layers</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DynamicDecodeLayer</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime10GptDecoderE" title="tensorrt_llm::runtime::GptDecoder::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDynamicDecodeLayer</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder19mDynamicDecodeLayerE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder14mLogProbsTiledE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder14mLogProbsTiledE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder14mLogProbsTiledE"></span><span id="tensorrt_llm::runtime::GptDecoder::mLogProbsTiled__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1ac4a614d15044a39d9010ea86035ca326"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder9TensorPtrE" title="tensorrt_llm::runtime::GptDecoder::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mLogProbsTiled</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder14mLogProbsTiledE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptDecoder15mSamplingConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptDecoder15mSamplingConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptDecoder15mSamplingConfigE"></span><span id="tensorrt_llm::runtime::GptDecoder::mSamplingConfig__SamplingConfig"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoder_1ac921712531dd8bb357fe6787f036db97"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="tensorrt_llm::runtime::SamplingConfig"><span class="n"><span class="pre">SamplingConfig</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mSamplingConfig</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptDecoder15mSamplingConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="gptdecoderbatch-h">
|
||
<h2>gptDecoderBatch.h<a class="headerlink" href="#gptdecoderbatch-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatchE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatchE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatchE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GptDecoderBatch</span></span></span><span class="w"> </span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="k"><span class="pre">public</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv412tensorrt_llm" title="tensorrt_llm"><span class="n"><span class="pre">tensorrt_llm</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimeE" title="tensorrt_llm::runtime"><span class="n"><span class="pre">runtime</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatchE" title="tensorrt_llm::runtime::IGptDecoderBatch"><span class="n"><span class="pre">IGptDecoderBatch</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatchE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="docutils container">
|
||
<em>#include <gptDecoderBatch.h></em></div>
|
||
<p>GPT decoder class with support for in-flight batching. </p>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13CudaStreamPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch13CudaStreamPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch13CudaStreamPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a8206454db9d639c251910c03681a9ed0"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">CudaStreamPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStreamE" title="tensorrt_llm::runtime::CudaStream"><span class="n"><span class="pre">CudaStream</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13CudaStreamPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a593596978ca3ce5ce4f500702a42182e"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch15GptDecoderBatchENSt6size_tENSt6size_tE13CudaStreamPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch15GptDecoderBatchENSt6size_tENSt6size_tE13CudaStreamPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch15GptDecoderBatchENSt6size_tENSt6size_tE13CudaStreamPtr"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::GptDecoderBatch__std::s.std::s.CudaStreamPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1af478d2ea92161498aefa5ddb70d36262"></span><span class="sig-name descname"><span class="n"><span class="pre">GptDecoderBatch</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">vocabSize</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">vocabSizePadded</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13CudaStreamPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::CudaStreamPtr"><span class="n"><span class="pre">CudaStreamPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">stream</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch15GptDecoderBatchENSt6size_tENSt6size_tE13CudaStreamPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch5setupE8SizeType8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch5setupE8SizeType8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch5setupE8SizeType8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::setup__SizeType.SizeType.SizeType.SizeType.SizeType.nvinfer1::DataType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a70c4656323b556fe1e26a9b60cda7848"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setup</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxBatchSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxBeamWidth</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxAttentionWindow</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxSequenceLength</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxTokensPerStep</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">dtype</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch5setupE8SizeType8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Setup the decoder before calling <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1ab7e07276f33bfa6ef3c90baa49ee6eec"><span class="std std-ref"><span class="pre">forward()</span></span></a></code></p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch10newRequestE8SizeTypeRKN13decoder_batch7RequestERK14SamplingConfig">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch10newRequestE8SizeTypeRKN13decoder_batch7RequestERK14SamplingConfig"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch10newRequestE8SizeTypeRKN13decoder_batch7RequestERK14SamplingConfig"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::newRequest__SizeType.decoder_batch::RequestCR.SamplingConfigCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a7214c20bc16c253fd2cb199884cd9859"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">newRequest</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchIdx</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE" title="tensorrt_llm::runtime::decoder_batch"><span class="n"><span class="pre">decoder_batch</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7RequestE" title="tensorrt_llm::runtime::decoder_batch::Request"><span class="n"><span class="pre">Request</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">request</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="tensorrt_llm::runtime::SamplingConfig"><span class="n"><span class="pre">SamplingConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">samplingConfig</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch10newRequestE8SizeTypeRKN13decoder_batch7RequestERK14SamplingConfig" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Initialize the decoder at <code class="docutils literal notranslate"><span class="pre">batchIdx</span></code> with a new <code class="docutils literal notranslate"><span class="pre">request</span></code>. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::newBatch__GenerationInputCR.GenerationOutputCR.SamplingConfigCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a050019ac1971ebc1a8c816d9dd22d7b4"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">newBatch</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInputE" title="tensorrt_llm::runtime::GenerationInput"><span class="n"><span class="pre">GenerationInput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">inputs</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutputE" title="tensorrt_llm::runtime::GenerationOutput"><span class="n"><span class="pre">GenerationOutput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">outputs</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="tensorrt_llm::runtime::SamplingConfig"><span class="n"><span class="pre">SamplingConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">samplingConfig</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Initialize the decoder with new batch of inputs. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::forwardAsync__decoder_batch::OutputR.decoder_batch::InputCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1aa468001b519ad9767958cb8e660faea5"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="n"><span class="pre">TokenPtr</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forwardAsync</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE" title="tensorrt_llm::runtime::decoder_batch"><span class="n"><span class="pre">decoder_batch</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch6OutputE" title="tensorrt_llm::runtime::decoder_batch::Output"><span class="n"><span class="pre">Output</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE" title="tensorrt_llm::runtime::decoder_batch"><span class="n"><span class="pre">decoder_batch</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5InputE" title="tensorrt_llm::runtime::decoder_batch::Input"><span class="n"><span class="pre">Input</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">input</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Run one step for all requests without blocking the host process and return the token for synchronization. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch11forwardSyncERKN13decoder_batch5TokenE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch11forwardSyncERKN13decoder_batch5TokenE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch11forwardSyncERKN13decoder_batch5TokenE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::forwardSync__decoder_batch::TokenCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a495a39bf71a7d39cd81495834716760f"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forwardSync</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE" title="tensorrt_llm::runtime::decoder_batch"><span class="n"><span class="pre">decoder_batch</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5TokenE" title="tensorrt_llm::runtime::decoder_batch::Token"><span class="n"><span class="pre">Token</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">e</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch11forwardSyncERKN13decoder_batch5TokenE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Wait for the call to <code class="docutils literal notranslate"><span class="pre">forwardAsync</span></code> associated with a token to complete. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12forwardAsyncERN7decoder6OutputERKN7decoder5InputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch12forwardAsyncERN7decoder6OutputERKN7decoder5InputE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch12forwardAsyncERN7decoder6OutputERKN7decoder5InputE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::forwardAsync__decoder::OutputR.decoder::InputCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1ab0220317a75f65030f59878e26e3d737"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forwardAsync</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoderE" title="tensorrt_llm::runtime::decoder"><span class="n"><span class="pre">decoder</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder6OutputE" title="tensorrt_llm::runtime::decoder::Output"><span class="n"><span class="pre">Output</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoderE" title="tensorrt_llm::runtime::decoder"><span class="n"><span class="pre">decoder</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder5InputE" title="tensorrt_llm::runtime::decoder::Input"><span class="n"><span class="pre">Input</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">input</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12forwardAsyncERN7decoder6OutputERKN7decoder5InputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Run one step for all requests without blocking the host thread. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch11forwardSyncEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch11forwardSyncEv"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch11forwardSyncEv"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::forwardSync"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a4cfcadb7da525a74e3fa3143ccd56b53"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forwardSync</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch11forwardSyncEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Wait for the last call to <code class="docutils literal notranslate"><span class="pre">forwardAsync</span></code> to complete. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch11getFinishedEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch11getFinishedEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch11getFinishedEv"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::getFinishedC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a4c69dab125603dd2a4fbd9ab043afa30"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getFinished</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch11getFinishedEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[batchSize], indicators of finished requests </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch12getOutputIdsE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch12getOutputIdsE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch12getOutputIdsE8SizeType"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::getOutputIds__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a313a9ae3a464f84398b9ba038b4af554"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getOutputIds</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchIdx</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch12getOutputIdsE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p><strong>batchIdx</strong> – index of the batch </p>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>[maxBeamWidth, maxInputLength + maxNewTokens], contains input token ids and generated token ids without padding for request <code class="docutils literal notranslate"><span class="pre">batchIdx</span></code>, on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch12getOutputIdsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch12getOutputIdsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch12getOutputIdsEv"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::getOutputIdsC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a445fc8f3f0db689b2166cb15fdc63df2"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getOutputIds</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch12getOutputIdsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[batchSize, maxBeamWidth, maxInputLength + maxNewTokens], contains input token ids and generated token ids without padding, on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch8finalizeE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch8finalizeE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch8finalizeE8SizeType"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::finalize__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a95478c97710c43b25c91dbe3aa9544b3"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="tensorrt_llm::runtime::CudaEvent"><span class="n"><span class="pre">CudaEvent</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">finalize</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchIdx</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch8finalizeE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Gather final beam search results for request <code class="docutils literal notranslate"><span class="pre">batchIdx</span></code>. Result will only be available after event returned. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch8finalizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch8finalizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch8finalizeEv"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::finalizeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a28208992ea3e90e60712d07ed05e8a72"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">finalize</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch8finalizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Gather final beam search results for all requests. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch12getParentIdsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch12getParentIdsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch12getParentIdsEv"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::getParentIdsC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a93178ec5242faf2de970d4d017352dae"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getParentIds</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch12getParentIdsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[batchSize, maxBeamWidth, maxInputLength + maxNewTokens], contains parent ids collected during beam search without padding, on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch14getCumLogProbsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch14getCumLogProbsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch14getCumLogProbsEv"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::getCumLogProbsC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a3c07c5204d41a4dfdf688a4482d510bb"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getCumLogProbs</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch14getCumLogProbsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[batchSize, maxBeamWidth], cumulative log probabilities (per beam), on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch14getCumLogProbsE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch14getCumLogProbsE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch14getCumLogProbsE8SizeType"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::getCumLogProbs__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1ac93b3755a416298a93a7cc7263c49c9c"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getCumLogProbs</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchIdx</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch14getCumLogProbsE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[maxBeamWidth], cumulative log probabilities (per beam), on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch11getLogProbsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch11getLogProbsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch11getLogProbsEv"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::getLogProbsC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a9c8cbfc561d34e459d677c1031588cf9"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getLogProbs</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch11getLogProbsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[batchSize, maxBeamWidth, maxSequenceLength], log probabilities (per beam), on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch11getLogProbsE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch11getLogProbsE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch11getLogProbsE8SizeType"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::getLogProbs__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a92033458c848a4f94e7ab2c4f9516c1e"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getLogProbs</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchIdx</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch11getLogProbsE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[maxBeamWidth, maxSequenceLength], log probabilities (per beam), on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch15getAllNewTokensEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch15getAllNewTokensEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch15getAllNewTokensEv"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::getAllNewTokensC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a8217e98da5b107d12401590d80eeb976"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getAllNewTokens</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch15getAllNewTokensEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Get maxTokensPerStep tokens generated in the last forward pass. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[maxTokensPerStep, batchSize, maxBeamWidth], tokens generated in last forward pass, on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch12getNewTokensE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch12getNewTokensE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch12getNewTokensE8SizeType"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::getNewTokens__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1ac08d8a77d78b71ff527ecd5999cc16d2"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getNewTokens</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">iter</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch12getNewTokensE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Get tokens generated in one step of last forward pass. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p><strong>iter</strong> – The iteration within [0; maxTokensPerStep) for which to get the tokens </p>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>[batchSize, beamWidth], tokens generated in <code class="docutils literal notranslate"><span class="pre">iter</span></code> (per beam), on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch10getNbStepsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch10getNbStepsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch10getNbStepsEv"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::getNbStepsC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a9c9a6a07562637a290ed93e987bd06a7"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getNbSteps</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch10getNbStepsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[batchSize], the number of generation steps executed on each request </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch13getNbFinishedEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch13getNbFinishedEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch13getNbFinishedEv"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::getNbFinishedC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a7c4d967f7646e5a78f50d4ac6844be93"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getNbFinished</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch13getNbFinishedEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[1], number of finished sequences, in pinned host memory </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-types">Private Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13GptDecoderPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch13GptDecoderPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch13GptDecoderPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1adbc3e2ab6fcff2a86fee1974fd2ea358"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GptDecoderPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unique_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11IGptDecoderE" title="tensorrt_llm::runtime::IGptDecoder"><span class="n"><span class="pre">IGptDecoder</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13GptDecoderPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16DecodingInputPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch16DecodingInputPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch16DecodingInputPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1aebed7ff7ea091a472908a7d2cc468684"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DecodingInputPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unique_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13DecodingInputE" title="tensorrt_llm::runtime::DecodingInput"><span class="n"><span class="pre">DecodingInput</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16DecodingInputPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch17DecodingOutputPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch17DecodingOutputPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch17DecodingOutputPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a8b297105bd88a4066694adf8a91d4073"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DecodingOutputPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unique_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DecodingOutputE" title="tensorrt_llm::runtime::DecodingOutput"><span class="n"><span class="pre">DecodingOutput</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch17DecodingOutputPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-functions">Private Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch18postProcessRequestE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime15GptDecoderBatch18postProcessRequestE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime15GptDecoderBatch18postProcessRequestE8SizeType"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::postProcessRequest__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a7c4def0f8b1239b53724fbf6cf576b12"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="tensorrt_llm::runtime::CudaEvent"><span class="n"><span class="pre">CudaEvent</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">postProcessRequest</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchIdx</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime15GptDecoderBatch18postProcessRequestE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Gather final beam search results for request <code class="docutils literal notranslate"><span class="pre">batchIdx</span></code>. </p>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch10mVocabSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch10mVocabSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch10mVocabSizeE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mVocabSize__std::sC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a65caae45851a98064c90efb4e69fd5be"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mVocabSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch10mVocabSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16mVocabSizePaddedE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch16mVocabSizePaddedE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch16mVocabSizePaddedE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mVocabSizePadded__std::sC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a6a3edc3073a3affe187f9344568d5349"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mVocabSizePadded</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16mVocabSizePaddedE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch7mStreamE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch7mStreamE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch7mStreamE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mStream__CudaStreamPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a33675102b6406b35993f06c59508b4fd"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13CudaStreamPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::CudaStreamPtr"><span class="n"><span class="pre">CudaStreamPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mStream</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch7mStreamE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch14mBufferManagerE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch14mBufferManagerE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch14mBufferManagerE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mBufferManager__BufferManager"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a73a99bf969ac6a13872b1b93f443bc2d"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="tensorrt_llm::runtime::BufferManager"><span class="n"><span class="pre">BufferManager</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mBufferManager</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch14mBufferManagerE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13mForwardTokenE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch13mForwardTokenE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch13mForwardTokenE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mForwardToken__TokenPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1abe39442ac571c5827d98ec295bd0513c"></span><span class="n"><span class="pre">TokenPtr</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mForwardToken</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13mForwardTokenE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13mForwardEventE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch13mForwardEventE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch13mForwardEventE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mForwardEvent__CudaEvent"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a9d42242aa2aac2bffd0387a6272f57f9"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="tensorrt_llm::runtime::CudaEvent"><span class="n"><span class="pre">CudaEvent</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mForwardEvent</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13mForwardEventE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch8mStreamsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch8mStreamsE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch8mStreamsE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mStreams__std::vector:CudaStreamPtr:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a5b1a9b00ef30809bef69336e5adfcc6c"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13CudaStreamPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::CudaStreamPtr"><span class="n"><span class="pre">CudaStreamPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mStreams</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch8mStreamsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9mDecodersE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch9mDecodersE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch9mDecodersE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mDecoders__std::vector:GptDecoderPtr:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a656cea9abf1ea0c8b3697a79ab51dde9"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13GptDecoderPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::GptDecoderPtr"><span class="n"><span class="pre">GptDecoderPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDecoders</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9mDecodersE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch15mDecodingInputsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch15mDecodingInputsE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch15mDecodingInputsE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mDecodingInputs__std::vector:DecodingInputPtr:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1aeb33339a3b75a2152134fdacd2660786"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16DecodingInputPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::DecodingInputPtr"><span class="n"><span class="pre">DecodingInputPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDecodingInputs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch15mDecodingInputsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16mDecodingOutputsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch16mDecodingOutputsE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch16mDecodingOutputsE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mDecodingOutputs__std::vector:DecodingOutputPtr:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1ab1c5ab4afe168288cb33331a486d5be8"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch17DecodingOutputPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::DecodingOutputPtr"><span class="n"><span class="pre">DecodingOutputPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDecodingOutputs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16mDecodingOutputsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch19mJointDecodingInputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch19mJointDecodingInputE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch19mJointDecodingInputE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mJointDecodingInput__DecodingInputPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a73642bc20fd9bcd68b262edd55d4d2a7"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16DecodingInputPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::DecodingInputPtr"><span class="n"><span class="pre">DecodingInputPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mJointDecodingInput</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch19mJointDecodingInputE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch20mJointDecodingOutputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch20mJointDecodingOutputE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch20mJointDecodingOutputE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mJointDecodingOutput__DecodingOutputPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a09890f57577749180eb23ba792989e96"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch17DecodingOutputPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::DecodingOutputPtr"><span class="n"><span class="pre">DecodingOutputPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mJointDecodingOutput</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch20mJointDecodingOutputE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch14mDraftTokenIdsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch14mDraftTokenIdsE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch14mDraftTokenIdsE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mDraftTokenIds__std::vector:TensorPtr:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1aae2a553d3c59b1f3d0de3c1205a68673"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDraftTokenIds</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch14mDraftTokenIdsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12mDraftLogitsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch12mDraftLogitsE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch12mDraftLogitsE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mDraftLogits__std::vector:TensorPtr:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a1d8cc482b234869894cb75802a84457d"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDraftLogits</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12mDraftLogitsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch15mAcceptByLogitsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch15mAcceptByLogitsE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch15mAcceptByLogitsE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mAcceptByLogits__std::vector:b:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1add4954c40b66f5cd29f15326d83f0d23"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mAcceptByLogits</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch15mAcceptByLogitsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch15mNumDraftTokensE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch15mNumDraftTokensE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch15mNumDraftTokensE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mNumDraftTokens__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1ac9a6914fb43e482d6da7c26ce69f0519"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mNumDraftTokens</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch15mNumDraftTokensE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13mCurandStatesE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch13mCurandStatesE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch13mCurandStatesE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mCurandStates__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a182eb5969447169037eadb734138e6b7"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mCurandStates</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13mCurandStatesE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch8mNbStepsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch8mNbStepsE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch8mNbStepsE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mNbSteps__std::vector:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1ab82d738a6ee4eb24160c4203f50ba47b"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mNbSteps</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch8mNbStepsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9mFinishedE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch9mFinishedE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch9mFinishedE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mFinished__std::vector:b:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a4bacfb74153463dd2ea29e9e58d62139"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mFinished</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9mFinishedE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12mFinishedSumE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch12mFinishedSumE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch12mFinishedSumE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mFinishedSum__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a5e29dd7a16e6dcfdbc6af1f5a30d454d"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mFinishedSum</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12mFinishedSumE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13mMaxNewTokensE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch13mMaxNewTokensE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch13mMaxNewTokensE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mMaxNewTokens__std::vector:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1adda26d8626cb810bd54f0eae099f81d6"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mMaxNewTokens</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch13mMaxNewTokensE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch11mBeamWidthsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch11mBeamWidthsE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch11mBeamWidthsE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mBeamWidths__std::vector:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a62af2790978fdbdce912bb55d1538c7a"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mBeamWidths</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch11mBeamWidthsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch23mGeneratedTokensPerStepE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch23mGeneratedTokensPerStepE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch23mGeneratedTokensPerStepE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mGeneratedTokensPerStep__std::vector:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a88c38b63243a4f3b2f2593dc57803be2"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mGeneratedTokensPerStep</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch23mGeneratedTokensPerStepE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch14mFinishedStepsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch14mFinishedStepsE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch14mFinishedStepsE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mFinishedSteps__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1abe9d67818cff6708e78b0b23a010fe59"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mFinishedSteps</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch14mFinishedStepsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch11mDraftProbsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch11mDraftProbsE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch11mDraftProbsE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mDraftProbs__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1ac91bf42fb15e82f745a929df086b9612"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDraftProbs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch11mDraftProbsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12mTargetProbsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch12mTargetProbsE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch12mTargetProbsE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mTargetProbs__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a545d6c68ca6c6dc7ea49dce14891630f"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::GptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mTargetProbs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch12mTargetProbsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch18mMaxSequenceLengthE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch18mMaxSequenceLengthE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch18mMaxSequenceLengthE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mMaxSequenceLength__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a17b9d45dd6c74bddca33b2edb555fe3c"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mMaxSequenceLength</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch18mMaxSequenceLengthE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch19mMaxAttentionWindowE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch19mMaxAttentionWindowE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch19mMaxAttentionWindowE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mMaxAttentionWindow__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a0df27b74f4c7ecbde4473a5c12b7fd97"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mMaxAttentionWindow</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch19mMaxAttentionWindowE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16mActualBatchSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch16mActualBatchSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch16mActualBatchSizeE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mActualBatchSize__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1a7e2f18c7b2ebe3d76b568c46380e92c4"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mActualBatchSize</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch16mActualBatchSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch17mMaxTokensPerStepE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime15GptDecoderBatch17mMaxTokensPerStepE"></span><span id="_CPPv2N12tensorrt_llm7runtime15GptDecoderBatch17mMaxTokensPerStepE"></span><span id="tensorrt_llm::runtime::GptDecoderBatch::mMaxTokensPerStep__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptDecoderBatch_1aab9825732279e411e112af18cb11a25e"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mMaxTokensPerStep</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime15GptDecoderBatch17mMaxTokensPerStepE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="gptjsonconfig-h">
|
||
<h2>gptJsonConfig.h<a class="headerlink" href="#gptjsonconfig-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13GptJsonConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13GptJsonConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime13GptJsonConfigE"></span><span id="tensorrt_llm::runtime::GptJsonConfig"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GptJsonConfig</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE8SizeType8SizeTypeRK14GptModelConfig">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE8SizeType8SizeTypeRK14GptModelConfig"></span><span id="_CPPv2N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE8SizeType8SizeTypeRK14GptModelConfig"></span><span id="tensorrt_llm::runtime::GptJsonConfig::GptJsonConfig__ss.ss.ss.SizeType.SizeType.GptModelConfigCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1aefa732b931baed06f6bf789a65944123"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GptJsonConfig</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">name</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">version</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">precision</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">tensorParallelism</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">pipelineParallelism</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfigE" title="tensorrt_llm::runtime::GptModelConfig"><span class="n"><span class="pre">GptModelConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">modelConfig</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig13GptJsonConfigENSt6stringENSt6stringENSt6stringE8SizeType8SizeTypeRK14GptModelConfig" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getModelConfigEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13GptJsonConfig14getModelConfigEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13GptJsonConfig14getModelConfigEv"></span><span id="tensorrt_llm::runtime::GptJsonConfig::getModelConfigC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1a124fb0206f4ac3ff47629bcb8147589d"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfigE" title="tensorrt_llm::runtime::GptModelConfig"><span class="n"><span class="pre">GptModelConfig</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getModelConfig</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14getModelConfigEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig7getNameEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13GptJsonConfig7getNameEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13GptJsonConfig7getNameEv"></span><span id="tensorrt_llm::runtime::GptJsonConfig::getNameC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1a929bf268a1dd42fa06b6d05834bd6646"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getName</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig7getNameEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig10getVersionEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13GptJsonConfig10getVersionEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13GptJsonConfig10getVersionEv"></span><span id="tensorrt_llm::runtime::GptJsonConfig::getVersionC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1a633c67c2eb9b4c589957537e1908da14"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getVersion</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig10getVersionEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getPrecisionEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13GptJsonConfig12getPrecisionEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13GptJsonConfig12getPrecisionEv"></span><span id="tensorrt_llm::runtime::GptJsonConfig::getPrecisionC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1ab5c3f3e5854ebdbd1b0f0d26fa8c2a6f"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getPrecision</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getPrecisionEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig20getTensorParallelismEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13GptJsonConfig20getTensorParallelismEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13GptJsonConfig20getTensorParallelismEv"></span><span id="tensorrt_llm::runtime::GptJsonConfig::getTensorParallelismCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1af3d5d313552e8497406ce3ae6b18bc11"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getTensorParallelism</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig20getTensorParallelismEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig22getPipelineParallelismEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13GptJsonConfig22getPipelineParallelismEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13GptJsonConfig22getPipelineParallelismEv"></span><span id="tensorrt_llm::runtime::GptJsonConfig::getPipelineParallelismCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1a2ec48773fe7b568d771f53770d9b6b0d"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getPipelineParallelism</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig22getPipelineParallelismEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getWorldSizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13GptJsonConfig12getWorldSizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13GptJsonConfig12getWorldSizeEv"></span><span id="tensorrt_llm::runtime::GptJsonConfig::getWorldSizeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1a589461cb3bd53963212f1eda119d7f2e"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getWorldSize</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig12getWorldSizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE"></span><span id="_CPPv2NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE"></span><span id="tensorrt_llm::runtime::GptJsonConfig::engineFilename__WorldConfigCR.ssCRC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1ac663861699ef7f573f64d5fdb89f14af"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">engineFilename</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="tensorrt_llm::runtime::WorldConfig"><span class="n"><span class="pre">WorldConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">worldConfig</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">model</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfigRKNSt6stringE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig"></span><span id="_CPPv2NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig"></span><span id="tensorrt_llm::runtime::GptJsonConfig::engineFilename__WorldConfigCRC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1a9ce08952a809fbe5859a685215dd7258"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">engineFilename</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="tensorrt_llm::runtime::WorldConfig"><span class="n"><span class="pre">WorldConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">worldConfig</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13GptJsonConfig14engineFilenameERK11WorldConfig" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-functions">Public Static Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE"></span><span id="_CPPv2N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE"></span><span id="tensorrt_llm::runtime::GptJsonConfig::parse__ssCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1a258c808e0e2c5445c807ae2f0a257782"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfigE" title="tensorrt_llm::runtime::GptJsonConfig"><span class="n"><span class="pre">GptJsonConfig</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">parse</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">json</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt6stringE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE"></span><span id="_CPPv2N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE"></span><span id="tensorrt_llm::runtime::GptJsonConfig::parse__isR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1af74ea4db9854b1f0ddd8aaa0d4a48f39"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfigE" title="tensorrt_llm::runtime::GptJsonConfig"><span class="n"><span class="pre">GptJsonConfig</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">parse</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">istream</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">json</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERNSt7istreamE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE"></span><span id="_CPPv2N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE"></span><span id="tensorrt_llm::runtime::GptJsonConfig::parse__std::filesystem::pathCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1a959c20c852124ced898b12bbdeb5d79f"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfigE" title="tensorrt_llm::runtime::GptJsonConfig"><span class="n"><span class="pre">GptJsonConfig</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">parse</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">filesystem</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">path</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">path</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5parseERKNSt10filesystem4pathE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5mNameE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13GptJsonConfig5mNameE"></span><span id="_CPPv2N12tensorrt_llm7runtime13GptJsonConfig5mNameE"></span><span id="tensorrt_llm::runtime::GptJsonConfig::mName__ssC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1aa23cc7f0c9ad465ffdb3c1950876b470"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mName</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig5mNameE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13GptJsonConfig8mVersionE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13GptJsonConfig8mVersionE"></span><span id="_CPPv2N12tensorrt_llm7runtime13GptJsonConfig8mVersionE"></span><span id="tensorrt_llm::runtime::GptJsonConfig::mVersion__ssC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1a254b88b5fe490e3835177dd32ecb2c8f"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mVersion</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig8mVersionE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13GptJsonConfig10mPrecisionE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13GptJsonConfig10mPrecisionE"></span><span id="_CPPv2N12tensorrt_llm7runtime13GptJsonConfig10mPrecisionE"></span><span id="tensorrt_llm::runtime::GptJsonConfig::mPrecision__ssC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1acf01c9bba53cd18d0ece1026ef19e485"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mPrecision</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig10mPrecisionE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13GptJsonConfig18mTensorParallelismE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13GptJsonConfig18mTensorParallelismE"></span><span id="_CPPv2N12tensorrt_llm7runtime13GptJsonConfig18mTensorParallelismE"></span><span id="tensorrt_llm::runtime::GptJsonConfig::mTensorParallelism__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1a48b4d443ddb453b3349799486f020a3d"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mTensorParallelism</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig18mTensorParallelismE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13GptJsonConfig20mPipelineParallelismE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13GptJsonConfig20mPipelineParallelismE"></span><span id="_CPPv2N12tensorrt_llm7runtime13GptJsonConfig20mPipelineParallelismE"></span><span id="tensorrt_llm::runtime::GptJsonConfig::mPipelineParallelism__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1ac469f1b66356d8ba919e63939aa26cf9"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mPipelineParallelism</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig20mPipelineParallelismE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13GptJsonConfig15mGptModelConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13GptJsonConfig15mGptModelConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime13GptJsonConfig15mGptModelConfigE"></span><span id="tensorrt_llm::runtime::GptJsonConfig::mGptModelConfig__GptModelConfigC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptJsonConfig_1a74a9d093ba911cfd9c09008a29124537"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfigE" title="tensorrt_llm::runtime::GptModelConfig"><span class="n"><span class="pre">GptModelConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mGptModelConfig</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13GptJsonConfig15mGptModelConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="gptmodelconfig-h">
|
||
<h2>gptModelConfig.h<a class="headerlink" href="#gptmodelconfig-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfigE"></span><span id="tensorrt_llm::runtime::GptModelConfig"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GptModelConfig</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp enum-class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig12ModelVariantE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig12ModelVariantE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig12ModelVariantE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a5ab7e0ffcb31d8d6d19afd863370a635"></span><span class="k"><span class="pre">enum</span></span><span class="w"> </span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">ModelVariant</span></span></span><span class="w"> </span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int32_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12ModelVariantE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p><em>Values:</em></p>
|
||
<dl class="cpp enumerator">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig12ModelVariant4kGptE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig12ModelVariant4kGptE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig12ModelVariant4kGptE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a5ab7e0ffcb31d8d6d19afd863370a635aeb854c1219d60212d16ad06f0d454dc8"></span><span class="k"><span class="pre">enumerator</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kGpt</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12ModelVariant4kGptE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp enumerator">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig12ModelVariant4kGlmE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig12ModelVariant4kGlmE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig12ModelVariant4kGlmE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a5ab7e0ffcb31d8d6d19afd863370a635a30a41043cc5346b26f02b1a3e1cf54d5"></span><span class="k"><span class="pre">enumerator</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kGlm</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12ModelVariant4kGlmE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig14GptModelConfigE8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig14GptModelConfigE8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig14GptModelConfigE8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::GptModelConfig::GptModelConfig__SizeType.SizeType.SizeType.SizeType.nvinfer1::DataTypeCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a93a4b8bc5df2e1a25d4b876fdefb1ff6"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GptModelConfig</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">vocabSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">nbLayers</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">nbHeads</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">hiddenSize</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">dtype</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig14GptModelConfigE8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig12getVocabSizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig12getVocabSizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig12getVocabSizeEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getVocabSizeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1aff992ef62ed1999326b48800913b2bee"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getVocabSize</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig12getVocabSizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig18getVocabSizePaddedE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig18getVocabSizePaddedE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig18getVocabSizePaddedE8SizeType"></span><span id="tensorrt_llm::runtime::GptModelConfig::getVocabSizePadded__SizeTypeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1acf1d9e9818c254ee026c012388025480"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getVocabSizePadded</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">worldSize</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig18getVocabSizePaddedE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig11getNbLayersE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig11getNbLayersE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig11getNbLayersE8SizeType"></span><span id="tensorrt_llm::runtime::GptModelConfig::getNbLayers__SizeTypeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a527a93c79413842c6706295232b0b9ed"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getNbLayers</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">pipelineParallelism</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">1</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig11getNbLayersE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig10getNbHeadsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig10getNbHeadsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig10getNbHeadsEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getNbHeadsCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a00ef36e3eb9bd188a911b7f80c345e0f"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getNbHeads</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig10getNbHeadsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig12getNbKvHeadsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig12getNbKvHeadsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig12getNbKvHeadsEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getNbKvHeadsCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a51a65e744ce4675cbdaaff83f16f2c54"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getNbKvHeads</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig12getNbKvHeadsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig12setNbKvHeadsE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig12setNbKvHeadsE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig12setNbKvHeadsE8SizeType"></span><span id="tensorrt_llm::runtime::GptModelConfig::setNbKvHeads__SizeTypeCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ad837f99f5aafdcc1ef7baa15c86617b5"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setNbKvHeads</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">nbKvHeads</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12setNbKvHeadsE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig13getHiddenSizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig13getHiddenSizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig13getHiddenSizeEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getHiddenSizeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a9df3d4f4da4ad6c30e6c91419d6b268f"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getHiddenSize</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig13getHiddenSizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig14getSizePerHeadEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig14getSizePerHeadEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig14getSizePerHeadEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getSizePerHeadCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a70409542e05a302a44ac2d571aea25db"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getSizePerHead</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig14getSizePerHeadEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig11getDataTypeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig11getDataTypeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig11getDataTypeEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getDataTypeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ab0dd6dd6a8b7cacfe4f60716066f8613"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getDataType</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig11getDataTypeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig21useGptAttentionPluginEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig21useGptAttentionPluginEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig21useGptAttentionPluginEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::useGptAttentionPluginCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a2eedc76ee7dc4712de143bcdc02f40f9"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">useGptAttentionPlugin</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig21useGptAttentionPluginEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig21useGptAttentionPluginEb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig21useGptAttentionPluginEb"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig21useGptAttentionPluginEb"></span><span id="tensorrt_llm::runtime::GptModelConfig::useGptAttentionPlugin__bCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ac3723398406d29b02be8a06912ee0d82"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">useGptAttentionPlugin</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">useGptAttentionPlugin</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig21useGptAttentionPluginEb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig14usePackedInputEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig14usePackedInputEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig14usePackedInputEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::usePackedInputCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a4894eb60ae226002fda29841977f7935"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">usePackedInput</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig14usePackedInputEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig14usePackedInputEb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig14usePackedInputEb"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig14usePackedInputEb"></span><span id="tensorrt_llm::runtime::GptModelConfig::usePackedInput__bCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1af71f4a0b8a8a8fc6e21ea28612b81ed1"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">usePackedInput</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">inputPacked</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig14usePackedInputEb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15usePagedKvCacheEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig15usePagedKvCacheEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig15usePagedKvCacheEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::usePagedKvCacheCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a173a85af1a71420f692612ca00c87d69"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">usePagedKvCache</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15usePagedKvCacheEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig15usePagedKvCacheEb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig15usePagedKvCacheEb"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig15usePagedKvCacheEb"></span><span id="tensorrt_llm::runtime::GptModelConfig::usePagedKvCache__bCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a80165e232642897d7c4fb621bb61fed3"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">usePagedKvCache</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">pagedKvCache</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15usePagedKvCacheEb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig17getTokensPerBlockEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig17getTokensPerBlockEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig17getTokensPerBlockEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getTokensPerBlockCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a0fa158a8e4b14102c6ee79a717d40879"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getTokensPerBlock</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig17getTokensPerBlockEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig17setTokensPerBlockE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig17setTokensPerBlockE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig17setTokensPerBlockE8SizeType"></span><span id="tensorrt_llm::runtime::GptModelConfig::setTokensPerBlock__SizeTypeCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a443a5a8b94f03dd8b0a8fbbec298d3f8"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setTokensPerBlock</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">TokensPerBlock</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig17setTokensPerBlockE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig12getQuantModeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig12getQuantModeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig12getQuantModeEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getQuantModeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1aa35c989f165bd8aa9437c3c6ba7d0a75"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="n"><span class="pre">common</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">QuantMode</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getQuantMode</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig12getQuantModeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig12setQuantModeEN6common9QuantModeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig12setQuantModeEN6common9QuantModeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig12setQuantModeEN6common9QuantModeE"></span><span id="tensorrt_llm::runtime::GptModelConfig::setQuantMode__common::QuantModeCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a41fe2aa1fdd76ce76301859981425417"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setQuantMode</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">common</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">QuantMode</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">QuantMode</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12setQuantModeEN6common9QuantModeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig24supportsInflightBatchingEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig24supportsInflightBatchingEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig24supportsInflightBatchingEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::supportsInflightBatchingCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a275c4804ce2373f0c977c7a5f2ddd2a0"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">supportsInflightBatching</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig24supportsInflightBatchingEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getMaxBatchSizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig15getMaxBatchSizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig15getMaxBatchSizeEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getMaxBatchSizeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a24b66ade6d982663d81fa7b42d9c6055"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getMaxBatchSize</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getMaxBatchSizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setMaxBatchSizeE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig15setMaxBatchSizeE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig15setMaxBatchSizeE8SizeType"></span><span id="tensorrt_llm::runtime::GptModelConfig::setMaxBatchSize__SizeTypeCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ab784bd1a00eb729f402abe8875b564ea"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setMaxBatchSize</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxBatchSize</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setMaxBatchSizeE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getMaxBeamWidthEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig15getMaxBeamWidthEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig15getMaxBeamWidthEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getMaxBeamWidthCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ae882051a3ab7b4d5f1027fb95e4b5907"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getMaxBeamWidth</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getMaxBeamWidthEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setMaxBeamWidthE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig15setMaxBeamWidthE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig15setMaxBeamWidthE8SizeType"></span><span id="tensorrt_llm::runtime::GptModelConfig::setMaxBeamWidth__SizeTypeCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a6f5145cdde241d9418f28a42051b5e61"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setMaxBeamWidth</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxBeamWidth</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setMaxBeamWidthE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig14getMaxInputLenEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig14getMaxInputLenEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig14getMaxInputLenEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getMaxInputLenCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1af1e370c6c5bbf9dfc854e12c14cccb79"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getMaxInputLen</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig14getMaxInputLenEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig14setMaxInputLenE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig14setMaxInputLenE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig14setMaxInputLenE8SizeType"></span><span id="tensorrt_llm::runtime::GptModelConfig::setMaxInputLen__SizeTypeCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ab80523799abed725a58348c4d56c8ad8"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setMaxInputLen</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxInputLen</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig14setMaxInputLenE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getMaxOutputLenEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig15getMaxOutputLenEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig15getMaxOutputLenEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getMaxOutputLenCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1aaa48e78ace7bb49aa634f3cb84ed7ac4"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getMaxOutputLen</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getMaxOutputLenEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setMaxOutputLenE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig15setMaxOutputLenE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig15setMaxOutputLenE8SizeType"></span><span id="tensorrt_llm::runtime::GptModelConfig::setMaxOutputLen__SizeTypeCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ab5e91bd0f16db6355ab0e0a14378658a"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setMaxOutputLen</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxOutputLen</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setMaxOutputLenE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getMaxNumTokensEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig15getMaxNumTokensEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig15getMaxNumTokensEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getMaxNumTokensCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a5065aee21fa4e99f5c52bad69117a5cb"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getMaxNumTokens</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getMaxNumTokensEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setMaxNumTokensENSt8optionalI8SizeTypeEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig15setMaxNumTokensENSt8optionalI8SizeTypeEE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig15setMaxNumTokensENSt8optionalI8SizeTypeEE"></span><span id="tensorrt_llm::runtime::GptModelConfig::setMaxNumTokens__std::optional:SizeType:CE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a06b325b04c1b396a0430320435f81373"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setMaxNumTokens</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="n sig-param"><span class="pre">maxNumTokens</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setMaxNumTokensENSt8optionalI8SizeTypeEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15usePromptTuningEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig15usePromptTuningEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig15usePromptTuningEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::usePromptTuningCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a14410c2939a2c4a7e82ec3d37cb5e767"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">usePromptTuning</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15usePromptTuningEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig30getMaxPromptEmbeddingTableSizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig30getMaxPromptEmbeddingTableSizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig30getMaxPromptEmbeddingTableSizeEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getMaxPromptEmbeddingTableSizeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a0e61bbb5092e714899e7296c10499ded"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getMaxPromptEmbeddingTableSize</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig30getMaxPromptEmbeddingTableSizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig30setMaxPromptEmbeddingTableSizeE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig30setMaxPromptEmbeddingTableSizeE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig30setMaxPromptEmbeddingTableSizeE8SizeType"></span><span id="tensorrt_llm::runtime::GptModelConfig::setMaxPromptEmbeddingTableSize__SizeTypeCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ae8c2698780f6ab43ccf08cf58730f395"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setMaxPromptEmbeddingTableSize</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxPromptEmbeddingTableSize</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig30setMaxPromptEmbeddingTableSizeE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig20computeContextLogitsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig20computeContextLogitsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig20computeContextLogitsEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::computeContextLogitsCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a2f0e4d2c822ec1a83c858674ffce5ec2"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">computeContextLogits</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig20computeContextLogitsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig20computeContextLogitsEb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig20computeContextLogitsEb"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig20computeContextLogitsEb"></span><span id="tensorrt_llm::runtime::GptModelConfig::computeContextLogits__bCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a33188908109cfcc7baa824e284a1af8e"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">computeContextLogits</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">computeContextLogits</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig20computeContextLogitsEb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig23computeGenerationLogitsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig23computeGenerationLogitsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig23computeGenerationLogitsEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::computeGenerationLogitsCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ac92c3cb52036f92bfe70515fd828137b"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">computeGenerationLogits</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig23computeGenerationLogitsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig23computeGenerationLogitsEb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig23computeGenerationLogitsEb"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig23computeGenerationLogitsEb"></span><span id="tensorrt_llm::runtime::GptModelConfig::computeGenerationLogits__bCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a715acca463b00c872f9d37b4dc0c1de9"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">computeGenerationLogits</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">computeGenerationLogits</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig23computeGenerationLogitsEb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getModelVariantEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig15getModelVariantEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig15getModelVariantEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getModelVariantC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a9e832f202599100dfac6af143f8c72b4"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12ModelVariantE" title="tensorrt_llm::runtime::GptModelConfig::ModelVariant"><span class="n"><span class="pre">ModelVariant</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getModelVariant</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig15getModelVariantEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setModelVariantE12ModelVariant">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig15setModelVariantE12ModelVariant"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig15setModelVariantE12ModelVariant"></span><span id="tensorrt_llm::runtime::GptModelConfig::setModelVariant__ModelVariant"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a5fd810a5a863b75656d6c0914b2d5762"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setModelVariant</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12ModelVariantE" title="tensorrt_llm::runtime::GptModelConfig::ModelVariant"><span class="n"><span class="pre">ModelVariant</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">modelVariant</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15setModelVariantE12ModelVariant" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig18useCustomAllReduceEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig18useCustomAllReduceEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig18useCustomAllReduceEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::useCustomAllReduceCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a392c5d57f071a1a36fa628580975faf9"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">useCustomAllReduce</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig18useCustomAllReduceEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig18useCustomAllReduceEb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig18useCustomAllReduceEb"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig18useCustomAllReduceEb"></span><span id="tensorrt_llm::runtime::GptModelConfig::useCustomAllReduce__bCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a79e7448c925f5d6785575250d7a1971f"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">useCustomAllReduce</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">customAllReduce</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig18useCustomAllReduceEb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig14setMaxDraftLenE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig14setMaxDraftLenE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig14setMaxDraftLenE8SizeType"></span><span id="tensorrt_llm::runtime::GptModelConfig::setMaxDraftLen__SizeTypeCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ac96cb0cf174bb295ff5a2508d33ee749"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setMaxDraftLen</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxDraftLen</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig14setMaxDraftLenE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig14getMaxDraftLenEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig14getMaxDraftLenEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig14getMaxDraftLenEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getMaxDraftLenC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a859eba2f2493fb140863844b89c3b992"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getMaxDraftLen</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig14getMaxDraftLenEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig19getMaxTokensPerStepEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig19getMaxTokensPerStepEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig19getMaxTokensPerStepEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getMaxTokensPerStepCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ac202c324c51a94e74473a1ea2c264eac"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getMaxTokensPerStep</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig19getMaxTokensPerStepEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig30setUseContextFMHAForGenerationEb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig30setUseContextFMHAForGenerationEb"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig30setUseContextFMHAForGenerationEb"></span><span id="tensorrt_llm::runtime::GptModelConfig::setUseContextFMHAForGeneration__bCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a5797c6c67bb2515bb86775181f9aafbc"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setUseContextFMHAForGeneration</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">useContextFMHAForGeneration</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig30setUseContextFMHAForGenerationEb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig27getContextFMHAForGenerationEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig27getContextFMHAForGenerationEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig27getContextFMHAForGenerationEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getContextFMHAForGenerationCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ab0a189b6918177de1545d6632acea793"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getContextFMHAForGeneration</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig27getContextFMHAForGenerationEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig19setPagedContextFMHAEb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig19setPagedContextFMHAEb"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig19setPagedContextFMHAEb"></span><span id="tensorrt_llm::runtime::GptModelConfig::setPagedContextFMHA__bCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a81098c7ddcc5557c3278a40f056f1cd9"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setPagedContextFMHA</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">pagedContextFMHA</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig19setPagedContextFMHAEb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14GptModelConfig19getPagedContextFMHAEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14GptModelConfig19getPagedContextFMHAEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14GptModelConfig19getPagedContextFMHAEv"></span><span id="tensorrt_llm::runtime::GptModelConfig::getPagedContextFMHACCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a6f65a9c4d3bcf2a5772b5f9bd5f164e8"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getPagedContextFMHA</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14GptModelConfig19getPagedContextFMHAEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig10mVocabSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig10mVocabSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig10mVocabSizeE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mVocabSize__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a18e1092a5c44a311577bc4954efc9ad8"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mVocabSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig10mVocabSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig9mNbLayersE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig9mNbLayersE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig9mNbLayersE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mNbLayers__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a83dd559a542a2ebfe932387d4bc65faa"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mNbLayers</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig9mNbLayersE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig8mNbHeadsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig8mNbHeadsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig8mNbHeadsE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mNbHeads__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a3aed4484b10e66d10c0f2e330aea1f06"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mNbHeads</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig8mNbHeadsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig10mNbKvHeadsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig10mNbKvHeadsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig10mNbKvHeadsE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mNbKvHeads__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1aafe290665c7ed003ec2347f04f1a54a5"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mNbKvHeads</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig10mNbKvHeadsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig11mHiddenSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig11mHiddenSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig11mHiddenSizeE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mHiddenSize__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a43e64ac4881c3a9eee58b7dee25964e2"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mHiddenSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig11mHiddenSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig9mDataTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig9mDataTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig9mDataTypeE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mDataType__nvinfer1::DataType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a497a3a345c3e48362790139c6fe56526"></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDataType</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig9mDataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig22mUseGptAttentionPluginE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig22mUseGptAttentionPluginE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig22mUseGptAttentionPluginE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mUseGptAttentionPlugin__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a2c837cd8fccbcae0427ccb0334ddd9d2"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mUseGptAttentionPlugin</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig22mUseGptAttentionPluginE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig12mInputPackedE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig12mInputPackedE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig12mInputPackedE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mInputPacked__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a780f8ca1c1f7565694104b0fa5bf45fb"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mInputPacked</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12mInputPackedE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mPagedKvCacheE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig13mPagedKvCacheE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig13mPagedKvCacheE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mPagedKvCache__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a2b70f372d6c64c92f1ad003043dcdb52"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mPagedKvCache</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mPagedKvCacheE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig15mTokensPerBlockE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig15mTokensPerBlockE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig15mTokensPerBlockE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mTokensPerBlock__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1aa5ad1102f45507190c50ccfbd74f0788"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mTokensPerBlock</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig15mTokensPerBlockE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig10mQuantModeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig10mQuantModeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig10mQuantModeE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mQuantMode__common::QuantMode"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a9a5da6ac7818f7df4f68e3306653598b"></span><span class="n"><span class="pre">common</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">QuantMode</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mQuantMode</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig10mQuantModeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mMaxBatchSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig13mMaxBatchSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig13mMaxBatchSizeE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mMaxBatchSize__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a8714ccf704b0a20be40bb99e229c2439"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mMaxBatchSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mMaxBatchSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mMaxBeamWidthE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig13mMaxBeamWidthE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig13mMaxBeamWidthE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mMaxBeamWidth__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a7d2bcd870c8e96cd525f689e5f4a4391"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mMaxBeamWidth</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mMaxBeamWidthE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig12mMaxInputLenE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig12mMaxInputLenE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig12mMaxInputLenE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mMaxInputLen__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ab4be5cfe878d1333c6add3b824b6a7e4"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mMaxInputLen</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12mMaxInputLenE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mMaxOutputLenE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig13mMaxOutputLenE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig13mMaxOutputLenE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mMaxOutputLen__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1adc7f72184ca681976df8197f475942c2"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mMaxOutputLen</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mMaxOutputLenE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mMaxNumTokensE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig13mMaxNumTokensE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig13mMaxNumTokensE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mMaxNumTokens__std::optional:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1aa20bf7021d240c626fa6210511c31c47"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mMaxNumTokens</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mMaxNumTokensE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig21mComputeContextLogitsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig21mComputeContextLogitsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig21mComputeContextLogitsE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mComputeContextLogits__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a49736d7c35c69ae8eb50892e69dcfeb3"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mComputeContextLogits</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig21mComputeContextLogitsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig24mComputeGenerationLogitsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig24mComputeGenerationLogitsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig24mComputeGenerationLogitsE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mComputeGenerationLogits__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a73f45ad3401a6c92d9b4727fb45b4485"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mComputeGenerationLogits</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig24mComputeGenerationLogitsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mModelVariantE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig13mModelVariantE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig13mModelVariantE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mModelVariant__ModelVariant"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ae45c6e3f4a0ae12a5df7ba02281b544e"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12ModelVariantE" title="tensorrt_llm::runtime::GptModelConfig::ModelVariant"><span class="n"><span class="pre">ModelVariant</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mModelVariant</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig13mModelVariantE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig19mUseCustomAllReduceE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig19mUseCustomAllReduceE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig19mUseCustomAllReduceE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mUseCustomAllReduce__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a2475ff83565a03603f3a3e61425320d6"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mUseCustomAllReduce</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig19mUseCustomAllReduceE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig28mMaxPromptEmbeddingTableSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig28mMaxPromptEmbeddingTableSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig28mMaxPromptEmbeddingTableSizeE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mMaxPromptEmbeddingTableSize__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a49acc82c17323e998fc0efdcc5e28ecd"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mMaxPromptEmbeddingTableSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig28mMaxPromptEmbeddingTableSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig12mMaxDraftLenE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig12mMaxDraftLenE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig12mMaxDraftLenE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mMaxDraftLen__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1a9e91f1f08560ab2853f0e983409daf45"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mMaxDraftLen</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig12mMaxDraftLenE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig28mUseContextFMHAForGenerationE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig28mUseContextFMHAForGenerationE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig28mUseContextFMHAForGenerationE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mUseContextFMHAForGeneration__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ab356aeff83dcb888b9cd7d3b52600e94"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mUseContextFMHAForGeneration</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig28mUseContextFMHAForGenerationE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14GptModelConfig17mPagedContextFMHAE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14GptModelConfig17mPagedContextFMHAE"></span><span id="_CPPv2N12tensorrt_llm7runtime14GptModelConfig17mPagedContextFMHAE"></span><span id="tensorrt_llm::runtime::GptModelConfig::mPagedContextFMHA__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptModelConfig_1ab3d224a56d091d293dc93a21881c5a78"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mPagedContextFMHA</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfig17mPagedContextFMHAE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="gptsession-h">
|
||
<h2>gptSession.h<a class="headerlink" href="#gptsession-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm13batch_managerE">
|
||
<span id="_CPPv3N12tensorrt_llm13batch_managerE"></span><span id="_CPPv2N12tensorrt_llm13batch_managerE"></span><span id="tensorrt_llm::batch_manager"></span><span class="target" id="namespacetensorrt__llm_1_1batch__manager"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">batch_manager</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm13batch_managerE" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm13batch_manager16kv_cache_managerE">
|
||
<span id="_CPPv3N12tensorrt_llm13batch_manager16kv_cache_managerE"></span><span id="_CPPv2N12tensorrt_llm13batch_manager16kv_cache_managerE"></span><span id="tensorrt_llm::batch_manager::kv_cache_manager"></span><span class="target" id="namespacetensorrt__llm_1_1batch__manager_1_1kv__cache__manager"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kv_cache_manager</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm13batch_manager16kv_cache_managerE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSessionE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSessionE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSessionE"></span><span id="tensorrt_llm::runtime::GptSession"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GptSession</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSessionE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession9LoggerPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession9LoggerPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession9LoggerPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1abf601de29903bb11af9d3d2976ea08a6"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">LoggerPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">ILogger</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession9LoggerPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr"></span><span id="tensorrt_llm::runtime::GptSession::GptSession__ConfigCR.GptModelConfigCR.WorldConfigCR.voidCP.std::s.LoggerPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a8f3776eb2f369f36460b77e660078686"></span><span class="sig-name descname"><span class="n"><span class="pre">GptSession</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6ConfigE" title="tensorrt_llm::runtime::GptSession::Config"><span class="n"><span class="pre">Config</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">sessionConfig</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfigE" title="tensorrt_llm::runtime::GptModelConfig"><span class="n"><span class="pre">GptModelConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">modelConfig</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="tensorrt_llm::runtime::WorldConfig"><span class="n"><span class="pre">WorldConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">worldConfig</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">engineBuffer</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">engineSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession9LoggerPtrE" title="tensorrt_llm::runtime::GptSession::LoggerPtr"><span class="n"><span class="pre">LoggerPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">logger</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">nullptr</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigPKvNSt6size_tE9LoggerPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigRKNSt6vectorI7uint8_tEE9LoggerPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigRKNSt6vectorI7uint8_tEE9LoggerPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigRKNSt6vectorI7uint8_tEE9LoggerPtr"></span><span id="tensorrt_llm::runtime::GptSession::GptSession__ConfigCR.GptModelConfigCR.WorldConfigCR.std::vector:uint8_t:CR.LoggerPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a08881cdd06f59f2f5988bd267aafcf99"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GptSession</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6ConfigE" title="tensorrt_llm::runtime::GptSession::Config"><span class="n"><span class="pre">Config</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">sessionConfig</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfigE" title="tensorrt_llm::runtime::GptModelConfig"><span class="n"><span class="pre">GptModelConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">modelConfig</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="tensorrt_llm::runtime::WorldConfig"><span class="n"><span class="pre">WorldConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">worldConfig</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">uint8_t</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">engineBuffer</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession9LoggerPtrE" title="tensorrt_llm::runtime::GptSession::LoggerPtr"><span class="n"><span class="pre">LoggerPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">logger</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">nullptr</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigRKNSt6vectorI7uint8_tEE9LoggerPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigRKNSt6stringE9LoggerPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigRKNSt6stringE9LoggerPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigRKNSt6stringE9LoggerPtr"></span><span id="tensorrt_llm::runtime::GptSession::GptSession__ConfigCR.GptModelConfigCR.WorldConfigCR.ssCR.LoggerPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a968c21746698cf88e117bbd0fb9e81fe"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GptSession</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6ConfigE" title="tensorrt_llm::runtime::GptSession::Config"><span class="n"><span class="pre">Config</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">sessionConfig</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfigE" title="tensorrt_llm::runtime::GptModelConfig"><span class="n"><span class="pre">GptModelConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">modelConfig</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="tensorrt_llm::runtime::WorldConfig"><span class="n"><span class="pre">WorldConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">worldConfig</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">engineFile</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession9LoggerPtrE" title="tensorrt_llm::runtime::GptSession::LoggerPtr"><span class="n"><span class="pre">LoggerPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">logger</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">nullptr</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession10GptSessionERK6ConfigRK14GptModelConfigRK11WorldConfigRKNSt6stringE9LoggerPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10GptSession9getLoggerEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10GptSession9getLoggerEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime10GptSession9getLoggerEv"></span><span id="tensorrt_llm::runtime::GptSession::getLoggerC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a3fa9a3cb9db8934ff06b1df13063b2f3"></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">ILogger</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getLogger</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession9getLoggerEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10GptSession16getBufferManagerEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10GptSession16getBufferManagerEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime10GptSession16getBufferManagerEv"></span><span id="tensorrt_llm::runtime::GptSession::getBufferManagerC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a57a73dc8c994ce28207da1331377a08b"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="tensorrt_llm::runtime::BufferManager"><span class="n"><span class="pre">BufferManager</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getBufferManager</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession16getBufferManagerEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10GptSession14getModelConfigEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10GptSession14getModelConfigEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime10GptSession14getModelConfigEv"></span><span id="tensorrt_llm::runtime::GptSession::getModelConfigC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1aafeb2d6a1276ed948457924d1a54e744"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfigE" title="tensorrt_llm::runtime::GptModelConfig"><span class="n"><span class="pre">GptModelConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getModelConfig</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession14getModelConfigEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10GptSession14getWorldConfigEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10GptSession14getWorldConfigEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime10GptSession14getWorldConfigEv"></span><span id="tensorrt_llm::runtime::GptSession::getWorldConfigC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a8921d43edbec6aa0b9ba6a6894505542"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="tensorrt_llm::runtime::WorldConfig"><span class="n"><span class="pre">WorldConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getWorldConfig</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession14getWorldConfigEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10GptSession9getDeviceEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10GptSession9getDeviceEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime10GptSession9getDeviceEv"></span><span id="tensorrt_llm::runtime::GptSession::getDeviceC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a94905fac580c8d0cd5b26b7fe319e853"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getDevice</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession9getDeviceEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession8generateER16GenerationOutputRK15GenerationInputRK14SamplingConfig">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession8generateER16GenerationOutputRK15GenerationInputRK14SamplingConfig"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession8generateER16GenerationOutputRK15GenerationInputRK14SamplingConfig"></span><span id="tensorrt_llm::runtime::GptSession::generate__GenerationOutputR.GenerationInputCR.SamplingConfigCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a55d90d8c6fccd7de2975d20ded7e4e42"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">generate</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutputE" title="tensorrt_llm::runtime::GenerationOutput"><span class="n"><span class="pre">GenerationOutput</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">outputs</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInputE" title="tensorrt_llm::runtime::GenerationInput"><span class="n"><span class="pre">GenerationInput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">inputs</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="tensorrt_llm::runtime::SamplingConfig"><span class="n"><span class="pre">SamplingConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">samplingConfig</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession8generateER16GenerationOutputRK15GenerationInputRK14SamplingConfig" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-types">Private Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession14KvCacheManagerE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession14KvCacheManagerE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession14KvCacheManagerE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a17734c9adff9c0c3dd37d104c9c20879"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">KvCacheManager</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm13batch_managerE" title="tensorrt_llm::batch_manager"><span class="n"><span class="pre">batch_manager</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm13batch_manager16kv_cache_managerE" title="tensorrt_llm::batch_manager::kv_cache_manager"><span class="n"><span class="pre">kv_cache_manager</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">KVCacheManager</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14KvCacheManagerE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession13KvCacheConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession13KvCacheConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession13KvCacheConfigE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a14e12e3a0354f7faa6497a29fb8a4c90"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">KvCacheConfig</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm13batch_managerE" title="tensorrt_llm::batch_manager"><span class="n"><span class="pre">batch_manager</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm13batch_manager16kv_cache_managerE" title="tensorrt_llm::batch_manager::kv_cache_manager"><span class="n"><span class="pre">kv_cache_manager</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">KvCacheConfig</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession13KvCacheConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a3f4d6f00907ec557418c31614d991df4"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimeE" title="tensorrt_llm::runtime"><span class="n"><span class="pre">runtime</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession22TokenGeneratedCallbackE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession22TokenGeneratedCallbackE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession22TokenGeneratedCallbackE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a15194437f183d58237ab0c8af3878b23"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TokenGeneratedCallback</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">function</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">void</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n"><span class="pre">step</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n"><span class="pre">finished</span></span><span class="p"><span class="pre">)</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession22TokenGeneratedCallbackE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-functions">Private Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession13useCudaGraphsEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession13useCudaGraphsEv"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession13useCudaGraphsEv"></span><span id="tensorrt_llm::runtime::GptSession::useCudaGraphs"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1adae7d88300e62c0e18178dc9962ffd07"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">useCudaGraphs</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession13useCudaGraphsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession15generateBatchedERNSt6vectorI16GenerationOutputEERKNSt6vectorI15GenerationInputEERK14SamplingConfigRK22TokenGeneratedCallback">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession15generateBatchedERNSt6vectorI16GenerationOutputEERKNSt6vectorI15GenerationInputEERK14SamplingConfigRK22TokenGeneratedCallback"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession15generateBatchedERNSt6vectorI16GenerationOutputEERKNSt6vectorI15GenerationInputEERK14SamplingConfigRK22TokenGeneratedCallback"></span><span id="tensorrt_llm::runtime::GptSession::generateBatched__std::vector:GenerationOutput:R.std::vector:GenerationInput:CR.SamplingConfigCR.TokenGeneratedCallbackCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a7fa116048db82b70aa2c733ba4fd16c8"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">generateBatched</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutputE" title="tensorrt_llm::runtime::GenerationOutput"><span class="n"><span class="pre">GenerationOutput</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">microBatchesOutputs</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInputE" title="tensorrt_llm::runtime::GenerationInput"><span class="n"><span class="pre">GenerationInput</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">microBatchesInputs</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="tensorrt_llm::runtime::SamplingConfig"><span class="n"><span class="pre">SamplingConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">samplingConfig</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession22TokenGeneratedCallbackE" title="tensorrt_llm::runtime::GptSession::TokenGeneratedCallback"><span class="n"><span class="pre">TokenGeneratedCallback</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">onTokenGenerated</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession15generateBatchedERNSt6vectorI16GenerationOutputEERKNSt6vectorI15GenerationInputEERK14SamplingConfigRK22TokenGeneratedCallback" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession5setupERK6Config">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession5setupERK6Config"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession5setupERK6Config"></span><span id="tensorrt_llm::runtime::GptSession::setup__ConfigCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a1dbeea870aaae467ecfe6961bb2bf259"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setup</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6ConfigE" title="tensorrt_llm::runtime::GptSession::Config"><span class="n"><span class="pre">Config</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">sessionConfig</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession5setupERK6Config" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession14createContextsE8SizeType8SizeTypeb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession14createContextsE8SizeType8SizeTypeb"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession14createContextsE8SizeType8SizeTypeb"></span><span id="tensorrt_llm::runtime::GptSession::createContexts__SizeType.SizeType.b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1ae3759d6bf2b60f7ac4a7959431d278a5"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">createContexts</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">numBatchesCtx</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">numBatchesGen</span></span>, <span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">useCudaGraphs</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14createContextsE8SizeType8SizeTypeb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession13createBuffersE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession13createBuffersE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession13createBuffersE8SizeType"></span><span id="tensorrt_llm::runtime::GptSession::createBuffers__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a9a0d4e7b740eff3848b6cb2d15d99608"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">createBuffers</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">numMicroBatches</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession13createBuffersE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeEb8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession14createDecodersE8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeEb8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession14createDecodersE8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeEb8SizeType"></span><span id="tensorrt_llm::runtime::GptSession::createDecoders__SizeType.SizeType.SizeType.SizeType.nvinfer1::DataType.b.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a0e57411defaeba60af4959e722fdbbcd"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">createDecoders</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">beamWidth</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxAttentionWindow</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxSequenceLength</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">logitsType</span></span>, <span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">decoderPerRequest</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">numMicroBatches</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14createDecodersE8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeEb8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE8SizeType8SizeType8SizeType8SizeTypeRK13KvCacheConfig">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE8SizeType8SizeType8SizeType8SizeTypeRK13KvCacheConfig"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE8SizeType8SizeType8SizeType8SizeTypeRK13KvCacheConfig"></span><span id="tensorrt_llm::runtime::GptSession::createKvCacheManager__SizeType.SizeType.SizeType.SizeType.KvCacheConfigCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1adbd9c3936108564cbdc84a5563535523"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">createKvCacheManager</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">beamWidth</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxAttentionWindow</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxSequenceLength</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession13KvCacheConfigE" title="tensorrt_llm::runtime::GptSession::KvCacheConfig"><span class="n"><span class="pre">KvCacheConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">config</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession20createKvCacheManagerE8SizeType8SizeType8SizeType8SizeTypeRK13KvCacheConfig" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession30createCustomAllReduceWorkspaceE8SizeType8SizeType8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession30createCustomAllReduceWorkspaceE8SizeType8SizeType8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession30createCustomAllReduceWorkspaceE8SizeType8SizeType8SizeType"></span><span id="tensorrt_llm::runtime::GptSession::createCustomAllReduceWorkspace__SizeType.SizeType.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a761e1bcaecfcd45d43b9737a97f88ef4"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">createCustomAllReduceWorkspace</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">beamWidth</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxSequenceLength</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession30createCustomAllReduceWorkspaceE8SizeType8SizeType8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession18executeContextStepERKNSt6vectorI15GenerationInputEERKNSt6vectorI8SizeTypeEEPK14KvCacheManager">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession18executeContextStepERKNSt6vectorI15GenerationInputEERKNSt6vectorI8SizeTypeEEPK14KvCacheManager"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession18executeContextStepERKNSt6vectorI15GenerationInputEERKNSt6vectorI8SizeTypeEEPK14KvCacheManager"></span><span id="tensorrt_llm::runtime::GptSession::executeContextStep__std::vector:GenerationInput:CR.std::vector:SizeType:CR.KvCacheManagerCP"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1ab9c9713ffbacf77261cc0a71d9b04414"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">executeContextStep</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInputE" title="tensorrt_llm::runtime::GenerationInput"><span class="n"><span class="pre">GenerationInput</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">microBatches</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">microBatchOffsets</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14KvCacheManagerE" title="tensorrt_llm::runtime::GptSession::KvCacheManager"><span class="n"><span class="pre">KvCacheManager</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">kvCacheManager</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession18executeContextStepERKNSt6vectorI15GenerationInputEERKNSt6vectorI8SizeTypeEEPK14KvCacheManager" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession21executeGenerationStepE8SizeTypeRKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI8SizeTypeEEP14KvCacheManagerRNSt6vectorIbEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession21executeGenerationStepE8SizeTypeRKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI8SizeTypeEEP14KvCacheManagerRNSt6vectorIbEE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession21executeGenerationStepE8SizeTypeRKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI8SizeTypeEEP14KvCacheManagerRNSt6vectorIbEE"></span><span id="tensorrt_llm::runtime::GptSession::executeGenerationStep__SizeType.std::vector:GenerationInput:CR.std::vector:GenerationOutput:R.std::vector:SizeType:CR.KvCacheManagerP.std::vector:b:R"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1aaca25dd333bb7b4f2c4f5ddf700edacd"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">executeGenerationStep</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">step</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInputE" title="tensorrt_llm::runtime::GenerationInput"><span class="n"><span class="pre">GenerationInput</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">microBatchesInputs</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutputE" title="tensorrt_llm::runtime::GenerationOutput"><span class="n"><span class="pre">GenerationOutput</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">microBatchesOutputs</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">microBatchOffsets</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14KvCacheManagerE" title="tensorrt_llm::runtime::GptSession::KvCacheManager"><span class="n"><span class="pre">KvCacheManager</span></span></a><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">kvCacheManager</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">microBatchesFinished</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession21executeGenerationStepE8SizeTypeRKNSt6vectorI15GenerationInputEERNSt6vectorI16GenerationOutputEERKNSt6vectorI8SizeTypeEEP14KvCacheManagerRNSt6vectorIbEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession16decoderStepAsyncE8SizeType8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession16decoderStepAsyncE8SizeType8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession16decoderStepAsyncE8SizeType8SizeType"></span><span id="tensorrt_llm::runtime::GptSession::decoderStepAsync__SizeType.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1ab03cc4c728c2da8c0767efdc515af402"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">decoderStepAsync</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">decoderStep</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">microBatchId</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession16decoderStepAsyncE8SizeType8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Execute decoder on last PP rank, receive decoder output on other PP ranks. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession14shouldStopSyncE8SizeType8SizeType8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession14shouldStopSyncE8SizeType8SizeType8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession14shouldStopSyncE8SizeType8SizeType8SizeType"></span><span id="tensorrt_llm::runtime::GptSession::shouldStopSync__SizeType.SizeType.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a4d2ef8994105f56856cd3e44666611e2"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">shouldStopSync</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">beamWidth</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">microBatchId</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14shouldStopSyncE8SizeType8SizeType8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Synchronize with the decoder and return the <code class="docutils literal notranslate"><span class="pre">shouldStop</span></code> flag. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession8finalizeE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession8finalizeE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession8finalizeE8SizeType"></span><span id="tensorrt_llm::runtime::GptSession::finalize__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a49b547cc837f1c9dde99201e90a71156"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">finalize</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">microBatchId</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession8finalizeE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Collect final output ids and log probs on last PP rank and send them to first PP rank. </p>
|
||
<p>Receives are asynchronous on host, so synchronization is required before access. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession19kvCacheAddSequencesE8SizeType8SizeType8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession19kvCacheAddSequencesE8SizeType8SizeType8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession19kvCacheAddSequencesE8SizeType8SizeType8SizeType"></span><span id="tensorrt_llm::runtime::GptSession::kvCacheAddSequences__SizeType.SizeType.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a35035e8a6a38dd38f94571fb237721c8"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kvCacheAddSequences</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">beamWidth</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">microBatchId</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">firstBatchIdx</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession19kvCacheAddSequencesE8SizeType8SizeType8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10GptSession11initDecoderER7ITensorRK15GenerationInputRK16GenerationOutputRK14SamplingConfig8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10GptSession11initDecoderER7ITensorRK15GenerationInputRK16GenerationOutputRK14SamplingConfig8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime10GptSession11initDecoderER7ITensorRK15GenerationInputRK16GenerationOutputRK14SamplingConfig8SizeType"></span><span id="tensorrt_llm::runtime::GptSession::initDecoder__ITensorR.GenerationInputCR.GenerationOutputCR.SamplingConfigCR.SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a25e761e649ffe025d0df642d71544501"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">initDecoder</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">outputIds</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInputE" title="tensorrt_llm::runtime::GenerationInput"><span class="n"><span class="pre">GenerationInput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">inputs</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutputE" title="tensorrt_llm::runtime::GenerationOutput"><span class="n"><span class="pre">GenerationOutput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">outputs</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="tensorrt_llm::runtime::SamplingConfig"><span class="n"><span class="pre">SamplingConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">samplingConfig</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">microBatchId</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession11initDecoderER7ITensorRK15GenerationInputRK16GenerationOutputRK14SamplingConfig8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Populate outputIds and return reference to newTokens tensor. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession30createOnTokenGeneratedCallbackER16GenerationOutput">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession30createOnTokenGeneratedCallbackER16GenerationOutput"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession30createOnTokenGeneratedCallbackER16GenerationOutput"></span><span id="tensorrt_llm::runtime::GptSession::createOnTokenGeneratedCallback__GenerationOutputR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1ac7fab944335f448ad3296ebe39f9ef3f"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession22TokenGeneratedCallbackE" title="tensorrt_llm::runtime::GptSession::TokenGeneratedCallback"><span class="n"><span class="pre">TokenGeneratedCallback</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">createOnTokenGeneratedCallback</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutputE" title="tensorrt_llm::runtime::GenerationOutput"><span class="n"><span class="pre">GenerationOutput</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">outputs</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession30createOnTokenGeneratedCallbackER16GenerationOutput" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession12mModelConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession12mModelConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession12mModelConfigE"></span><span id="tensorrt_llm::runtime::GptSession::mModelConfig__GptModelConfigC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1acd20c0377c38abb8707d0fcc7b3c1b97"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14GptModelConfigE" title="tensorrt_llm::runtime::GptModelConfig"><span class="n"><span class="pre">GptModelConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mModelConfig</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession12mModelConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession12mWorldConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession12mWorldConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession12mWorldConfigE"></span><span id="tensorrt_llm::runtime::GptSession::mWorldConfig__WorldConfigC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1af712d3cd32f2c0952c6cb5bf1cfece45"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="tensorrt_llm::runtime::WorldConfig"><span class="n"><span class="pre">WorldConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mWorldConfig</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession12mWorldConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession7mDeviceE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession7mDeviceE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession7mDeviceE"></span><span id="tensorrt_llm::runtime::GptSession::mDevice__i"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a557d94b8bbfbdc168c417eeae307c25a"></span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDevice</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="o"><span class="pre">-</span></span><span class="m"><span class="pre">1</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession7mDeviceE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession13mPipelineCommE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession13mPipelineCommE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession13mPipelineCommE"></span><span id="tensorrt_llm::runtime::GptSession::mPipelineComm__std::shared_ptr:NcclCommunicator:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1afd92278f3aa9e57d02c58f5c5cb1de3a"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">NcclCommunicator</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mPipelineComm</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession13mPipelineCommE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession11mCommStreamE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession11mCommStreamE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession11mCommStreamE"></span><span id="tensorrt_llm::runtime::GptSession::mCommStream__std::shared_ptr:CudaStream:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a14480c0db4c1615ed788836285a3c1e7"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStreamE" title="tensorrt_llm::runtime::CudaStream"><span class="n"><span class="pre">CudaStream</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mCommStream</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession11mCommStreamE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession10mCommEventE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession10mCommEventE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession10mCommEventE"></span><span id="tensorrt_llm::runtime::GptSession::mCommEvent__CudaEvent"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a0916e45f7ddd9ac0a27eec4897260802"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="tensorrt_llm::runtime::CudaEvent"><span class="n"><span class="pre">CudaEvent</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mCommEvent</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession10mCommEventE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession9mCommPtrsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession9mCommPtrsE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession9mCommPtrsE"></span><span id="tensorrt_llm::runtime::GptSession::mCommPtrs__ITensor::SharedPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a62395eff1a3bce743fc6906a95d5101c"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mCommPtrs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession9mCommPtrsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17mIpcMemoryHandlesE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17mIpcMemoryHandlesE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17mIpcMemoryHandlesE"></span><span id="tensorrt_llm::runtime::GptSession::mIpcMemoryHandles__std::vector:std::shared_ptr:IpcMemory::"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a135834a47cb19851d6f8872b3a54c31a"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemoryE" title="tensorrt_llm::runtime::IpcMemory"><span class="n"><span class="pre">IpcMemory</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mIpcMemoryHandles</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17mIpcMemoryHandlesE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession25mDecoderMaxSequenceLengthE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession25mDecoderMaxSequenceLengthE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession25mDecoderMaxSequenceLengthE"></span><span id="tensorrt_llm::runtime::GptSession::mDecoderMaxSequenceLength__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a3eb70f53bb0cbc5c6e032c37520b101c"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDecoderMaxSequenceLength</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession25mDecoderMaxSequenceLengthE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession26mDecoderMaxAttentionWindowE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession26mDecoderMaxAttentionWindowE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession26mDecoderMaxAttentionWindowE"></span><span id="tensorrt_llm::runtime::GptSession::mDecoderMaxAttentionWindow__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1ab7ed97680fe2ede695ad376629272404"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDecoderMaxAttentionWindow</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession26mDecoderMaxAttentionWindowE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession7mLoggerE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession7mLoggerE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession7mLoggerE"></span><span id="tensorrt_llm::runtime::GptSession::mLogger__LoggerPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a4bd2d4d4f201bf17a87ed40c4e29ce55"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession9LoggerPtrE" title="tensorrt_llm::runtime::GptSession::LoggerPtr"><span class="n"><span class="pre">LoggerPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mLogger</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession7mLoggerE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession8mRuntimeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession8mRuntimeE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession8mRuntimeE"></span><span id="tensorrt_llm::runtime::GptSession::mRuntime__std::shared_ptr:TllmRuntime:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1aa97fc0a02f3f28e3e2121e2e9bc10c56"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">TllmRuntime</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mRuntime</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession8mRuntimeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession15mKvCacheManagerE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession15mKvCacheManagerE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession15mKvCacheManagerE"></span><span id="tensorrt_llm::runtime::GptSession::mKvCacheManager__std::shared_ptr:KvCacheManager:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1aeaf492a405a12cd82da00036d75838d0"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14KvCacheManagerE" title="tensorrt_llm::runtime::GptSession::KvCacheManager"><span class="n"><span class="pre">KvCacheManager</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mKvCacheManager</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession15mKvCacheManagerE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17mMicroBatchConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17mMicroBatchConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17mMicroBatchConfigE"></span><span id="tensorrt_llm::runtime::GptSession::mMicroBatchConfig__MicroBatchConfig"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a70891459edc318254e61e107ec5edcb2"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfigE" title="tensorrt_llm::runtime::GptSession::MicroBatchConfig"><span class="n"><span class="pre">MicroBatchConfig</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mMicroBatchConfig</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17mMicroBatchConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession9mDecodersE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession9mDecodersE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession9mDecodersE"></span><span id="tensorrt_llm::runtime::GptSession::mDecoders__std::vector:std::shared_ptr:IStatefulGptDecoder::"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1ab3287006aede8e62f11db44d5f8997e6"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoderE" title="tensorrt_llm::runtime::IStatefulGptDecoder"><span class="n"><span class="pre">IStatefulGptDecoder</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDecoders</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession9mDecodersE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession8mBuffersE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession8mBuffersE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession8mBuffersE"></span><span id="tensorrt_llm::runtime::GptSession::mBuffers__std::vector:std::shared_ptr:RuntimeBuffers::"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a96b0baf2000c1616dcdcecf836cdd143"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">RuntimeBuffers</span></span><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mBuffers</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession8mBuffersE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession15mReceivedEventsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession15mReceivedEventsE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession15mReceivedEventsE"></span><span id="tensorrt_llm::runtime::GptSession::mReceivedEvents__std::vector:CudaEvent:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a9253a1bccec0b1ab57bab7b7d5b6f5bb"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="tensorrt_llm::runtime::CudaEvent"><span class="n"><span class="pre">CudaEvent</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mReceivedEvents</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession15mReceivedEventsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession14mCudaGraphModeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession14mCudaGraphModeE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession14mCudaGraphModeE"></span><span id="tensorrt_llm::runtime::GptSession::mCudaGraphMode__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1a1bf104808d61798aeba1c87beeb2c101"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mCudaGraphMode</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="k"><span class="pre">false</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession14mCudaGraphModeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession19mCudaGraphInstancesE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession19mCudaGraphInstancesE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession19mCudaGraphInstancesE"></span><span id="tensorrt_llm::runtime::GptSession::mCudaGraphInstances__std::vector:CudaGraphExecutor:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1abf794ab36d1086fbf43a6a33db6e5181"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorE" title="tensorrt_llm::runtime::GptSession::CudaGraphExecutor"><span class="n"><span class="pre">CudaGraphExecutor</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mCudaGraphInstances</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession19mCudaGraphInstancesE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-friends">Friends</p>
|
||
<dl>
|
||
<dt class="sig sig-object cpp">
|
||
<em class="property"><span class="pre">friend</span> <span class="pre">class</span></em> <span class="pre">batch_manager::TrtGptModelV1</span></dt>
|
||
</dl>
|
||
|
||
</div>
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession6ConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession6ConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession6ConfigE"></span><span id="tensorrt_llm::runtime::GptSession::Config"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1Config"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Config</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6ConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="docutils container">
|
||
<em>#include <gptSession.h></em></div>
|
||
<p>Configuration for session execution and buffer sizes. <code class="docutils literal notranslate"><span class="pre">generate</span></code> may be called with batch size and beam width smaller than the configured parameters. </p>
|
||
<p><code class="docutils literal notranslate"><span class="pre">maxBatchSize</span></code> will be divided by the number of micro batches to initialize each batch buffer. </p>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession6Config6ConfigE8SizeType8SizeType8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession6Config6ConfigE8SizeType8SizeType8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession6Config6ConfigE8SizeType8SizeType8SizeType"></span><span id="tensorrt_llm::runtime::GptSession::Config::Config__SizeType.SizeType.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1Config_1a18da0794db4fcd78d86fcd251a271315"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Config</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxBatchSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxBeamWidth</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxSequenceLength</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6Config6ConfigE8SizeType8SizeType8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession6Config12maxBatchSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession6Config12maxBatchSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession6Config12maxBatchSizeE"></span><span id="tensorrt_llm::runtime::GptSession::Config::maxBatchSize__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1Config_1a287bf1db2d227b17409414054fbfd72e"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">maxBatchSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6Config12maxBatchSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession6Config12maxBeamWidthE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession6Config12maxBeamWidthE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession6Config12maxBeamWidthE"></span><span id="tensorrt_llm::runtime::GptSession::Config::maxBeamWidth__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1Config_1aaee696b7af4da45b54ab762b4eba2059"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">maxBeamWidth</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6Config12maxBeamWidthE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession6Config17maxSequenceLengthE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession6Config17maxSequenceLengthE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession6Config17maxSequenceLengthE"></span><span id="tensorrt_llm::runtime::GptSession::Config::maxSequenceLength__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1Config_1a741c59327475ef8172e8fb68cb1b5260"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">maxSequenceLength</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6Config17maxSequenceLengthE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession6Config17decoderPerRequestE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession6Config17decoderPerRequestE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession6Config17decoderPerRequestE"></span><span id="tensorrt_llm::runtime::GptSession::Config::decoderPerRequest__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1Config_1a3a5fc9eed846017ce119c4d624defab4"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">decoderPerRequest</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="k"><span class="pre">false</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6Config17decoderPerRequestE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession6Config13cudaGraphModeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession6Config13cudaGraphModeE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession6Config13cudaGraphModeE"></span><span id="tensorrt_llm::runtime::GptSession::Config::cudaGraphMode__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1Config_1a2584bcfc17050c7ce1370868ccb1e9b9"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cudaGraphMode</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="k"><span class="pre">false</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6Config13cudaGraphModeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession6Config13kvCacheConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession6Config13kvCacheConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession6Config13kvCacheConfigE"></span><span id="tensorrt_llm::runtime::GptSession::Config::kvCacheConfig__KvCacheConfig"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1Config_1ab6b5dafa19a5fa0c82d979e17d0a9b0f"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10GptSession13KvCacheConfigE" title="tensorrt_llm::runtime::GptSession::KvCacheConfig"><span class="n"><span class="pre">KvCacheConfig</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kvCacheConfig</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6Config13kvCacheConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession6Config17ctxMicroBatchSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession6Config17ctxMicroBatchSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession6Config17ctxMicroBatchSizeE"></span><span id="tensorrt_llm::runtime::GptSession::Config::ctxMicroBatchSize__std::optional:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1Config_1a07a837ef0fe1417e9859470895f95988"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">ctxMicroBatchSize</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">nullopt</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6Config17ctxMicroBatchSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession6Config17genMicroBatchSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession6Config17genMicroBatchSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession6Config17genMicroBatchSizeE"></span><span id="tensorrt_llm::runtime::GptSession::Config::genMicroBatchSize__std::optional:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1Config_1a0843b7e8eaeec76fab3f19863502aec2"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">genMicroBatchSize</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">nullopt</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession6Config17genMicroBatchSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorE"></span><span id="tensorrt_llm::runtime::GptSession::CudaGraphExecutor"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1CudaGraphExecutor"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">CudaGraphExecutor</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor17CudaGraphExecutorEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor17CudaGraphExecutorEv"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor17CudaGraphExecutorEv"></span><span id="tensorrt_llm::runtime::GptSession::CudaGraphExecutor::CudaGraphExecutor"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1CudaGraphExecutor_1a0f76e8397ca3097bc3451e2251c4d6bd"></span><span class="sig-name descname"><span class="n"><span class="pre">CudaGraphExecutor</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">default</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor17CudaGraphExecutorEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorD0Ev">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorD0Ev"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorD0Ev"></span><span id="tensorrt_llm::runtime::GptSession::CudaGraphExecutor::~CudaGraphExecutor"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1CudaGraphExecutor_1a0d609c019d81064a9cdf235352d7c25f"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">~CudaGraphExecutor</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutorD0Ev" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor11hasInstanceEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor11hasInstanceEv"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor11hasInstanceEv"></span><span id="tensorrt_llm::runtime::GptSession::CudaGraphExecutor::hasInstance"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1CudaGraphExecutor_1a11ce3f651b7e0c1dbba82460a85cfd3b"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">hasInstance</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor11hasInstanceEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor5clearEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor5clearEv"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor5clearEv"></span><span id="tensorrt_llm::runtime::GptSession::CudaGraphExecutor::clear"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1CudaGraphExecutor_1a6bd0bf9ff37bb89cb06d03fb19b2de59"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">clear</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor5clearEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor16prepareNextGraphERK11TllmRuntime8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor16prepareNextGraphERK11TllmRuntime8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor16prepareNextGraphERK11TllmRuntime8SizeType"></span><span id="tensorrt_llm::runtime::GptSession::CudaGraphExecutor::prepareNextGraph__TllmRuntimeCR.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1CudaGraphExecutor_1ae8bcb9ec8982af90576b5fc24b6f5599"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">prepareNextGraph</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">TllmRuntime</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">runtime</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">nextContextId</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor16prepareNextGraphERK11TllmRuntime8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6launchERK10CudaStream">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6launchERK10CudaStream"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6launchERK10CudaStream"></span><span id="tensorrt_llm::runtime::GptSession::CudaGraphExecutor::launch__CudaStreamCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1CudaGraphExecutor_1a9d32b4b5046b27364c3e265b433b62a4"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">launch</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStreamE" title="tensorrt_llm::runtime::CudaStream"><span class="n"><span class="pre">CudaStream</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">stream</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6launchERK10CudaStream" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-functions">Private Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6createERK11cudaGraph_t">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6createERK11cudaGraph_t"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6createERK11cudaGraph_t"></span><span id="tensorrt_llm::runtime::GptSession::CudaGraphExecutor::create__cudaGraph_tCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1CudaGraphExecutor_1a368e5d334bee7c4afd9085fdbe98f02e"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">create</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">cudaGraph_t</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">graph</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6createERK11cudaGraph_t" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6updateERK11cudaGraph_t">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6updateERK11cudaGraph_t"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6updateERK11cudaGraph_t"></span><span id="tensorrt_llm::runtime::GptSession::CudaGraphExecutor::update__cudaGraph_tCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1CudaGraphExecutor_1a776709d610ef7122a55d1a9dd211acb9"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">update</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">cudaGraph_t</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">graph</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor6updateERK11cudaGraph_t" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor14uploadToStreamERK10CudaStream">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor14uploadToStreamERK10CudaStream"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor14uploadToStreamERK10CudaStream"></span><span id="tensorrt_llm::runtime::GptSession::CudaGraphExecutor::uploadToStream__CudaStreamCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1CudaGraphExecutor_1af2cd5b05bdcf087f91696bc83daa90e0"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">uploadToStream</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStreamE" title="tensorrt_llm::runtime::CudaStream"><span class="n"><span class="pre">CudaStream</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">stream</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor14uploadToStreamERK10CudaStream" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor9mInstanceE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor9mInstanceE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor9mInstanceE"></span><span id="tensorrt_llm::runtime::GptSession::CudaGraphExecutor::mInstance__cudaGraphExec_t"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1CudaGraphExecutor_1ac8e98428b96096b5509dc101b66be172"></span><span class="n"><span class="pre">cudaGraphExec_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mInstance</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession17CudaGraphExecutor9mInstanceE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession16MicroBatchConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession16MicroBatchConfigE"></span><span id="tensorrt_llm::runtime::GptSession::MicroBatchConfig"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1MicroBatchConfig"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">MicroBatchConfig</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigEv"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigEv"></span><span id="tensorrt_llm::runtime::GptSession::MicroBatchConfig::MicroBatchConfig"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1MicroBatchConfig_1a1eac3f1b519be9f762d23157d6b04444"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">MicroBatchConfig</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigE8SizeType8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigE8SizeType8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigE8SizeType8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEE"></span><span id="tensorrt_llm::runtime::GptSession::MicroBatchConfig::MicroBatchConfig__SizeType.SizeType.std::optional:SizeType:.std::optional:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1MicroBatchConfig_1a55ab0fe231a604121d4801890ac22b7e"></span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">MicroBatchConfig</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxBatchSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">pipelineParallelism</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="n sig-param"><span class="pre">genMicroBatchSize</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="n sig-param"><span class="pre">ctxMicroBatchSize</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig16MicroBatchConfigE8SizeType8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig12numCtxPerGenEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig12numCtxPerGenEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig12numCtxPerGenEv"></span><span id="tensorrt_llm::runtime::GptSession::MicroBatchConfig::numCtxPerGenCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1MicroBatchConfig_1a36ce805a188b296f338f411333bf9158"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">numCtxPerGen</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig12numCtxPerGenEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig15getCtxContextIdE8SizeType8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig15getCtxContextIdE8SizeType8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig15getCtxContextIdE8SizeType8SizeType"></span><span id="tensorrt_llm::runtime::GptSession::MicroBatchConfig::getCtxContextId__SizeType.SizeTypeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1MicroBatchConfig_1a9079c00bbea192f469364110544be9a8"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getCtxContextId</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">generationBatchId</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">contextBatchId</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig15getCtxContextIdE8SizeType8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>First 2 * numGenBatches contexts are for generation phase, next numCtxBatches are for context phase. Use numCtxPerGen() contexts for the context batches of each generation batch. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig15getGenContextIdE8SizeType8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig15getGenContextIdE8SizeType8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig15getGenContextIdE8SizeType8SizeType"></span><span id="tensorrt_llm::runtime::GptSession::MicroBatchConfig::getGenContextId__SizeType.SizeTypeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1MicroBatchConfig_1a56e4fdda5114c792aaf96ce251bb4103"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getGenContextId</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">flipFlopId</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">generationBatchId</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime10GptSession16MicroBatchConfig15getGenContextIdE8SizeType8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>First 2 * numGenBatches contexts are for generation phase, flip-flop between 2 of them for each generation batch. </p>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig13numCtxBatchesE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession16MicroBatchConfig13numCtxBatchesE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession16MicroBatchConfig13numCtxBatchesE"></span><span id="tensorrt_llm::runtime::GptSession::MicroBatchConfig::numCtxBatches__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1MicroBatchConfig_1aaf5c9ff509b390c78cabf6dbeb2c32b0"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">numCtxBatches</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig13numCtxBatchesE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig13numGenBatchesE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession16MicroBatchConfig13numGenBatchesE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession16MicroBatchConfig13numGenBatchesE"></span><span id="tensorrt_llm::runtime::GptSession::MicroBatchConfig::numGenBatches__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1MicroBatchConfig_1a1519020a4d32b0dfd1770376b244e250"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">numGenBatches</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig13numGenBatchesE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig12ctxBatchSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession16MicroBatchConfig12ctxBatchSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession16MicroBatchConfig12ctxBatchSizeE"></span><span id="tensorrt_llm::runtime::GptSession::MicroBatchConfig::ctxBatchSize__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1MicroBatchConfig_1abe899259672c5a9d1503af2a0356bbaa"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">ctxBatchSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig12ctxBatchSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig12genBatchSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10GptSession16MicroBatchConfig12genBatchSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime10GptSession16MicroBatchConfig12genBatchSizeE"></span><span id="tensorrt_llm::runtime::GptSession::MicroBatchConfig::genBatchSize__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GptSession_1_1MicroBatchConfig_1a012551c5c3785c45f4be19612f0e4a02"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">genBatchSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10GptSession16MicroBatchConfig12genBatchSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime5utilsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime5utilsE"></span><span id="_CPPv2N12tensorrt_llm7runtime5utilsE"></span><span id="tensorrt_llm::runtime::utils"></span><span class="target" id="namespacetensorrt__llm_1_1runtime_1_1utils"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">utils</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime5utilsE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-functions">Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime5utils10loadEngineERKNSt6stringE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime5utils10loadEngineERKNSt6stringE"></span><span id="_CPPv2N12tensorrt_llm7runtime5utils10loadEngineERKNSt6stringE"></span><span id="tensorrt_llm::runtime::utils::loadEngine__ssCR"></span><span class="target" id="gptSession_8h_1ae397b7fd72675fbc97c0e662cc71b5eb"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">uint8_t</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">loadEngine</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">enginePath</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime5utils10loadEngineERKNSt6stringE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="ibuffer-h">
|
||
<h2>iBuffer.h<a class="headerlink" href="#ibuffer-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString_3_01MemoryType_1_1kGPU_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">MemoryTypeString</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryType4kGPUE" title="tensorrt_llm::runtime::MemoryType::kGPU"><span class="n"><span class="pre">kGPU</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEE5valueE"></span><span id="tensorrt_llm::runtime::MemoryTypeString:MemoryType::kGPU:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString_3_01MemoryType_1_1kGPU_01_4_1adc272a863661fdf8ea08ad956ebe5975"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"GPU"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kGPUEE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString_3_01MemoryType_1_1kCPU_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">MemoryTypeString</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryType4kCPUE" title="tensorrt_llm::runtime::MemoryType::kCPU"><span class="n"><span class="pre">kCPU</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEE5valueE"></span><span id="tensorrt_llm::runtime::MemoryTypeString:MemoryType::kCPU:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString_3_01MemoryType_1_1kCPU_01_4_1ad18d7d70b64c48821a5928c3eb1b6d0e"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"CPU"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType4kCPUEE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString_3_01MemoryType_1_1kPINNED_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">MemoryTypeString</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryType7kPINNEDE" title="tensorrt_llm::runtime::MemoryType::kPINNED"><span class="n"><span class="pre">kPINNED</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEE5valueE"></span><span id="tensorrt_llm::runtime::MemoryTypeString:MemoryType::kPINNED:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString_3_01MemoryType_1_1kPINNED_01_4_1a661ffce25b1fb3d0f97348ef5e92e6b6"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"PINNED"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16MemoryTypeStringIN10MemoryType7kPINNEDEE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kFLOAT_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DataTypeTraits</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kFLOAT</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4typeE"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kFLOAT_01_4_1af6ef0c2bf073670006e1a68fd861495b"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="kt"><span class="pre">float</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4nameE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4nameE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4nameE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kFLOAT:::name__cA"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kFLOAT_01_4_1aff9156cc400ebaa290f874998c6ddc24"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"float"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4nameE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4sizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4sizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4sizeE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kFLOAT:::size__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kFLOAT_01_4_1aba2b5525ce1f152f1aaf69380203c672"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4typeE" title="tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kFLOAT>::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kFLOATEE4sizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kHALF_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DataTypeTraits</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kHALF</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4typeE"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kHALF_01_4_1a08c9427d16066ff8ee9e9deb35a91871"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">half</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4nameE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4nameE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4nameE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kHALF:::name__cA"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kHALF_01_4_1a5dcc983372abc63f1e73e0ef4efe3af4"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"half"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4nameE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4sizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4sizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4sizeE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kHALF:::size__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kHALF_01_4_1ae11a9f8c46eeece89d904c7ca51be48e"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4typeE" title="tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kHALF>::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kHALFEE4sizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT8_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DataTypeTraits</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT8</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4typeE"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT8_01_4_1a51b8ee14d86b4b2a6cc5e57a1d524c43"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int8_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4nameE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4nameE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4nameE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kINT8:::name__cA"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT8_01_4_1aaf33f5d7fe9708fd4e85ed2d4a22c043"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"int8"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4nameE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4sizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4sizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4sizeE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kINT8:::size__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT8_01_4_1ad9bb9e89d790ebde4f26846c795f167a"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4typeE" title="tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT8>::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kINT8EE4sizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DataTypeTraits</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT32</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4typeE"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_01_4_1a37fa1b65a6bece3eb638f7693132053c"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int32_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4nameE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4nameE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4nameE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kINT32:::name__cA"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_01_4_1a51d6f667c98dc58d42c9b885299c6375"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"int32"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4nameE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4sizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4sizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4sizeE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kINT32:::size__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_01_4_1aad0e5753b4c85a9d8103f715aca31fa7"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4typeE" title="tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32>::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EE4sizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DataTypeTraits</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT64</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4typeE"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_01_4_1a288b116cbff3532cf2b80e7206277846"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int64_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4nameE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4nameE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4nameE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kINT64:::name__cA"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_01_4_1a8ebfbe17f94412a4eed0de836c4cd55a"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"int64"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4nameE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4sizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4sizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4sizeE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kINT64:::size__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_01_4_1ad8e7069321866172865f3464991ced3b"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4typeE" title="tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64>::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EE4sizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXtrueEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_00_01true_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DataTypeTraits</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT32</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="k"><span class="pre">true</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXtrueEE4typeE"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_00_01true_01_4_1a41a0f3bcdb82b843a9594fbe518c148d"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">uint32_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4nameE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4nameE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXtrueEE4nameE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kINT32.true:::name__cA"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_00_01true_01_4_1aa736c483d9d0e4aa71d03e8c777e341c"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"uint32"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4nameE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4sizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4sizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXtrueEE4sizeE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kINT32.true:::size__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_00_01true_01_4_1a39eaff2ce1df3547b2790e42c61167f2"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4typeE" title="tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT32, true>::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT32EXL1EEE4sizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXtrueEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_00_01true_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DataTypeTraits</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT64</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="k"><span class="pre">true</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXtrueEE4typeE"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_00_01true_01_4_1a8376cfb6029bfec1e7aaa9c29369b094"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">uint64_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4nameE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4nameE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXtrueEE4nameE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kINT64.true:::name__cA"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_00_01true_01_4_1a869291a56676cdac6140f9846e99ffbf"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"uint64"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4nameE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4sizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4sizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXtrueEE4sizeE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kINT64.true:::size__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_00_01true_01_4_1a50499242c7be43b3775a86737243d7c9"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4typeE" title="tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kINT64, true>::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kINT64EXL1EEE4sizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE">
|
||
<span id="_CPPv3I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE"></span><span id="_CPPv2I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kUnsigned</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kBOOL_00_01kUnsigned_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DataTypeTraits</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kBOOL</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE" title="tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kBOOL, kUnsigned>::kUnsigned"><span class="n"><span class="pre">kUnsigned</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4typeE"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kBOOL_00_01kUnsigned_01_4_1a3ef7ec1c22f6cc0b397ab5eb28c232eb"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4nameE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4nameE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4nameE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kBOOL.kUnsigned:::name__cA"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kBOOL_00_01kUnsigned_01_4_1aba47b1869e577d85a3d93cc68b2ab24d"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"bool"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4nameE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4sizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4sizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4sizeE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kBOOL.kUnsigned:::size__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kBOOL_00_01kUnsigned_01_4_1a1d0ef1feb1bbf08798efcdaaf934fcc0"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4typeE" title="tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kBOOL, kUnsigned>::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType5kBOOLE9kUnsignedE4sizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE">
|
||
<span id="_CPPv3I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE"></span><span id="_CPPv2I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kUnsigned</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kUINT8_00_01kUnsigned_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DataTypeTraits</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kUINT8</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE" title="tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kUINT8, kUnsigned>::kUnsigned"><span class="n"><span class="pre">kUnsigned</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4I_bEN12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4typeE"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kUINT8_00_01kUnsigned_01_4_1a5a3089fdad68ca4ce8bf36137d18a147"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">uint8_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4nameE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4nameE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4nameE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kUINT8.kUnsigned:::name__cA"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kUINT8_00_01kUnsigned_01_4_1a31c93a3cf26ca1fbce36b588c146996c"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"uint8"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4nameE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4sizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4sizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4sizeE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:nvinfer1::DataType::kUINT8.kUnsigned:::size__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kUINT8_00_01kUnsigned_01_4_1ad0a569389e9dda69079149e8ab016ab0"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4typeE" title="tensorrt_llm::runtime::DataTypeTraits<nvinfer1::DataType::kUINT8, kUnsigned>::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsIN8nvinfer18DataType6kUINT8E9kUnsignedE4sizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1int8__t_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TRTDataType</span></span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int8_t</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEE5valueE"></span><span id="tensorrt_llm::runtime::TRTDataType:std::int8_t:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1int8__t_01_4_1a996ff7940394a814ae164728312bf5ff"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT8</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt6int8_tEE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1int32__t_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TRTDataType</span></span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int32_t</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEE5valueE"></span><span id="tensorrt_llm::runtime::TRTDataType:std::int32_t:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1int32__t_01_4_1a10403a956a1d979e0cd10c8034e9f3e1"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT32</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int32_tEE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1uint32__t_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TRTDataType</span></span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">uint32_t</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEE5valueE"></span><span id="tensorrt_llm::runtime::TRTDataType:std::uint32_t:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1uint32__t_01_4_1a96b97cf0edb4ad984dd69278acfabd10"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE" title="tensorrt_llm::runtime::BufferDataType"><span class="n"><span class="pre">BufferDataType</span></span></a><span class="p"><span class="pre">{</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT32</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="k"><span class="pre">true</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint32_tEE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1int64__t_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TRTDataType</span></span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int64_t</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEE5valueE"></span><span id="tensorrt_llm::runtime::TRTDataType:std::int64_t:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1int64__t_01_4_1af2839adf78453826b3a7f8422c9130fb"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT64</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7int64_tEE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1uint64__t_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TRTDataType</span></span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">uint64_t</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEE5valueE"></span><span id="tensorrt_llm::runtime::TRTDataType:std::uint64_t:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1uint64__t_01_4_1a6d279398fbfedbbfffd0f7fbd1eb80b8"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE" title="tensorrt_llm::runtime::BufferDataType"><span class="n"><span class="pre">BufferDataType</span></span></a><span class="p"><span class="pre">{</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT64</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="k"><span class="pre">true</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt8uint64_tEE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1uint8__t_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TRTDataType</span></span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">uint8_t</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEE5valueE"></span><span id="tensorrt_llm::runtime::TRTDataType:std::uint8_t:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1uint8__t_01_4_1a60d418bc6cea9f845ee353d78f0c3d66"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kUINT8</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeINSt7uint8_tEE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-typedefs">Typedefs</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime18PointerElementTypeE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime18PointerElementTypeE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="iBuffer_8h_1a6b78d5482ec51a801a9fe54db6eaa0f9"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">PointerElementType</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">remove_reference_t</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE" title="tensorrt_llm::runtime::PointerElementType::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">element_type</span></span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-enums">Enums</p>
|
||
<dl class="cpp enum-class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10MemoryTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10MemoryTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime10MemoryTypeE"></span><span class="target" id="iBuffer_8h_1a57051a59520fc335a72e6fd1d08fa869"></span><span class="k"><span class="pre">enum</span></span><span class="w"> </span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">MemoryType</span></span></span><span class="w"> </span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int32_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p><em>Values:</em></p>
|
||
<dl class="cpp enumerator">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10MemoryType4kGPUE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10MemoryType4kGPUE"></span><span id="_CPPv2N12tensorrt_llm7runtime10MemoryType4kGPUE"></span><span class="target" id="iBuffer_8h_1a57051a59520fc335a72e6fd1d08fa869a37ae524b76587efa776affdc5cdf2ac1"></span><span class="k"><span class="pre">enumerator</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kGPU</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10MemoryType4kGPUE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp enumerator">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10MemoryType4kCPUE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10MemoryType4kCPUE"></span><span id="_CPPv2N12tensorrt_llm7runtime10MemoryType4kCPUE"></span><span class="target" id="iBuffer_8h_1a57051a59520fc335a72e6fd1d08fa869a2ce310327f474afc9f6774faa2f57903"></span><span class="k"><span class="pre">enumerator</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kCPU</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10MemoryType4kCPUE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp enumerator">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10MemoryType7kPINNEDE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10MemoryType7kPINNEDE"></span><span id="_CPPv2N12tensorrt_llm7runtime10MemoryType7kPINNEDE"></span><span class="target" id="iBuffer_8h_1a57051a59520fc335a72e6fd1d08fa869ae3278bcaa387e6baeef9b80c1e61c35a"></span><span class="k"><span class="pre">enumerator</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kPINNED</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10MemoryType7kPINNEDE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-functions">Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime16constPointerCastERKNSt10shared_ptrI1TEE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime16constPointerCastERKNSt10shared_ptrI1TEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="iBuffer_8h_1ad7234909a7d00791f3d22a797078e9de"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">remove_const_t</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE" title="tensorrt_llm::runtime::constPointerCast::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">constPointerCast</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE" title="tensorrt_llm::runtime::constPointerCast::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">ptr</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERKNSt10shared_ptrI1TEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE">
|
||
<span id="_CPPv3I00EN12tensorrt_llm7runtime16constPointerCastERRNSt10unique_ptrI1T1DEE"></span><span id="_CPPv2I00EN12tensorrt_llm7runtime16constPointerCastERRNSt10unique_ptrI1T1DEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">D</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="iBuffer_8h_1a1398d57cec6aacd5be041575ccb140fb"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">remove_const_t</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE" title="tensorrt_llm::runtime::constPointerCast::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">constPointerCast</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unique_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE" title="tensorrt_llm::runtime::constPointerCast::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE" title="tensorrt_llm::runtime::constPointerCast::D"><span class="n"><span class="pre">D</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">ptr</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4I00EN12tensorrt_llm7runtime16constPointerCastENSt10shared_ptrINSt14remove_const_tI1TEEEERRNSt10unique_ptrI1T1DEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime10bufferCastERK7IBuffer"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime10bufferCastERK7IBuffer"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="iBuffer_8h_1aa39a24d2db1c10a205c75aa2c6a8f069"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer" title="tensorrt_llm::runtime::bufferCast::T"><span class="n"><span class="pre">T</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="sig-name descname"><span class="n"><span class="pre">bufferCast</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">buffer</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEPK1TRK7IBuffer" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime10bufferCastER7IBuffer"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime10bufferCastER7IBuffer"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="iBuffer_8h_1a2f29317ef105d176296ef6b5518bcddf"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer" title="tensorrt_llm::runtime::bufferCast::T"><span class="n"><span class="pre">T</span></span></a><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="sig-name descname"><span class="n"><span class="pre">bufferCast</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">buffer</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime10bufferCastEP1TR7IBuffer" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer">
|
||
<span id="_CPPv3N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer"></span><span id="_CPPv2N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer"></span><span id="tensorrt_llm::runtime::lshift-operator__osR.IBufferCR"></span><span class="target" id="iBuffer_8h_1a4363785cd968e4e0cd1933cba37850b9"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">ostream</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="k"><span class="pre">operator</span></span><span class="o"><span class="pre"><<</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">ostream</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">buffer</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7IBuffer" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Utility function to print a buffer. </p>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE">
|
||
<span id="_CPPv3I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE"></span><span id="_CPPv2I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">MemoryTypeString</span></span></span><a class="headerlink" href="#_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime16MemoryTypeStringE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString_3_01MemoryType_1_1kGPU_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">kGPU</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19PhonyNameDueToError5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime19PhonyNameDueToError5valueE"></span><span id="tensorrt_llm::runtime::PhonyNameDueToError::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString_3_01MemoryType_1_1kGPU_01_4_1adc272a863661fdf8ea08ad956ebe5975"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"GPU"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString_3_01MemoryType_1_1kCPU_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">kCPU</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString_3_01MemoryType_1_1kCPU_01_4_1ad18d7d70b64c48821a5928c3eb1b6d0e"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"CPU"</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString_3_01MemoryType_1_1kPINNED_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">kPINNED</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1MemoryTypeString_3_01MemoryType_1_1kPINNED_01_4_1a661ffce25b1fb3d0f97348ef5e92e6b6"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"PINNED"</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE">
|
||
<span id="_CPPv3I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE"></span><span id="_CPPv2I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kDataType</span></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kIsUnsigned</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">false</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kIsPointer</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">false</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DataTypeTraits</span></span></span><a class="headerlink" href="#_CPPv4I_N8nvinfer18DataTypeE_b_bEN12tensorrt_llm7runtime14DataTypeTraitsE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="docutils container">
|
||
<em>#include <iBuffer.h></em></div>
|
||
<p>For converting a TensorRT data type to a C++ data type. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kFLOAT_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">kFLOAT</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19PhonyNameDueToError4typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime19PhonyNameDueToError4typeE"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kFLOAT_01_4_1af6ef0c2bf073670006e1a68fd861495b"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="kt"><span class="pre">float</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19PhonyNameDueToError4nameE"></span><span id="_CPPv2N12tensorrt_llm7runtime19PhonyNameDueToError4nameE"></span><span id="tensorrt_llm::runtime::PhonyNameDueToError::name__cA"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kFLOAT_01_4_1aff9156cc400ebaa290f874998c6ddc24"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"float"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4nameE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE"></span><span id="tensorrt_llm::runtime::PhonyNameDueToError::size__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kFLOAT_01_4_1aba2b5525ce1f152f1aaf69380203c672"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE" title="tensorrt_llm::runtime::PhonyNameDueToError::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4sizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kHALF_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">kHALF</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kHALF_01_4_1a08c9427d16066ff8ee9e9deb35a91871"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">half</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kHALF_01_4_1a5dcc983372abc63f1e73e0ef4efe3af4"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"half"</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kHALF_01_4_1ae11a9f8c46eeece89d904c7ca51be48e"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE" title="tensorrt_llm::runtime::PhonyNameDueToError::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT8_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">kINT8</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT8_01_4_1a51b8ee14d86b4b2a6cc5e57a1d524c43"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int8_t</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT8_01_4_1aaf33f5d7fe9708fd4e85ed2d4a22c043"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"int8"</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT8_01_4_1ad9bb9e89d790ebde4f26846c795f167a"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE" title="tensorrt_llm::runtime::PhonyNameDueToError::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">kINT32</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_01_4_1a37fa1b65a6bece3eb638f7693132053c"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int32_t</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_01_4_1a51d6f667c98dc58d42c9b885299c6375"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"int32"</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_01_4_1aad0e5753b4c85a9d8103f715aca31fa7"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE" title="tensorrt_llm::runtime::PhonyNameDueToError::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">kINT64</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_01_4_1a288b116cbff3532cf2b80e7206277846"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int64_t</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_01_4_1a8ebfbe17f94412a4eed0de836c4cd55a"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"int64"</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_01_4_1ad8e7069321866172865f3464991ced3b"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE" title="tensorrt_llm::runtime::PhonyNameDueToError::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_00_01true_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">kINT32,</span> <span class="pre">true</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_00_01true_01_4_1a41a0f3bcdb82b843a9594fbe518c148d"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">uint32_t</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_00_01true_01_4_1aa736c483d9d0e4aa71d03e8c777e341c"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"uint32"</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT32_00_01true_01_4_1a39eaff2ce1df3547b2790e42c61167f2"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE" title="tensorrt_llm::runtime::PhonyNameDueToError::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_00_01true_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">kINT64,</span> <span class="pre">true</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_00_01true_01_4_1a8376cfb6029bfec1e7aaa9c29369b094"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">uint64_t</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_00_01true_01_4_1a869291a56676cdac6140f9846e99ffbf"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"uint64"</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kINT64_00_01true_01_4_1a50499242c7be43b3775a86737243d7c9"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE" title="tensorrt_llm::runtime::PhonyNameDueToError::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kBOOL_00_01kUnsigned_01_4"></span><span class="sig-name descname"><span class="pre">template<bool</span> <span class="pre">kUnsigned></span> <span class="pre">kBOOL,</span> <span class="pre">kUnsigned</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kBOOL_00_01kUnsigned_01_4_1a3ef7ec1c22f6cc0b397ab5eb28c232eb"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kBOOL_00_01kUnsigned_01_4_1aba47b1869e577d85a3d93cc68b2ab24d"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"bool"</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kBOOL_00_01kUnsigned_01_4_1a1d0ef1feb1bbf08798efcdaaf934fcc0"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE" title="tensorrt_llm::runtime::PhonyNameDueToError::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kUINT8_00_01kUnsigned_01_4"></span><span class="sig-name descname"><span class="pre">template<bool</span> <span class="pre">kUnsigned></span> <span class="pre">kUINT8,</span> <span class="pre">kUnsigned</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kUINT8_00_01kUnsigned_01_4_1a5a3089fdad68ca4ce8bf36137d18a147"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">uint8_t</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kUINT8_00_01kUnsigned_01_4_1a31c93a3cf26ca1fbce36b588c146996c"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"uint8"</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01nvinfer1_1_1DataType_1_1kUINT8_00_01kUnsigned_01_4_1ad0a569389e9dda69079149e8ab016ab0"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19PhonyNameDueToError4typeE" title="tensorrt_llm::runtime::PhonyNameDueToError::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE">
|
||
<span id="_CPPv3I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE"></span><span id="_CPPv2I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXtrueEEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kDataType</span></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kUnsigned</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01kDataType_00_01kUnsigned_00_01true_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DataTypeTraits</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE" title="tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::kDataType"><span class="n"><span class="pre">kDataType</span></span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE" title="tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::kUnsigned"><span class="n"><span class="pre">kUnsigned</span></span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="k"><span class="pre">true</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXtrueEE4typeE"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01kDataType_00_01kUnsigned_00_01true_01_4_1a4e4f2844614eff1320acd710bc0cfe9c"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="n"><span class="pre">DataTypeTraits</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE" title="tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::kDataType"><span class="n"><span class="pre">kDataType</span></span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I_N8nvinfer18DataTypeE_bEN12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEEE" title="tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::kUnsigned"><span class="n"><span class="pre">kUnsigned</span></span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="k"><span class="pre">false</span></span><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">type</span></span><span class="p"><span class="pre">*</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4nameE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4nameE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXtrueEE4nameE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:kDataType.kUnsigned.true:::name__cA"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01kDataType_00_01kUnsigned_00_01true_01_4_1a82b47cb338e9493046c041d4e511564d"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">name</span></span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="s"><span class="pre">"*"</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4nameE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4sizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4sizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXtrueEE4sizeE"></span><span id="tensorrt_llm::runtime::DataTypeTraits:kDataType.kUnsigned.true:::size__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1DataTypeTraits_3_01kDataType_00_01kUnsigned_00_01true_01_4_1a2c1daab28b706ec5735fb3b5367a733e"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4typeE" title="tensorrt_llm::runtime::DataTypeTraits<kDataType, kUnsigned, true>::type"><span class="n"><span class="pre">type</span></span></a><span class="p"><span class="pre">)</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14DataTypeTraitsI9kDataType9kUnsignedXL1EEE4sizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14BufferDataTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14BufferDataTypeE"></span><span id="tensorrt_llm::runtime::BufferDataType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferDataType"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">BufferDataType</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="docutils container">
|
||
<em>#include <iBuffer.h></em></div>
|
||
<p>A wrapper around <code class="docutils literal notranslate"><span class="pre">nvinfer1::DataType</span></code> that provides a support for pointer types. </p>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb"></span><span id="_CPPv2N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb"></span><span id="tensorrt_llm::runtime::BufferDataType::BufferDataType__nvinfer1::DataType.b.bCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferDataType_1a3cdb7e5d96b677f670d211cd3f0d2029"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">BufferDataType</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">dataType</span></span>, <span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">_unsigned</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">false</span></span>, <span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">pointer</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">false</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataType14BufferDataTypeEN8nvinfer18DataTypeEbb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14BufferDataTypecvN8nvinfer18DataTypeEEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14BufferDataTypecvN8nvinfer18DataTypeEEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14BufferDataTypecvN8nvinfer18DataTypeEEv"></span><span id="tensorrt_llm::runtime::BufferDataType::castto-nvinfer1::DataType-operatorCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferDataType_1ae0e234f2e49d57ea1ec39bf76ef5f843"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="sig-name descname"><span class="k"><span class="pre">operator</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14BufferDataTypecvN8nvinfer18DataTypeEEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14BufferDataType11getDataTypeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14BufferDataType11getDataTypeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14BufferDataType11getDataTypeEv"></span><span id="tensorrt_llm::runtime::BufferDataType::getDataTypeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferDataType_1a375ef9858082b42a89a8fbddeb758836"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getDataType</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14BufferDataType11getDataTypeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14BufferDataType9isPointerEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14BufferDataType9isPointerEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14BufferDataType9isPointerEv"></span><span id="tensorrt_llm::runtime::BufferDataType::isPointerCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferDataType_1a4f456474dbc06fcfb4c5fdd4f30c681b"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">isPointer</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14BufferDataType9isPointerEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14BufferDataType10isUnsignedEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14BufferDataType10isUnsignedEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14BufferDataType10isUnsignedEv"></span><span id="tensorrt_llm::runtime::BufferDataType::isUnsignedCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferDataType_1a84da512a92aa9b9ba7498d8eface36d1"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">isUnsigned</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14BufferDataType10isUnsignedEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14BufferDataType7getSizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14BufferDataType7getSizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14BufferDataType7getSizeEv"></span><span id="tensorrt_llm::runtime::BufferDataType::getSizeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferDataType_1a0e1c8d7eb345611735b5c8998efc1b29"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getSize</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14BufferDataType7getSizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14BufferDataType15kTrtPointerTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14BufferDataType15kTrtPointerTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14BufferDataType15kTrtPointerTypeE"></span><span id="tensorrt_llm::runtime::BufferDataType::kTrtPointerType__auto"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferDataType_1a10497366a0660dd533bd6bac96a65e97"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kTrtPointerType</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT64</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataType15kTrtPointerTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14BufferDataType9mDataTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14BufferDataType9mDataTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14BufferDataType9mDataTypeE"></span><span id="tensorrt_llm::runtime::BufferDataType::mDataType__nvinfer1::DataType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferDataType_1a57916add2426171d7066d14df4e796d8"></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDataType</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataType9mDataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14BufferDataType9mUnsignedE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14BufferDataType9mUnsignedE"></span><span id="_CPPv2N12tensorrt_llm7runtime14BufferDataType9mUnsignedE"></span><span id="tensorrt_llm::runtime::BufferDataType::mUnsigned__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferDataType_1a675fe3124bb2de4dd047ce69a1a5a88b"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mUnsigned</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataType9mUnsignedE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14BufferDataType8mPointerE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14BufferDataType8mPointerE"></span><span id="_CPPv2N12tensorrt_llm7runtime14BufferDataType8mPointerE"></span><span id="tensorrt_llm::runtime::BufferDataType::mPointer__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferDataType_1a494f3b4c8e08ef43209cac0e2f114e0c"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mPointer</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataType8mPointerE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0_bEN12tensorrt_llm7runtime11TRTDataTypeE">
|
||
<span id="_CPPv3I0_bEN12tensorrt_llm7runtime11TRTDataTypeE"></span><span id="_CPPv2I0_bEN12tensorrt_llm7runtime11TRTDataTypeE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">false</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TRTDataType</span></span></span><a class="headerlink" href="#_CPPv4I0_bEN12tensorrt_llm7runtime11TRTDataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="docutils container">
|
||
<em>#include <iBuffer.h></em></div>
|
||
<p>For converting a C++ data type to a TensorRT data type. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIfEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime11TRTDataTypeIfEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime11TRTDataTypeIfEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01float_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TRTDataType</span></span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">float</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIfEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIfE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TRTDataTypeIfE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TRTDataTypeIfE5valueE"></span><span id="tensorrt_llm::runtime::TRTDataType:float:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01float_01_4_1a0a72c60c5a9b946e64a960d1075a5af9"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kFLOAT</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIfE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeI4halfEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime11TRTDataTypeI4halfEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime11TRTDataTypeI4halfEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01half_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TRTDataType</span></span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">half</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeI4halfEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TRTDataTypeI4halfE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TRTDataTypeI4halfE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TRTDataTypeI4halfE5valueE"></span><span id="tensorrt_llm::runtime::TRTDataType:half:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01half_01_4_1a2febf53869fcfd71830c674652e7c7d4"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kHALF</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeI4halfE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1int8__t_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">int8_t</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1int8__t_01_4_1a996ff7940394a814ae164728312bf5ff"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT8</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1int32__t_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">int32_t</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1int32__t_01_4_1a10403a956a1d979e0cd10c8034e9f3e1"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT32</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1uint32__t_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">uint32_t</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1uint32__t_01_4_1a96b97cf0edb4ad984dd69278acfabd10"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE" title="tensorrt_llm::runtime::BufferDataType"><span class="n"><span class="pre">BufferDataType</span></span></a><span class="p"><span class="pre">{</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT32</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="k"><span class="pre">true</span></span><span class="p"><span class="pre">}</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1int64__t_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">int64_t</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1int64__t_01_4_1af2839adf78453826b3a7f8422c9130fb"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT64</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1uint64__t_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">uint64_t</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1uint64__t_01_4_1a6d279398fbfedbbfffd0f7fbd1eb80b8"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE" title="tensorrt_llm::runtime::BufferDataType"><span class="n"><span class="pre">BufferDataType</span></span></a><span class="p"><span class="pre">{</span></span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kINT64</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="k"><span class="pre">true</span></span><span class="p"><span class="pre">}</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIbEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime11TRTDataTypeIbEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime11TRTDataTypeIbEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01bool_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TRTDataType</span></span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIbEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIbE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TRTDataTypeIbE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TRTDataTypeIbE5valueE"></span><span id="tensorrt_llm::runtime::TRTDataType:b:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01bool_01_4_1a590c40a56a5eabf6069340edc07d84e4"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kBOOL</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIbE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1uint8__t_01_4"></span><span class="sig-name descname"><span class="pre">template<></span> <span class="pre">uint8_t</span> <span class="pre">></span></span></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01std_1_1uint8__t_01_4_1a60d418bc6cea9f845ee353d78f0c3d66"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">kUINT8</span></span><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIPvEE">
|
||
<span id="_CPPv3IEN12tensorrt_llm7runtime11TRTDataTypeIPvEE"></span><span id="_CPPv2IEN12tensorrt_llm7runtime11TRTDataTypeIPvEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01void_01_5_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TRTDataType</span></span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">void</span></span><span class="p"><span class="pre">*</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4IEN12tensorrt_llm7runtime11TRTDataTypeIPvEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIPvE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TRTDataTypeIPvE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TRTDataTypeIPvE5valueE"></span><span id="tensorrt_llm::runtime::TRTDataType:voidP:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01void_01_5_01_4_1a63d38011d7c02b6ce399d457537b1a93"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE" title="tensorrt_llm::runtime::BufferDataType"><span class="n"><span class="pre">BufferDataType</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataType15kTrtPointerTypeE" title="tensorrt_llm::runtime::BufferDataType::kTrtPointerType"><span class="n"><span class="pre">kTrtPointerType</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIPvE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp struct">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01T_01_5_01_4"></span><span class="k"><span class="pre">struct</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TRTDataType</span></span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE" title="tensorrt_llm::runtime::TRTDataType<T*>::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">*</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE5valueE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TRTDataTypeIP1TE5valueE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TRTDataTypeIP1TE5valueE"></span><span id="tensorrt_llm::runtime::TRTDataType:TP:::value__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01T_01_5_01_4_1ae513ee17ebefd7e2c538476736488aa1"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE" title="tensorrt_llm::runtime::BufferDataType"><span class="n"><span class="pre">BufferDataType</span></span></a><span class="p"><span class="pre">{</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE" title="tensorrt_llm::runtime::TRTDataType<T*>::kUnderlyingType"><span class="n"><span class="pre">kUnderlyingType</span></span></a><span class="p"><span class="pre">.</span></span><span class="n"><span class="pre">getDataType</span></span><span class="p"><span class="pre">(</span></span><span class="p"><span class="pre">)</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE" title="tensorrt_llm::runtime::TRTDataType<T*>::kUnderlyingType"><span class="n"><span class="pre">kUnderlyingType</span></span></a><span class="p"><span class="pre">.</span></span><span class="n"><span class="pre">isUnsigned</span></span><span class="p"><span class="pre">(</span></span><span class="p"><span class="pre">)</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="k"><span class="pre">true</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE5valueE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-static-attributes">Private Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE"></span><span id="tensorrt_llm::runtime::TRTDataType:TP:::kUnderlyingType__auto"></span><span class="target" id="structtensorrt__llm_1_1runtime_1_1TRTDataType_3_01T_01_5_01_4_1aafb13ea78bfe5c1ddf1a77093531b0ff"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">auto</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kUnderlyingType</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14BufferDataTypeE" title="tensorrt_llm::runtime::BufferDataType"><span class="n"><span class="pre">BufferDataType</span></span></a><span class="p"><span class="pre">{</span></span><span class="n"><span class="pre">TRTDataType</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime11TRTDataTypeIP1TEE" title="tensorrt_llm::runtime::TRTDataType<T*>::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="k"><span class="pre">false</span></span><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">value</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11TRTDataTypeIP1TE15kUnderlyingTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBufferE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBufferE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBufferE"></span><span id="tensorrt_llm::runtime::IBuffer"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">IBuffer</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Subclassed by <a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1ITensor"><span class="std std-ref">tensorrt_llm::runtime::ITensor</span></a></p>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer9UniquePtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer9UniquePtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1ab5684b52d1990c0a0f70c25d0b6c1465"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">UniquePtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unique_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer9SharedPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer9SharedPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a2f0c3696d87a3887b38da126cbef1759"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">SharedPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a3892842dc7c9dcc1cad622470ac97999"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">UniqueConstPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unique_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer14SharedConstPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer14SharedConstPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer14SharedConstPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a8eefcf151b57310d8ca78b8e25c46c39"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">SharedConstPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer14SharedConstPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer8DataTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer8DataTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer8DataTypeE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a4036935d2bbb442bf9d071df2eff24bd"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DataType</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer8DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer4dataEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer4dataEv"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer4dataEv"></span><span id="tensorrt_llm::runtime::IBuffer::data"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a1b29144573f04c11a8c59576a2ddca4f"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="sig-name descname"><span class="n"><span class="pre">data</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer4dataEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns a pointer to underlying array. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7IBuffer4dataEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime7IBuffer4dataEv"></span><span id="tensorrt_llm::runtime::IBuffer::dataC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a49f4130965beadb2b82a0b6bcd50cd11"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="sig-name descname"><span class="n"><span class="pre">data</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns a pointer to underlying array. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE"></span><span id="tensorrt_llm::runtime::IBuffer::data__std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1ada0b7259447dab20f65e144030f55cef"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="sig-name descname"><span class="n"><span class="pre">data</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">index</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns a pointer to the underlying array at a given element index. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE"></span><span id="_CPPv2NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE"></span><span id="tensorrt_llm::runtime::IBuffer::data__std::sC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a797f41a093bb00596edaf60f329f66e1"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="sig-name descname"><span class="n"><span class="pre">data</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">index</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer4dataENSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns a pointer to the underlying array at a given element index. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7IBuffer7getSizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7IBuffer7getSizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime7IBuffer7getSizeEv"></span><span id="tensorrt_llm::runtime::IBuffer::getSizeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1ab280c88977e5cf7d3c3ab88e29dcbe62"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getSize</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer7getSizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns the size (in number of elements) of the buffer. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7IBuffer14getSizeInBytesEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7IBuffer14getSizeInBytesEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime7IBuffer14getSizeInBytesEv"></span><span id="tensorrt_llm::runtime::IBuffer::getSizeInBytesC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a3121c0295ee572bb45067bba2d35defa"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getSizeInBytes</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer14getSizeInBytesEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns the size (in bytes) of the buffer. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7IBuffer11getCapacityEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7IBuffer11getCapacityEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime7IBuffer11getCapacityEv"></span><span id="tensorrt_llm::runtime::IBuffer::getCapacityC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a33c48c142ee4ee1c1537d1bef5a7ed16"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getCapacity</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer11getCapacityEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns the capacity of the buffer. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7IBuffer11getDataTypeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7IBuffer11getDataTypeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime7IBuffer11getDataTypeEv"></span><span id="tensorrt_llm::runtime::IBuffer::getDataTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a006dc512c6b37d582a2e825249c4a3a2"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer8DataTypeE" title="tensorrt_llm::runtime::IBuffer::DataType"><span class="n"><span class="pre">DataType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getDataType</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer11getDataTypeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns the data type of the buffer. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7IBuffer15getDataTypeNameEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7IBuffer15getDataTypeNameEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime7IBuffer15getDataTypeNameEv"></span><span id="tensorrt_llm::runtime::IBuffer::getDataTypeNameC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a32794b7a1c08dfb83a19f78b8b388eaa"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="sig-name descname"><span class="n"><span class="pre">getDataTypeName</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer15getDataTypeNameEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7IBuffer13getMemoryTypeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7IBuffer13getMemoryTypeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime7IBuffer13getMemoryTypeEv"></span><span id="tensorrt_llm::runtime::IBuffer::getMemoryTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1ade5fc6e89a07ad03927a616fdcbb0463"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getMemoryType</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer13getMemoryTypeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns the memory type of the buffer. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7IBuffer17getMemoryTypeNameEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7IBuffer17getMemoryTypeNameEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime7IBuffer17getMemoryTypeNameEv"></span><span id="tensorrt_llm::runtime::IBuffer::getMemoryTypeNameC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1afd41586a8567409043799fdabca22dc4"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">char</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="sig-name descname"><span class="n"><span class="pre">getMemoryTypeName</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer17getMemoryTypeNameEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE"></span><span id="tensorrt_llm::runtime::IBuffer::resize__std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1af1281049c93d0a1d61b8682170761ad4"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">resize</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">newSize</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer6resizeENSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Resizes the buffer. This is a no-op if the new size is smaller than or equal to the current capacity. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer7releaseEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer7releaseEv"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer7releaseEv"></span><span id="tensorrt_llm::runtime::IBuffer::release"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a51dc4a186d9b315dfe77aacd33677ff7"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">release</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer7releaseEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Releases the buffer. It will be reset to nullptr. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBufferD0Ev">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBufferD0Ev"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBufferD0Ev"></span><span id="tensorrt_llm::runtime::IBuffer::~IBuffer"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1abeb460077884adc9aec0c351c9ef3637"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">~IBuffer</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">default</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBufferD0Ev" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferERK7IBuffer">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer7IBufferERK7IBuffer"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer7IBufferERK7IBuffer"></span><span id="tensorrt_llm::runtime::IBuffer::IBuffer__IBufferCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1ac9fd5dfcd8486d8f8150fdb470c38055"></span><span class="sig-name descname"><span class="n"><span class="pre">IBuffer</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferERK7IBuffer" title="tensorrt_llm::runtime::IBuffer::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">&</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">delete</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferERK7IBuffer" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Not allowed to copy. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBufferaSERK7IBuffer">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBufferaSERK7IBuffer"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBufferaSERK7IBuffer"></span><span id="tensorrt_llm::runtime::IBuffer::assign-operator__IBufferCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a10744c55831bf12db698adbb511d660e"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="k"><span class="pre">operator</span></span><span class="o"><span class="pre">=</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">&</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">delete</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBufferaSERK7IBuffer" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Not allowed to copy. </p>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-functions">Public Static Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE"></span><span id="tensorrt_llm::runtime::IBuffer::slice__SharedPtr.std::s.std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a6b9aed7e66f2bfc1f3f710d12dbceea6"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE" title="tensorrt_llm::runtime::IBuffer::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">slice</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE" title="tensorrt_llm::runtime::IBuffer::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">buffer</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">offset</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tENSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Creates a sliced view on the underlying <code class="docutils literal notranslate"><span class="pre">buffer</span></code>. The view will have the same data type as <code class="docutils literal notranslate"><span class="pre">buffer</span></code>. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>buffer</strong> – The buffer to view. </p></li>
|
||
<li><p><strong>offset</strong> – The offset of the view. </p></li>
|
||
<li><p><strong>size</strong> – The size of the view. </p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>A view on the <code class="docutils literal notranslate"><span class="pre">buffer</span></code>. </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE">
|
||
<span id="_CPPv3I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceERR9TConstPtrNSt6size_tENSt6size_tE"></span><span id="_CPPv2I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceERR9TConstPtrNSt6size_tENSt6size_tE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TConstPtr</span></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">enable_if_t</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">is_const_v</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE" title="tensorrt_llm::runtime::PointerElementType"><span class="n"><span class="pre">PointerElementType</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE" title="tensorrt_llm::runtime::IBuffer::slice::TConstPtr"><span class="n"><span class="pre">TConstPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="kt"><span class="pre">int</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a40f5f57b98c9918b617c1de832390b9c"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE" title="tensorrt_llm::runtime::IBuffer::UniqueConstPtr"><span class="n"><span class="pre">UniqueConstPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">slice</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE" title="tensorrt_llm::runtime::IBuffer::slice::TConstPtr"><span class="n"><span class="pre">TConstPtr</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">tensor</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">offset</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE"></span><span id="tensorrt_llm::runtime::IBuffer::slice__SharedPtr.std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a310d420f890b10b16951eae4b0227d21"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE" title="tensorrt_llm::runtime::IBuffer::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">slice</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE" title="tensorrt_llm::runtime::IBuffer::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">buffer</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">offset</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer5sliceE9SharedPtrNSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE">
|
||
<span id="_CPPv3I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceERR9TConstPtrNSt6size_tE"></span><span id="_CPPv2I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceERR9TConstPtrNSt6size_tE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TConstPtr</span></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">enable_if_t</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">is_const_v</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE" title="tensorrt_llm::runtime::PointerElementType"><span class="n"><span class="pre">PointerElementType</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE" title="tensorrt_llm::runtime::IBuffer::slice::TConstPtr"><span class="n"><span class="pre">TConstPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="kt"><span class="pre">int</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a9ffdc0f354482f983b6a16825ad25109"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE" title="tensorrt_llm::runtime::IBuffer::UniqueConstPtr"><span class="n"><span class="pre">UniqueConstPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">slice</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE" title="tensorrt_llm::runtime::IBuffer::slice::TConstPtr"><span class="n"><span class="pre">TConstPtr</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">tensor</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">offset</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr"></span><span id="tensorrt_llm::runtime::IBuffer::view__SharedPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a4fb6a8d4a92376cdea0957a26629f53b"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE" title="tensorrt_llm::runtime::IBuffer::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">view</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE" title="tensorrt_llm::runtime::IBuffer::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">tensor</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns a view on the underlying <code class="docutils literal notranslate"><span class="pre">tensor</span></code> which can be independently resized. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p><strong>tensor</strong> – The tensor to view. </p>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>A view on the <code class="docutils literal notranslate"><span class="pre">tensor</span></code>. </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE"></span><span id="tensorrt_llm::runtime::IBuffer::view__SharedPtr.std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a58bc0fcaa0356cf9e20ce1d06b16c70f"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE" title="tensorrt_llm::runtime::IBuffer::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">view</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE" title="tensorrt_llm::runtime::IBuffer::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">tensor</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer4viewE9SharedPtrNSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns a view on the underlying <code class="docutils literal notranslate"><span class="pre">tensor</span></code> with a different size. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>tensor</strong> – The tensor to view. </p></li>
|
||
<li><p><strong>size</strong> – The size of the view. </p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>A view on the <code class="docutils literal notranslate"><span class="pre">tensor</span></code>. </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE">
|
||
<span id="_CPPv3I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewERR9TConstPtrNSt6size_tE"></span><span id="_CPPv2I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewERR9TConstPtrNSt6size_tE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TConstPtr</span></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">enable_if_t</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">is_const_v</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE" title="tensorrt_llm::runtime::PointerElementType"><span class="n"><span class="pre">PointerElementType</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE" title="tensorrt_llm::runtime::IBuffer::view::TConstPtr"><span class="n"><span class="pre">TConstPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="kt"><span class="pre">int</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1af28ec3097ffc66614052cef9392265bb"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer14UniqueConstPtrE" title="tensorrt_llm::runtime::IBuffer::UniqueConstPtr"><span class="n"><span class="pre">UniqueConstPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">view</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE" title="tensorrt_llm::runtime::IBuffer::view::TConstPtr"><span class="n"><span class="pre">TConstPtr</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">tensor</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7IBuffer4viewE14UniqueConstPtrRR9TConstPtrNSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE"></span><span id="tensorrt_llm::runtime::IBuffer::wrap__voidP.DataType.std::s.std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a6cf1157eb353c90dbe12711be9af63f2"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE" title="tensorrt_llm::runtime::IBuffer::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">wrap</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">data</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer8DataTypeE" title="tensorrt_llm::runtime::IBuffer::DataType"><span class="n"><span class="pre">DataType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">capacity</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tENSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Wraps the given <code class="docutils literal notranslate"><span class="pre">data</span></code> in an <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IBuffer"><span class="std std-ref"><span class="pre">IBuffer</span></span></a></code>. The <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IBuffer"><span class="std std-ref"><span class="pre">IBuffer</span></span></a></code> will not own the underlying <code class="docutils literal notranslate"><span class="pre">data</span></code> and cannot be resized beyond <code class="docutils literal notranslate"><span class="pre">capacity</span></code>. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>data</strong> – The data to wrap. </p></li>
|
||
<li><p><strong>type</strong> – The data type of the <code class="docutils literal notranslate"><span class="pre">data</span></code>. </p></li>
|
||
<li><p><strong>size</strong> – The size of the buffer. </p></li>
|
||
<li><p><strong>capacity</strong> – The capacity of the buffer. </p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>An <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IBuffer"><span class="std std-ref"><span class="pre">IBuffer</span></span></a></code>. </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE"></span><span id="tensorrt_llm::runtime::IBuffer::wrap__voidP.DataType.std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1af1fb9e5497bfc31b149ff9477161068d"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE" title="tensorrt_llm::runtime::IBuffer::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">wrap</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">data</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer8DataTypeE" title="tensorrt_llm::runtime::IBuffer::DataType"><span class="n"><span class="pre">DataType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer4wrapEPv8DataTypeNSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime7IBuffer4wrapEP1TNSt6size_tENSt6size_tE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime7IBuffer4wrapEP1TNSt6size_tENSt6size_tE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a1f5dd20e613af0bc2a05f0b09343535d"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE" title="tensorrt_llm::runtime::IBuffer::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">wrap</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE" title="tensorrt_llm::runtime::IBuffer::wrap::T"><span class="n"><span class="pre">T</span></span></a><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">data</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">capacity</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tENSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime7IBuffer4wrapEP1TNSt6size_tE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime7IBuffer4wrapEP1TNSt6size_tE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a2e4240d0d7f78a278716c8faccf5e9f9"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE" title="tensorrt_llm::runtime::IBuffer::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">wrap</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE" title="tensorrt_llm::runtime::IBuffer::wrap::T"><span class="n"><span class="pre">T</span></span></a><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">data</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrP1TNSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime7IBuffer4wrapERNSt6vectorI1TEE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime7IBuffer4wrapERNSt6vectorI1TEE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a84fdf2b484eee3440646edfece5b85b0"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9UniquePtrE" title="tensorrt_llm::runtime::IBuffer::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">wrap</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE" title="tensorrt_llm::runtime::IBuffer::wrap::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">v</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime7IBuffer4wrapE9UniquePtrRNSt6vectorI1TEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv"></span><span id="tensorrt_llm::runtime::IBuffer::memoryType__voidCP"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1a2c714d66d0336cac0708008e59dd71cd"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">memoryType</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">data</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer10memoryTypeEPKv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Determine the memory type of a pointer. </p>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-protected-functions">Protected Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7IBuffer7IBufferEv"></span><span id="_CPPv2N12tensorrt_llm7runtime7IBuffer7IBufferEv"></span><span id="tensorrt_llm::runtime::IBuffer::IBuffer"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1ad6ad0acb873c47b64fc8fec029696ac2"></span><span class="sig-name descname"><span class="n"><span class="pre">IBuffer</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">default</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer7IBufferEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE"></span><span id="_CPPv2NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE"></span><span id="tensorrt_llm::runtime::IBuffer::toBytes__std::sC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IBuffer_1aade9d63190ac92fdb3561a61af5ab2ee"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">toBytes</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7IBuffer7toBytesENSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns an array index or size in bytes. </p>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime11BufferRangeE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime11BufferRangeE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">BufferRange</span></span></span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange10value_typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange10value_typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange10value_typeE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1a577abddadeb9927120873f9d07325e37"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">value_type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE" title="tensorrt_llm::runtime::BufferRange::T"><span class="n"><span class="pre">T</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange10value_typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange9size_typeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange9size_typeE"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange9size_typeE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1ac52032549a72c5078e9dea0d731626ab"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size_type</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange9size_typeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange9referenceE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange9referenceE"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange9referenceE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1acb95456868b359618379a83adc048eaf"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">reference</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange10value_typeE" title="tensorrt_llm::runtime::BufferRange::value_type"><span class="n"><span class="pre">value_type</span></span></a><span class="p"><span class="pre">&</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange9referenceE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange15const_referenceE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange15const_referenceE"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange15const_referenceE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1aed057be953bd7fb90a48f5a7c3ae1692"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">const_reference</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange10value_typeE" title="tensorrt_llm::runtime::BufferRange::value_type"><span class="n"><span class="pre">value_type</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">&</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange15const_referenceE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange7pointerE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange7pointerE"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange7pointerE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1a286cbcbcb22a4f81104c9124130118c3"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">pointer</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE" title="tensorrt_llm::runtime::BufferRange::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">*</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange7pointerE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange13const_pointerE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange13const_pointerE"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange13const_pointerE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1aad04e26d81c56579e3d6a69ac5fa7412"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">const_pointer</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE" title="tensorrt_llm::runtime::BufferRange::T"><span class="n"><span class="pre">T</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">*</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange13const_pointerE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange8iteratorE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange8iteratorE"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange8iteratorE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1aeb69cf6a643d84e5c7d051bee4311869"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">iterator</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange7pointerE" title="tensorrt_llm::runtime::BufferRange::pointer"><span class="n"><span class="pre">pointer</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange8iteratorE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange14const_iteratorE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange14const_iteratorE"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange14const_iteratorE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1a36e1f97c5d72f04e004f1624a5709986"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">const_iterator</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange13const_pointerE" title="tensorrt_llm::runtime::BufferRange::const_pointer"><span class="n"><span class="pre">const_pointer</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange14const_iteratorE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer"></span><span id="tensorrt_llm::runtime::BufferRange::BufferRange__IBufferR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1a28e8d9ed5250f967aa8f06317074af7b"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">BufferRange</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">buffer</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange11BufferRangeER7IBuffer" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange5beginEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange5beginEv"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange5beginEv"></span><span id="tensorrt_llm::runtime::BufferRange::begin"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1aadf490250d5ce134a93e32ee11a34980"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange8iteratorE" title="tensorrt_llm::runtime::BufferRange::iterator"><span class="n"><span class="pre">iterator</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">begin</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange5beginEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange3endEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange3endEv"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange3endEv"></span><span id="tensorrt_llm::runtime::BufferRange::end"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1aefcb27b14d94348a6fad611d64fbac92"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange8iteratorE" title="tensorrt_llm::runtime::BufferRange::iterator"><span class="n"><span class="pre">iterator</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">end</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange3endEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11BufferRange5beginEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11BufferRange5beginEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11BufferRange5beginEv"></span><span id="tensorrt_llm::runtime::BufferRange::beginC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1a7fd5ff6c02c395fa4237a0eb1d9330cf"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange14const_iteratorE" title="tensorrt_llm::runtime::BufferRange::const_iterator"><span class="n"><span class="pre">const_iterator</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">begin</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11BufferRange5beginEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11BufferRange3endEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11BufferRange3endEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11BufferRange3endEv"></span><span id="tensorrt_llm::runtime::BufferRange::endC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1a758833712fb9f5aac0ec22591d767fee"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange14const_iteratorE" title="tensorrt_llm::runtime::BufferRange::const_iterator"><span class="n"><span class="pre">const_iterator</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">end</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11BufferRange3endEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange6cbeginEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange6cbeginEv"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange6cbeginEv"></span><span id="tensorrt_llm::runtime::BufferRange::cbegin"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1aad76274f379a648c172fa9f064f88d62"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange14const_iteratorE" title="tensorrt_llm::runtime::BufferRange::const_iterator"><span class="n"><span class="pre">const_iterator</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cbegin</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange6cbeginEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange4cendEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange4cendEv"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange4cendEv"></span><span id="tensorrt_llm::runtime::BufferRange::cend"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1a28a237e06e8971046f0fd4d7d9011fff"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange14const_iteratorE" title="tensorrt_llm::runtime::BufferRange::const_iterator"><span class="n"><span class="pre">const_iterator</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cend</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange4cendEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11BufferRange6cbeginEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11BufferRange6cbeginEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11BufferRange6cbeginEv"></span><span id="tensorrt_llm::runtime::BufferRange::cbeginC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1a8e5dfa0b4e150b5fdc0ce78af3c5d243"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange14const_iteratorE" title="tensorrt_llm::runtime::BufferRange::const_iterator"><span class="n"><span class="pre">const_iterator</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cbegin</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11BufferRange6cbeginEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11BufferRange4cendEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11BufferRange4cendEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11BufferRange4cendEv"></span><span id="tensorrt_llm::runtime::BufferRange::cendC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1a5df247c962064585ba1c47242a562dea"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange14const_iteratorE" title="tensorrt_llm::runtime::BufferRange::const_iterator"><span class="n"><span class="pre">const_iterator</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cend</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11BufferRange4cendEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11BufferRange4sizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11BufferRange4sizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11BufferRange4sizeEv"></span><span id="tensorrt_llm::runtime::BufferRange::sizeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1add27991a49b2ff4b17b187711cd9eba6"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange9size_typeE" title="tensorrt_llm::runtime::BufferRange::size_type"><span class="n"><span class="pre">size_type</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">size</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11BufferRange4sizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRangeixE9size_type">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRangeixE9size_type"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRangeixE9size_type"></span><span id="tensorrt_llm::runtime::BufferRange::subscript-operator__size_type"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1ab65060237344abbc8db90f2062abb3ab"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange9referenceE" title="tensorrt_llm::runtime::BufferRange::reference"><span class="n"><span class="pre">reference</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="k"><span class="pre">operator</span></span><span class="o"><span class="pre">[]</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange9size_typeE" title="tensorrt_llm::runtime::BufferRange::size_type"><span class="n"><span class="pre">size_type</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">index</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRangeixE9size_type" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11BufferRangeixE9size_type">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11BufferRangeixE9size_type"></span><span id="_CPPv2NK12tensorrt_llm7runtime11BufferRangeixE9size_type"></span><span id="tensorrt_llm::runtime::BufferRange::subscript-operator__size_typeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1acc8eff6f7541d117de3e09730425a430"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange15const_referenceE" title="tensorrt_llm::runtime::BufferRange::const_reference"><span class="n"><span class="pre">const_reference</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="k"><span class="pre">operator</span></span><span class="o"><span class="pre">[]</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange9size_typeE" title="tensorrt_llm::runtime::BufferRange::size_type"><span class="n"><span class="pre">size_type</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">index</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11BufferRangeixE9size_type" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange5mDataE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange5mDataE"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange5mDataE"></span><span id="tensorrt_llm::runtime::BufferRange::mData__TP"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1afd541e9707bd79322c5290261787902e"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime11BufferRangeE" title="tensorrt_llm::runtime::BufferRange::T"><span class="n"><span class="pre">T</span></span></a><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="sig-name descname"><span class="n"><span class="pre">mData</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange5mDataE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11BufferRange5mSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11BufferRange5mSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime11BufferRange5mSizeE"></span><span id="tensorrt_llm::runtime::BufferRange::mSize__size_type"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1BufferRange_1ae18e3afe46fa34b6f3a8d5bfa7911bfc"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange9size_typeE" title="tensorrt_llm::runtime::BufferRange::size_type"><span class="n"><span class="pre">size_type</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11BufferRange5mSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="igptdecoderbatch-h">
|
||
<h2>iGptDecoderBatch.h<a class="headerlink" href="#igptdecoderbatch-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatchE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16IGptDecoderBatchE"></span><span id="_CPPv2N12tensorrt_llm7runtime16IGptDecoderBatchE"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">IGptDecoderBatch</span></span></span><span class="w"> </span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="k"><span class="pre">public</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv412tensorrt_llm" title="tensorrt_llm"><span class="n"><span class="pre">tensorrt_llm</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimeE" title="tensorrt_llm::runtime"><span class="n"><span class="pre">runtime</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoderE" title="tensorrt_llm::runtime::IStatefulGptDecoder"><span class="n"><span class="pre">IStatefulGptDecoder</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatchE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="docutils container">
|
||
<em>#include <iGptDecoderBatch.h></em></div>
|
||
<p>GPT decoder class with support for in-flight batching. </p>
|
||
<p>Subclassed by <a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1GptDecoderBatch"><span class="std std-ref">tensorrt_llm::runtime::GptDecoderBatch</span></a></p>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch13CudaStreamPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16IGptDecoderBatch13CudaStreamPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime16IGptDecoderBatch13CudaStreamPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1a8968dd741ba1d28cddca68d850a62f59"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">CudaStreamPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStreamE" title="tensorrt_llm::runtime::CudaStream"><span class="n"><span class="pre">CudaStream</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch13CudaStreamPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16IGptDecoderBatch9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime16IGptDecoderBatch9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1ac23bb332c54e6c2b665d5f35fc64baf8"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch8TokenPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16IGptDecoderBatch8TokenPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime16IGptDecoderBatch8TokenPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1aefe802b00d9cc338c76f2bfc7bafad4c"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TokenPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unique_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE" title="tensorrt_llm::runtime::decoder_batch"><span class="n"><span class="pre">decoder_batch</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5TokenE" title="tensorrt_llm::runtime::decoder_batch::Token"><span class="n"><span class="pre">Token</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch8TokenPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch10newRequestE8SizeTypeRKN13decoder_batch7RequestERK14SamplingConfig">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16IGptDecoderBatch10newRequestE8SizeTypeRKN13decoder_batch7RequestERK14SamplingConfig"></span><span id="_CPPv2N12tensorrt_llm7runtime16IGptDecoderBatch10newRequestE8SizeTypeRKN13decoder_batch7RequestERK14SamplingConfig"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::newRequest__SizeType.decoder_batch::RequestCR.SamplingConfigCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1a795d229a59bc66688d9609ce62b40775"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">newRequest</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchIdx</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE" title="tensorrt_llm::runtime::decoder_batch"><span class="n"><span class="pre">decoder_batch</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7RequestE" title="tensorrt_llm::runtime::decoder_batch::Request"><span class="n"><span class="pre">Request</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">request</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="tensorrt_llm::runtime::SamplingConfig"><span class="n"><span class="pre">SamplingConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">samplingConfig</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch10newRequestE8SizeTypeRKN13decoder_batch7RequestERK14SamplingConfig" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Initialize the decoder at <code class="docutils literal notranslate"><span class="pre">batchIdx</span></code> with a new <code class="docutils literal notranslate"><span class="pre">request</span></code>. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16IGptDecoderBatch12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE"></span><span id="_CPPv2N12tensorrt_llm7runtime16IGptDecoderBatch12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::forwardAsync__decoder_batch::OutputR.decoder_batch::InputCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1a6c990b4aa463031ee4d4e2724997ae0e"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch8TokenPtrE" title="tensorrt_llm::runtime::IGptDecoderBatch::TokenPtr"><span class="n"><span class="pre">TokenPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forwardAsync</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE" title="tensorrt_llm::runtime::decoder_batch"><span class="n"><span class="pre">decoder_batch</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch6OutputE" title="tensorrt_llm::runtime::decoder_batch::Output"><span class="n"><span class="pre">Output</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE" title="tensorrt_llm::runtime::decoder_batch"><span class="n"><span class="pre">decoder_batch</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5InputE" title="tensorrt_llm::runtime::decoder_batch::Input"><span class="n"><span class="pre">Input</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">input</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch12forwardAsyncERN13decoder_batch6OutputERKN13decoder_batch5InputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Run one step for all requests without blocking the host process and return the token for synchronization. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch11forwardSyncERKN13decoder_batch5TokenE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16IGptDecoderBatch11forwardSyncERKN13decoder_batch5TokenE"></span><span id="_CPPv2N12tensorrt_llm7runtime16IGptDecoderBatch11forwardSyncERKN13decoder_batch5TokenE"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::forwardSync__decoder_batch::TokenCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1a7171eb7513202c09360d4139117c424e"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forwardSync</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE" title="tensorrt_llm::runtime::decoder_batch"><span class="n"><span class="pre">decoder_batch</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5TokenE" title="tensorrt_llm::runtime::decoder_batch::Token"><span class="n"><span class="pre">Token</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">token</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch11forwardSyncERKN13decoder_batch5TokenE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Wait for the call to <code class="docutils literal notranslate"><span class="pre">forwardAsync</span></code> associated with a token to complete. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch7forwardERN13decoder_batch6OutputERKN13decoder_batch5InputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16IGptDecoderBatch7forwardERN13decoder_batch6OutputERKN13decoder_batch5InputE"></span><span id="_CPPv2N12tensorrt_llm7runtime16IGptDecoderBatch7forwardERN13decoder_batch6OutputERKN13decoder_batch5InputE"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::forward__decoder_batch::OutputR.decoder_batch::InputCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1ab7e07276f33bfa6ef3c90baa49ee6eec"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forward</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE" title="tensorrt_llm::runtime::decoder_batch"><span class="n"><span class="pre">decoder_batch</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch6OutputE" title="tensorrt_llm::runtime::decoder_batch::Output"><span class="n"><span class="pre">Output</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE" title="tensorrt_llm::runtime::decoder_batch"><span class="n"><span class="pre">decoder_batch</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5InputE" title="tensorrt_llm::runtime::decoder_batch::Input"><span class="n"><span class="pre">Input</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">input</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch7forwardERN13decoder_batch6OutputERKN13decoder_batch5InputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Run one step for all requests and wait for completion on the host. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch12getOutputIdsE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime16IGptDecoderBatch12getOutputIdsE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime16IGptDecoderBatch12getOutputIdsE8SizeType"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::getOutputIds__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1a56bbbba5d310262f3614c9ca16d6e1d7"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::IGptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getOutputIds</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchIdx</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch12getOutputIdsE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p><strong>batchIdx</strong> – index of the batch </p>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>[maxBeamWidth, maxInputLength + maxNewTokens], contains input token ids and generated token ids without padding for request <code class="docutils literal notranslate"><span class="pre">batchIdx</span></code>, on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch8finalizeE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime16IGptDecoderBatch8finalizeE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime16IGptDecoderBatch8finalizeE8SizeType"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::finalize__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1a37a0d386522f5b256addcfbe32005538"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="tensorrt_llm::runtime::CudaEvent"><span class="n"><span class="pre">CudaEvent</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">finalize</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchIdx</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch8finalizeE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Gather final beam search results for request <code class="docutils literal notranslate"><span class="pre">batchIdx</span></code>. Result will only be available after event returned. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch11getFinishedEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime16IGptDecoderBatch11getFinishedEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime16IGptDecoderBatch11getFinishedEv"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::getFinishedC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1aaa0b5e6c02b7043c3b29a1d8ca68df76"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getFinished</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch11getFinishedEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[batchSize (actual)], marks finished requests (per batch) </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch14getCumLogProbsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime16IGptDecoderBatch14getCumLogProbsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime16IGptDecoderBatch14getCumLogProbsEv"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::getCumLogProbsC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1afa130a3df00b7d86e280f5caf017ab9d"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::IGptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getCumLogProbs</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch14getCumLogProbsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[batchSize, beamWidth], cumulative log probabilities (per beam), on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch14getCumLogProbsE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime16IGptDecoderBatch14getCumLogProbsE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime16IGptDecoderBatch14getCumLogProbsE8SizeType"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::getCumLogProbs__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1a2176789e8a2e659f0b6fa4137dbffaaf"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::IGptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getCumLogProbs</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchIdx</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch14getCumLogProbsE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[beamWidth], cumulative log probabilities (per beam) for request batchIdx, on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch11getLogProbsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime16IGptDecoderBatch11getLogProbsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime16IGptDecoderBatch11getLogProbsEv"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::getLogProbsC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1a8b387a350a37f25a383bdcc18e66f8f8"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::IGptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getLogProbs</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch11getLogProbsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[batchSize, beamWidth, maxSeqLen], log probabilities (per beam), on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch11getLogProbsE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime16IGptDecoderBatch11getLogProbsE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime16IGptDecoderBatch11getLogProbsE8SizeType"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::getLogProbs__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1af5635a23ba453db9f1e5edfa304e0958"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::IGptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getLogProbs</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchIdx</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch11getLogProbsE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[beamWidth, maxSeqLen], cumulative log probabilities (per beam) for request batchIdx, on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch12getParentIdsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime16IGptDecoderBatch12getParentIdsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime16IGptDecoderBatch12getParentIdsEv"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::getParentIdsC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1a1a37b811b0cc2a98507b57109844a06c"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch9TensorPtrE" title="tensorrt_llm::runtime::IGptDecoderBatch::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getParentIds</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch12getParentIdsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch10getNbStepsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime16IGptDecoderBatch10getNbStepsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime16IGptDecoderBatch10getNbStepsEv"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::getNbStepsC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1a935e778ac2c14276d940e09b9411e8ed"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getNbSteps</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime16IGptDecoderBatch10getNbStepsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-protected-functions">Protected Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch16IGptDecoderBatchEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime16IGptDecoderBatch16IGptDecoderBatchEv"></span><span id="_CPPv2N12tensorrt_llm7runtime16IGptDecoderBatch16IGptDecoderBatchEv"></span><span id="tensorrt_llm::runtime::IGptDecoderBatch::IGptDecoderBatch"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch_1abfc9e04a4f042f3c0220c84cff407ff3"></span><span class="sig-name descname"><span class="n"><span class="pre">IGptDecoderBatch</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">default</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime16IGptDecoderBatch16IGptDecoderBatchEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batchE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batchE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batchE"></span><span id="tensorrt_llm::runtime::decoder_batch"></span><span class="target" id="namespacetensorrt__llm_1_1runtime_1_1decoder__batch"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">decoder_batch</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batchE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-typedefs">Typedefs</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch6OutputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch6OutputE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch6OutputE"></span><span class="target" id="iGptDecoderBatch_8h_1a575658a5bf5a41310da470e54bf965d9"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Output</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoderE" title="tensorrt_llm::runtime::decoder"><span class="n"><span class="pre">decoder</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder6OutputE" title="tensorrt_llm::runtime::decoder::Output"><span class="n"><span class="pre">Output</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch6OutputE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7RequestE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7RequestE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7RequestE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Request</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7RequestE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request14ConstTensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request14ConstTensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request14ConstTensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1a0f1d32403828dcdb0db0badc5d0ba8e6"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">ConstTensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor14SharedConstPtrE" title="tensorrt_llm::runtime::ITensor::SharedConstPtr"><span class="n"><span class="pre">SharedConstPtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request14ConstTensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1a95d9dd610e7a6295d06f75a33cbb4c43"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9BufferPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request9BufferPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request9BufferPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1a78becbf7fa5928420a994c0d9d9ddb65"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">BufferPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE" title="tensorrt_llm::runtime::IBuffer::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9BufferPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14ConstTensorPtr8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14ConstTensorPtr8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14ConstTensorPtr8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::Request__ConstTensorPtr.SizeType.std::optional:SizeType:.std::optional:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1ac001937908b70ca7a843b86c06c1f7ee"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Request</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request14ConstTensorPtrE" title="tensorrt_llm::runtime::decoder_batch::Request::ConstTensorPtr"><span class="n"><span class="pre">ConstTensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">ids</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">inputLen</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="n sig-param"><span class="pre">maxNewTokens</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">nullopt</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="n sig-param"><span class="pre">endId</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">nullopt</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request7RequestE14ConstTensorPtr8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime13decoder_batch7Request22generatedTokensPerStepEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime13decoder_batch7Request22generatedTokensPerStepEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime13decoder_batch7Request22generatedTokensPerStepEv"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::generatedTokensPerStepC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1afc321e118eab079b555525518a0d69d3"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">generatedTokensPerStep</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime13decoder_batch7Request22generatedTokensPerStepEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request3idsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request3idsE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request3idsE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::ids__ConstTensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1ac8aaa11f8da8a1824edf1fb8d23ec40a"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request14ConstTensorPtrE" title="tensorrt_llm::runtime::decoder_batch::Request::ConstTensorPtr"><span class="n"><span class="pre">ConstTensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">ids</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request3idsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request8inputLenE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request8inputLenE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request8inputLenE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::inputLen__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1a88c0c0b993597c07f0dd9a941a04e741"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">inputLen</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request8inputLenE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12maxNewTokensE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request12maxNewTokensE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request12maxNewTokensE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::maxNewTokens__std::optional:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1a5ab1bf54050a431e7c26df7451f2f0f1"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">maxNewTokens</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12maxNewTokensE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request5endIdE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request5endIdE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request5endIdE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::endId__std::optional:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1ac1477f03a617c556bb264121200fcc0e"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">endId</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request5endIdE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftTokensE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request11draftTokensE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request11draftTokensE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::draftTokens__BufferPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1a1a524b5348e2d8ea442050f50ff3f1c7"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9BufferPtrE" title="tensorrt_llm::runtime::decoder_batch::Request::BufferPtr"><span class="n"><span class="pre">BufferPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">draftTokens</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftTokensE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftLogitsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request11draftLogitsE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request11draftLogitsE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::draftLogits__std::optional:TensorPtr:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1afa9181bc52e25fe7dc0e925c69dc8d86"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE" title="tensorrt_llm::runtime::decoder_batch::Request::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">draftLogits</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request11draftLogitsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13embeddingBiasE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request13embeddingBiasE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request13embeddingBiasE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::embeddingBias__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1acbedf401f2f77534aa355f3ecbb0b755"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE" title="tensorrt_llm::runtime::decoder_batch::Request::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">embeddingBias</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13embeddingBiasE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12badWordsListE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request12badWordsListE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request12badWordsListE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::badWordsList__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1af18cc1700b613308c14d492e69ab76e9"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE" title="tensorrt_llm::runtime::decoder_batch::Request::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">badWordsList</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request12badWordsListE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13stopWordsListE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request13stopWordsListE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request13stopWordsListE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::stopWordsList__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1addd0a66af57e7186287ac7e5853c0c9d"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request9TensorPtrE" title="tensorrt_llm::runtime::decoder_batch::Request::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">stopWordsList</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request13stopWordsListE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request18computeCumLogProbsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request18computeCumLogProbsE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request18computeCumLogProbsE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::computeCumLogProbs__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1ae608a0fadb52ad6ac8bd4ae96ab6f3bc"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">computeCumLogProbs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request18computeCumLogProbsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request15computeLogProbsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch7Request15computeLogProbsE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch7Request15computeLogProbsE"></span><span id="tensorrt_llm::runtime::decoder_batch::Request::computeLogProbs__b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Request_1ae35f498de3ce00f4ca94513b5c96ba8a"></span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">computeLogProbs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch7Request15computeLogProbsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5InputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5InputE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5InputE"></span><span id="tensorrt_llm::runtime::decoder_batch::Input"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Input"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Input</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5InputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Input_1aa8152e055448762bd78ad70f53eda8ba"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorConstPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor14SharedConstPtrE" title="tensorrt_llm::runtime::ITensor::SharedConstPtr"><span class="n"><span class="pre">SharedConstPtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5Input9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5Input9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Input_1ac182ee5aa51be63dfe20586ecaf40043"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEERKNSt6vectorIbEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEERKNSt6vectorIbEE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEERKNSt6vectorIbEE"></span><span id="tensorrt_llm::runtime::decoder_batch::Input::Input__std::vector:TensorConstPtr:CR.std::vector:b:CR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Input_1aace73d69f6cbc9cb1342cd83ecf0c506"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Input</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE" title="tensorrt_llm::runtime::decoder_batch::Input::TensorConstPtr"><span class="n"><span class="pre">TensorConstPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">logits</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">active</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEERKNSt6vectorIbEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEE"></span><span id="tensorrt_llm::runtime::decoder_batch::Input::Input__std::vector:TensorConstPtr:CR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Input_1aba21ef996e9e6fc1aca5bcc09fcd55ad"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Input</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE" title="tensorrt_llm::runtime::decoder_batch::Input::TensorConstPtr"><span class="n"><span class="pre">TensorConstPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">logits</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI14TensorConstPtrEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEERKNSt6vectorIbEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEERKNSt6vectorIbEE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEERKNSt6vectorIbEE"></span><span id="tensorrt_llm::runtime::decoder_batch::Input::Input__std::vector:TensorPtr:CR.std::vector:b:CR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Input_1ad2b3fc875250c83be03032f984154830"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Input</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input9TensorPtrE" title="tensorrt_llm::runtime::decoder_batch::Input::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">logits</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">active</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEERKNSt6vectorIbEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEE"></span><span id="tensorrt_llm::runtime::decoder_batch::Input::Input__std::vector:TensorPtr:CR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Input_1ad5c9b6c5a35df62813d6bedaae41660f"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Input</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input9TensorPtrE" title="tensorrt_llm::runtime::decoder_batch::Input::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">logits</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input5InputERKNSt6vectorI9TensorPtrEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input6logitsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5Input6logitsE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5Input6logitsE"></span><span id="tensorrt_llm::runtime::decoder_batch::Input::logits__std::vector:TensorConstPtr:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Input_1a9a9e759d4b5fa7e52ebded01ca1479e2"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE" title="tensorrt_llm::runtime::decoder_batch::Input::TensorConstPtr"><span class="n"><span class="pre">TensorConstPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">logits</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input6logitsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input6activeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5Input6activeE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5Input6activeE"></span><span id="tensorrt_llm::runtime::decoder_batch::Input::active__std::vector:b:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Input_1a85bb8bda589fcebf0c19994d76a26968"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">active</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input6activeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input16cacheIndirectionE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5Input16cacheIndirectionE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5Input16cacheIndirectionE"></span><span id="tensorrt_llm::runtime::decoder_batch::Input::cacheIndirection__TensorConstPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Input_1a29217fe46691aef9e896775d4aa30c83"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input14TensorConstPtrE" title="tensorrt_llm::runtime::decoder_batch::Input::TensorConstPtr"><span class="n"><span class="pre">TensorConstPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cacheIndirection</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Input16cacheIndirectionE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5TokenE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5TokenE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5TokenE"></span><span id="tensorrt_llm::runtime::decoder_batch::Token"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Token"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Token</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5TokenE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token5TokenERR9CudaEventRKNSt6vectorIbEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5Token5TokenERR9CudaEventRKNSt6vectorIbEE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5Token5TokenERR9CudaEventRKNSt6vectorIbEE"></span><span id="tensorrt_llm::runtime::decoder_batch::Token::Token__CudaEventRR.std::vector:b:CR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Token_1ab35d80ddc444d443a35ae642d3e9f862"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Token</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="tensorrt_llm::runtime::CudaEvent"><span class="n"><span class="pre">CudaEvent</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">event</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">active</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token5TokenERR9CudaEventRKNSt6vectorIbEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token5eventE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5Token5eventE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5Token5eventE"></span><span id="tensorrt_llm::runtime::decoder_batch::Token::event__CudaEvent"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Token_1a8a4fa5d069ee58377e79ddde0955dbde"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime9CudaEventE" title="tensorrt_llm::runtime::CudaEvent"><span class="n"><span class="pre">CudaEvent</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">event</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token5eventE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token6activeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13decoder_batch5Token6activeE"></span><span id="_CPPv2N12tensorrt_llm7runtime13decoder_batch5Token6activeE"></span><span id="tensorrt_llm::runtime::decoder_batch::Token::active__std::vector:b:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder__batch_1_1Token_1a92563b2a16378f689f9d600d8712f8fd"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">active</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13decoder_batch5Token6activeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="istatefulgptdecoder-h">
|
||
<h2>iStatefulGptDecoder.h<a class="headerlink" href="#istatefulgptdecoder-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoderE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19IStatefulGptDecoderE"></span><span id="_CPPv2N12tensorrt_llm7runtime19IStatefulGptDecoderE"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">IStatefulGptDecoder</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoderE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="docutils container">
|
||
<em>#include <iStatefulGptDecoder.h></em></div>
|
||
<p>GPT decoder class with support for in-flight batching. </p>
|
||
<p>Subclassed by <a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IGptDecoderBatch"><span class="std std-ref">tensorrt_llm::runtime::IGptDecoderBatch</span></a></p>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder13CudaStreamPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19IStatefulGptDecoder13CudaStreamPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime19IStatefulGptDecoder13CudaStreamPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1a310eb1dafd035c945176ea533ec74588"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">CudaStreamPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10CudaStreamE" title="tensorrt_llm::runtime::CudaStream"><span class="n"><span class="pre">CudaStream</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder13CudaStreamPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1a3987d8ce3a11babf865981af9d4ea18e"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupE8SizeType8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19IStatefulGptDecoder5setupE8SizeType8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime19IStatefulGptDecoder5setupE8SizeType8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::setup__SizeType.SizeType.SizeType.SizeType.SizeType.nvinfer1::DataType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1ae68db8a8fcb0686edc6135e1780e2041"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setup</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxBatchSize</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxBeamWidth</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxAttentionWindow</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxSequenceLength</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">maxTokensPerStep</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">dtype</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder5setupE8SizeType8SizeType8SizeType8SizeType8SizeTypeN8nvinfer18DataTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Setup the decoder before calling <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1a152618c3967cc29d314bd77d17c51e27"><span class="std std-ref"><span class="pre">forward()</span></span></a></code>, also calls reshapeBuffers. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19IStatefulGptDecoder8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig"></span><span id="_CPPv2N12tensorrt_llm7runtime19IStatefulGptDecoder8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::newBatch__GenerationInputCR.GenerationOutputCR.SamplingConfigCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1a2b8ead8e3fca4dcb2c6e95d8e063b3cf"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">newBatch</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime15GenerationInputE" title="tensorrt_llm::runtime::GenerationInput"><span class="n"><span class="pre">GenerationInput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">inputs</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime16GenerationOutputE" title="tensorrt_llm::runtime::GenerationOutput"><span class="n"><span class="pre">GenerationOutput</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">outputs</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="tensorrt_llm::runtime::SamplingConfig"><span class="n"><span class="pre">SamplingConfig</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">samplingConfig</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder8newBatchERK15GenerationInputRK16GenerationOutputRK14SamplingConfig" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Initialize the decoder with new batch of inputs. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder12forwardAsyncERN7decoder6OutputERKN7decoder5InputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19IStatefulGptDecoder12forwardAsyncERN7decoder6OutputERKN7decoder5InputE"></span><span id="_CPPv2N12tensorrt_llm7runtime19IStatefulGptDecoder12forwardAsyncERN7decoder6OutputERKN7decoder5InputE"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::forwardAsync__decoder::OutputR.decoder::InputCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1a7bb51780e6e9a6c41de214ffac8b07be"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forwardAsync</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoderE" title="tensorrt_llm::runtime::decoder"><span class="n"><span class="pre">decoder</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder6OutputE" title="tensorrt_llm::runtime::decoder::Output"><span class="n"><span class="pre">Output</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoderE" title="tensorrt_llm::runtime::decoder"><span class="n"><span class="pre">decoder</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder5InputE" title="tensorrt_llm::runtime::decoder::Input"><span class="n"><span class="pre">Input</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">input</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder12forwardAsyncERN7decoder6OutputERKN7decoder5InputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Run one step for all requests without blocking the host thread. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder11forwardSyncEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19IStatefulGptDecoder11forwardSyncEv"></span><span id="_CPPv2N12tensorrt_llm7runtime19IStatefulGptDecoder11forwardSyncEv"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::forwardSync"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1a2a2a7296d9137e434da174a04626722a"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forwardSync</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder11forwardSyncEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Wait for the last call to <code class="docutils literal notranslate"><span class="pre">forwardAsync</span></code> to complete. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder7forwardERN7decoder6OutputERKN7decoder5InputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19IStatefulGptDecoder7forwardERN7decoder6OutputERKN7decoder5InputE"></span><span id="_CPPv2N12tensorrt_llm7runtime19IStatefulGptDecoder7forwardERN7decoder6OutputERKN7decoder5InputE"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::forward__decoder::OutputR.decoder::InputCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1a152618c3967cc29d314bd77d17c51e27"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">forward</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoderE" title="tensorrt_llm::runtime::decoder"><span class="n"><span class="pre">decoder</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder6OutputE" title="tensorrt_llm::runtime::decoder::Output"><span class="n"><span class="pre">Output</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoderE" title="tensorrt_llm::runtime::decoder"><span class="n"><span class="pre">decoder</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder5InputE" title="tensorrt_llm::runtime::decoder::Input"><span class="n"><span class="pre">Input</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">input</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder7forwardERN7decoder6OutputERKN7decoder5InputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Run one step for all requests. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder8finalizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime19IStatefulGptDecoder8finalizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime19IStatefulGptDecoder8finalizeEv"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::finalizeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1ae29a2934bf1c89392862b8d83f199fa0"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">finalize</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder8finalizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Gather final beam search results for all requests. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder12getOutputIdsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime19IStatefulGptDecoder12getOutputIdsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime19IStatefulGptDecoder12getOutputIdsEv"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::getOutputIdsC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1a3f98067a78b64a319acb4a8b667e6249"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE" title="tensorrt_llm::runtime::IStatefulGptDecoder::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getOutputIds</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder12getOutputIdsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[batchSize, beamWidth, maxSequenceLength], all token ids, on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder14getCumLogProbsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime19IStatefulGptDecoder14getCumLogProbsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime19IStatefulGptDecoder14getCumLogProbsEv"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::getCumLogProbsC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1ad0a22a269ec223d875f0d68bb5efc744"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE" title="tensorrt_llm::runtime::IStatefulGptDecoder::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getCumLogProbs</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder14getCumLogProbsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[batchSize, maxBeamWidth], cumulative log probabilities (per beam), on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder11getLogProbsEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime19IStatefulGptDecoder11getLogProbsEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime19IStatefulGptDecoder11getLogProbsEv"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::getLogProbsC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1ad1d6dd18c64d32cf98b31792c9fc499b"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE" title="tensorrt_llm::runtime::IStatefulGptDecoder::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getLogProbs</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder11getLogProbsEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[batchSize, maxBeamWidth, maxSequenceLength], log probabilities (per beam), on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder12getNewTokensE8SizeType">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime19IStatefulGptDecoder12getNewTokensE8SizeType"></span><span id="_CPPv2NK12tensorrt_llm7runtime19IStatefulGptDecoder12getNewTokensE8SizeType"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::getNewTokens__SizeTypeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1aff1095cf556ce2d4893a43fbc0c5527b"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE" title="tensorrt_llm::runtime::IStatefulGptDecoder::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getNewTokens</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">iter</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder12getNewTokensE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Get tokens generated in one step of last forward pass. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p><strong>iter</strong> – The iteration within [0; maxTokensPerStep) for which to get the tokens </p>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>[batchSize, beamWidth], tokens generated in <code class="docutils literal notranslate"><span class="pre">iter</span></code> (per beam), on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder15getAllNewTokensEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime19IStatefulGptDecoder15getAllNewTokensEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime19IStatefulGptDecoder15getAllNewTokensEv"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::getAllNewTokensC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1a9ebd85b4c95c5bb2623565e4ab3983b6"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE" title="tensorrt_llm::runtime::IStatefulGptDecoder::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getAllNewTokens</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder15getAllNewTokensEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Get maxTokensPerStep tokens generated in the last forward pass. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[maxTokensPerStep, batchSize, maxBeamWidth], tokens generated in last forward pass, on gpu </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder13getNbFinishedEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime19IStatefulGptDecoder13getNbFinishedEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime19IStatefulGptDecoder13getNbFinishedEv"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::getNbFinishedC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1a551e560fe7c9120c500f47fa84514d99"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder9TensorPtrE" title="tensorrt_llm::runtime::IStatefulGptDecoder::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getNbFinished</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime19IStatefulGptDecoder13getNbFinishedEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="field-list simple">
|
||
<dt class="field-odd">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>[1], number of finished sequences, in pinned host memory </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoderD0Ev">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19IStatefulGptDecoderD0Ev"></span><span id="_CPPv2N12tensorrt_llm7runtime19IStatefulGptDecoderD0Ev"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::~IStatefulGptDecoder"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1a7dd550e0f0d980fd3f3f655f358e8ff0"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">~IStatefulGptDecoder</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">default</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoderD0Ev" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-protected-functions">Protected Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder19IStatefulGptDecoderEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime19IStatefulGptDecoder19IStatefulGptDecoderEv"></span><span id="_CPPv2N12tensorrt_llm7runtime19IStatefulGptDecoder19IStatefulGptDecoderEv"></span><span id="tensorrt_llm::runtime::IStatefulGptDecoder::IStatefulGptDecoder"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IStatefulGptDecoder_1a898fa69e15fa0d26fde3c7f50fdb8881"></span><span class="sig-name descname"><span class="n"><span class="pre">IStatefulGptDecoder</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">default</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime19IStatefulGptDecoder19IStatefulGptDecoderEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7decoderE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7decoderE"></span><span id="_CPPv2N12tensorrt_llm7runtime7decoderE"></span><span id="tensorrt_llm::runtime::decoder"></span><span class="target" id="namespacetensorrt__llm_1_1runtime_1_1decoder"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">decoder</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7decoderE" title="Link to this definition"></a><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7decoder5InputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7decoder5InputE"></span><span id="_CPPv2N12tensorrt_llm7runtime7decoder5InputE"></span><span id="tensorrt_llm::runtime::decoder::Input"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder_1_1Input"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Input</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7decoder5InputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7decoder5Input9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7decoder5Input9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime7decoder5Input9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder_1_1Input_1a00dc3503cac2813698c97486fba9ca51"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7decoder5Input9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7decoder5Input5InputE9TensorPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7decoder5Input5InputE9TensorPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime7decoder5Input5InputE9TensorPtr"></span><span id="tensorrt_llm::runtime::decoder::Input::Input__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder_1_1Input_1adbf9a04fb7b5c83766b236df5060d24a"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Input</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder5Input9TensorPtrE" title="tensorrt_llm::runtime::decoder::Input::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">logits</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7decoder5Input5InputE9TensorPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7decoder5Input6logitsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7decoder5Input6logitsE"></span><span id="_CPPv2N12tensorrt_llm7runtime7decoder5Input6logitsE"></span><span id="tensorrt_llm::runtime::decoder::Input::logits__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder_1_1Input_1a8b92e3c3e42f408503691dd5fb51e79e"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder5Input9TensorPtrE" title="tensorrt_llm::runtime::decoder::Input::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">logits</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7decoder5Input6logitsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7decoder5Input16cacheIndirectionE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7decoder5Input16cacheIndirectionE"></span><span id="_CPPv2N12tensorrt_llm7runtime7decoder5Input16cacheIndirectionE"></span><span id="tensorrt_llm::runtime::decoder::Input::cacheIndirection__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder_1_1Input_1ae425ecaffbd89893ed70d3ad32c660b1"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder5Input9TensorPtrE" title="tensorrt_llm::runtime::decoder::Input::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cacheIndirection</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7decoder5Input16cacheIndirectionE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7decoder6OutputE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7decoder6OutputE"></span><span id="_CPPv2N12tensorrt_llm7runtime7decoder6OutputE"></span><span id="tensorrt_llm::runtime::decoder::Output"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder_1_1Output"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Output</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7decoder6OutputE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7decoder6Output9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7decoder6Output9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime7decoder6Output9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder_1_1Output_1a2c4dff939d33fec2fd199699c216ff28"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7decoder6Output9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7decoder6Output6OutputEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7decoder6Output6OutputEv"></span><span id="_CPPv2N12tensorrt_llm7runtime7decoder6Output6OutputEv"></span><span id="tensorrt_llm::runtime::decoder::Output::Output"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder_1_1Output_1af52215c47e70f6af33b6353883c24948"></span><span class="sig-name descname"><span class="n"><span class="pre">Output</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">default</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7decoder6Output6OutputEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7decoder6Output16cacheIndirectionE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7decoder6Output16cacheIndirectionE"></span><span id="_CPPv2N12tensorrt_llm7runtime7decoder6Output16cacheIndirectionE"></span><span id="tensorrt_llm::runtime::decoder::Output::cacheIndirection__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder_1_1Output_1ae9e66b08bf05167a9d16130d0518fc0e"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder6Output9TensorPtrE" title="tensorrt_llm::runtime::decoder::Output::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">cacheIndirection</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7decoder6Output16cacheIndirectionE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7decoder6Output15sequenceLengthsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7decoder6Output15sequenceLengthsE"></span><span id="_CPPv2N12tensorrt_llm7runtime7decoder6Output15sequenceLengthsE"></span><span id="tensorrt_llm::runtime::decoder::Output::sequenceLengths__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1decoder_1_1Output_1a25913f9ceca02070a650d1135ba87a72"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7decoder6Output9TensorPtrE" title="tensorrt_llm::runtime::decoder::Output::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">sequenceLengths</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7decoder6Output15sequenceLengthsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="itensor-h">
|
||
<h2>iTensor.h<a class="headerlink" href="#itensor-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv48nvinfer1">
|
||
<span id="_CPPv38nvinfer1"></span><span id="_CPPv28nvinfer1"></span><span id="nvinfer1"></span><span class="target" id="namespacenvinfer1"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">nvinfer1</span></span></span><a class="headerlink" href="#_CPPv48nvinfer1" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-functions">Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE"></span><span id="_CPPv2N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE"></span><span id="tensorrt_llm::runtime::lshift-operator__osR.ITensor::ShapeCR"></span><span class="target" id="iTensor_8h_1ab843bef84b07b782c05c682399ee2b1a"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">ostream</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="k"><span class="pre">operator</span></span><span class="o"><span class="pre"><<</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">ostream</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">dims</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERKN7ITensor5ShapeE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Utility function to print a shape. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor">
|
||
<span id="_CPPv3N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor"></span><span id="_CPPv2N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor"></span><span id="tensorrt_llm::runtime::lshift-operator__osR.ITensorCR"></span><span class="target" id="iTensor_8h_1a2a38821feb0276616dde2d32020ef451"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">ostream</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="k"><span class="pre">operator</span></span><span class="o"><span class="pre"><<</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">ostream</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">output</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">tensor</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtimelsERNSt7ostreamERK7ITensor" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Utility function to print a tensor with its shape. </p>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensorE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensorE"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensorE"></span><span id="tensorrt_llm::runtime::ITensor"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">ITensor</span></span></span><span class="w"> </span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="k"><span class="pre">public</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv412tensorrt_llm" title="tensorrt_llm"><span class="n"><span class="pre">tensorrt_llm</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimeE" title="tensorrt_llm::runtime"><span class="n"><span class="pre">runtime</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor9UniquePtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor9UniquePtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a0ebcd2ee37abad2960daf1346816f348"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">UniquePtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unique_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor9SharedPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor9SharedPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a31e67140fadaeb6eaaf096ff37d640ad"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">SharedPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1ad199f95dd25dfbef298cc7d1f3655d66"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">UniqueConstPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">unique_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor14SharedConstPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor14SharedConstPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor14SharedConstPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a591e6b0aa01a0043967262ffdcc3974d"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">SharedConstPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">shared_ptr</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor14SharedConstPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor5ShapeE"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor5ShapeE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1ab2e78d36e5cc72b4443e832a46147fcc"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">Shape</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">Dims</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor7DimTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor7DimTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor7DimTypeE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a08933f77dd49cd3f0ff4bf832411d6f8"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DimType</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">remove_reference_t</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">decltype</span></span><span class="p"><span class="pre">(</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">d</span></span><span class="p"><span class="pre">[</span></span><span class="m"><span class="pre">0</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">)</span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7DimTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensorD0Ev">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensorD0Ev"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensorD0Ev"></span><span id="tensorrt_llm::runtime::ITensor::~ITensor"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a857da95b81330009b368308ed0c2d3d9"></span><span class="sig-name descname"><span class="n"><span class="pre">~ITensor</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">default</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensorD0Ev" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7ITensor8getShapeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7ITensor8getShapeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime7ITensor8getShapeEv"></span><span id="tensorrt_llm::runtime::ITensor::getShapeC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a9f2d4a0903e581784f5ed94d8ed1d58d"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getShape</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7ITensor8getShapeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns the tensor dimensions. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape"></span><span id="tensorrt_llm::runtime::ITensor::reshape__ShapeCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a772377264b089406fb1cf743ac3163f3"></span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">reshape</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">dims</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7reshapeERK5Shape" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Sets the tensor dimensions. The new size of the tensor will be <code class="docutils literal notranslate"><span class="pre">volume(dims)</span></code></p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE"></span><span id="tensorrt_llm::runtime::ITensor::resize__std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a8ed7ae223a11d8d516216a4d28286f62"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">virtual</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">resize</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">newSize</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor6resizeENSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Resizes the buffer. This is a no-op if the new size is smaller than or equal to the current capacity. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorERK7ITensor">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor7ITensorERK7ITensor"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor7ITensorERK7ITensor"></span><span id="tensorrt_llm::runtime::ITensor::ITensor__ITensorCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1ade4b1d2a214d378f73255357e32bee1f"></span><span class="sig-name descname"><span class="n"><span class="pre">ITensor</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorERK7ITensor" title="tensorrt_llm::runtime::ITensor::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">&</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">delete</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorERK7ITensor" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Not allowed to copy. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensoraSERK7ITensor">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensoraSERK7ITensor"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensoraSERK7ITensor"></span><span id="tensorrt_llm::runtime::ITensor::assign-operator__ITensorCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a943f0acaa8c746fa85980f4e13512a2c"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="k"><span class="pre">operator</span></span><span class="o"><span class="pre">=</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="p"><span class="pre">&</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">delete</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensoraSERK7ITensor" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Not allowed to copy. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor7squeezeE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor7squeezeE8SizeType"></span><span id="tensorrt_llm::runtime::ITensor::squeeze__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a5ca07f1cc675136634c6a435b5b8f8f3"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">squeeze</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">dim</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Removes the given <em>unit</em> dimensions from this tensor. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor9unsqueezeE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor9unsqueezeE8SizeType"></span><span id="tensorrt_llm::runtime::ITensor::unsqueeze__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a9725635429cc853be302ecee91bd4662"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">unsqueeze</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">dim</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Adds a <em>unit</em> dimension at the specified position. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape"></span><span id="_CPPv2NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape"></span><span id="tensorrt_llm::runtime::ITensor::shapeEquals__ShapeCRC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1ab84847a01479731500363a637003e03a"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">shapeEquals</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">other</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERK5Shape" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI8SizeTypeEE">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI8SizeTypeEE"></span><span id="_CPPv2NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI8SizeTypeEE"></span><span id="tensorrt_llm::runtime::ITensor::shapeEquals__std::initializer_list:SizeType:CRC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a0589c32d94c01c24f0f08a313aeab0ba"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">shapeEquals</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">initializer_list</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">other</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime7ITensor11shapeEqualsERKNSt16initializer_listI8SizeTypeEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T8SizeType">
|
||
<span id="_CPPv3I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEPK1T8SizeType"></span><span id="_CPPv2I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEPK1T8SizeType"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1ab3064d90488eb76a945df538a48ba683"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">shapeEquals</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T8SizeType" title="tensorrt_llm::runtime::ITensor::shapeEquals::T"><span class="n"><span class="pre">T</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">dims</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">count</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4I0ENK12tensorrt_llm7runtime7ITensor11shapeEqualsEbPK1T8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-functions">Public Static Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor6volumeERK5Shape">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor6volumeERK5Shape"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor6volumeERK5Shape"></span><span id="tensorrt_llm::runtime::ITensor::volume__ShapeCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a2afffa26551b43982bf51fa4920d4ade"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">int64_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">volume</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">dims</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor6volumeERK5Shape" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns the volume of the dimensions. Returns -1 if <code class="docutils literal notranslate"><span class="pre">d.nbDims</span> <span class="pre"><</span> <span class="pre">0</span></code>. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape"></span><span id="tensorrt_llm::runtime::ITensor::volumeNonNegative__ShapeCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1aac34c9309ce068d8216a54343348e21d"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">volumeNonNegative</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">shape</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor17volumeNonNegativeERK5Shape" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns the volume of the dimensions. Throws if <code class="docutils literal notranslate"><span class="pre">d.nbDims</span> <span class="pre"><</span> <span class="pre">0</span></code>. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape8SizeType"></span><span id="tensorrt_llm::runtime::ITensor::squeeze__ShapeCR.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a7c9ddd4f8b1eaa7b1a6276c49b2c8672"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">squeeze</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">shape</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">dim</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7squeezeERK5Shape8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Removes the given <em>unit</em> dimension from <code class="docutils literal notranslate"><span class="pre">shape</span></code>. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>shape</strong> – The shape to squeeze. </p></li>
|
||
<li><p><strong>dim</strong> – The dimension that should be removed (“squeezed”). </p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>A new shape without the unit dimension. </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape8SizeType"></span><span id="tensorrt_llm::runtime::ITensor::unsqueeze__ShapeCR.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a637c76757c7e71c448ec24217de99e70"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">unsqueeze</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">shape</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">dim</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9unsqueezeERK5Shape8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Add a <em>unit</em> dimension to <code class="docutils literal notranslate"><span class="pre">shape</span></code> at the specified position. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>shape</strong> – The shape to unsqueeze. </p></li>
|
||
<li><p><strong>dim</strong> – The dimension where unit dimension should be added. </p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>A new shape with the added unit dimension. </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE"></span><span id="tensorrt_llm::runtime::ITensor::slice__SharedPtr.std::s.std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1aa22bf50eff27dbfc64eed003851f4778"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE" title="tensorrt_llm::runtime::ITensor::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">slice</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">tensor</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">offset</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tENSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Creates a sliced view on the underlying <code class="docutils literal notranslate"><span class="pre">tensor</span></code>. The view will have the same data type as <code class="docutils literal notranslate"><span class="pre">tensor</span></code>. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>tensor</strong> – The tensor to view. </p></li>
|
||
<li><p><strong>offset</strong> – The offset of the view w.r.t. dimension 0 of the tensor. </p></li>
|
||
<li><p><strong>size</strong> – The size of the view w.r.t. dimension 0 of the tensor. </p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>A view on the <code class="docutils literal notranslate"><span class="pre">buffer</span></code>. </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE">
|
||
<span id="_CPPv3I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceERR9TConstPtrNSt6size_tENSt6size_tE"></span><span id="_CPPv2I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceERR9TConstPtrNSt6size_tENSt6size_tE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TConstPtr</span></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">enable_if_t</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">is_const_v</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE" title="tensorrt_llm::runtime::PointerElementType"><span class="n"><span class="pre">PointerElementType</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE" title="tensorrt_llm::runtime::ITensor::slice::TConstPtr"><span class="n"><span class="pre">TConstPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="kt"><span class="pre">int</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a201a60f7da459ec35f5d750e8d7053c4"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE" title="tensorrt_llm::runtime::ITensor::UniqueConstPtr"><span class="n"><span class="pre">UniqueConstPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">slice</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE" title="tensorrt_llm::runtime::ITensor::slice::TConstPtr"><span class="n"><span class="pre">TConstPtr</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">tensor</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">offset</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tENSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE"></span><span id="tensorrt_llm::runtime::ITensor::slice__SharedPtr.std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a3bc0148d89f892df6beff0f63ea33e6a"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE" title="tensorrt_llm::runtime::ITensor::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">slice</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">tensor</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">offset</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5sliceE9SharedPtrNSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE">
|
||
<span id="_CPPv3I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceERR9TConstPtrNSt6size_tE"></span><span id="_CPPv2I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceERR9TConstPtrNSt6size_tE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TConstPtr</span></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">enable_if_t</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">is_const_v</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE" title="tensorrt_llm::runtime::PointerElementType"><span class="n"><span class="pre">PointerElementType</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE" title="tensorrt_llm::runtime::ITensor::slice::TConstPtr"><span class="n"><span class="pre">TConstPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="kt"><span class="pre">int</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a01d828a32b3f280c1ee64ce5211da20b"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE" title="tensorrt_llm::runtime::ITensor::UniqueConstPtr"><span class="n"><span class="pre">UniqueConstPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">slice</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE" title="tensorrt_llm::runtime::ITensor::slice::TConstPtr"><span class="n"><span class="pre">TConstPtr</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">tensor</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">offset</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor5sliceE14UniqueConstPtrRR9TConstPtrNSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape"></span><span id="tensorrt_llm::runtime::ITensor::view__IBuffer::SharedPtr.ShapeCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1aeb7a31c92f9ebc17e4648ba4fff7e16e"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE" title="tensorrt_llm::runtime::ITensor::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">view</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBufferE" title="tensorrt_llm::runtime::IBuffer"><span class="n"><span class="pre">IBuffer</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7IBuffer9SharedPtrE" title="tensorrt_llm::runtime::IBuffer::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">buffer</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">dims</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor4viewEN7IBuffer9SharedPtrERK5Shape" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns a view on the underlying <code class="docutils literal notranslate"><span class="pre">buffer</span></code> (or tensor) with the given shape. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>tensor</strong> – The tensor to view. </p></li>
|
||
<li><p><strong>shape</strong> – The shape of the view. </p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>A view on the <code class="docutils literal notranslate"><span class="pre">tensor</span></code>. </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape">
|
||
<span id="_CPPv3I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewERR9TConstPtrRK5Shape"></span><span id="_CPPv2I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewERR9TConstPtrRK5Shape"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TConstPtr</span></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">enable_if_t</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">is_const_v</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime18PointerElementTypeE" title="tensorrt_llm::runtime::PointerElementType"><span class="n"><span class="pre">PointerElementType</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape" title="tensorrt_llm::runtime::ITensor::view::TConstPtr"><span class="n"><span class="pre">TConstPtr</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="kt"><span class="pre">int</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a481831d7c0d45fe462e91b07beef2617"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor14UniqueConstPtrE" title="tensorrt_llm::runtime::ITensor::UniqueConstPtr"><span class="n"><span class="pre">UniqueConstPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">view</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape" title="tensorrt_llm::runtime::ITensor::view::TConstPtr"><span class="n"><span class="pre">TConstPtr</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">tensor</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">dims</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0_NSt11enable_if_tINSt10is_const_vI18PointerElementTypeI9TConstPtrEEEiEEEN12tensorrt_llm7runtime7ITensor4viewE14UniqueConstPtrRR9TConstPtrRK5Shape" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr"></span><span id="tensorrt_llm::runtime::ITensor::view__SharedPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a0d748a6fdb8219af29ba918878bf44b2"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE" title="tensorrt_llm::runtime::ITensor::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">view</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">tensor</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor4viewE9SharedPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Returns a view on the underlying <code class="docutils literal notranslate"><span class="pre">tensor</span></code> which can be independently reshaped. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p><strong>tensor</strong> – The tensor to view. </p>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>A view on the <code class="docutils literal notranslate"><span class="pre">tensor</span></code>. </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE"></span><span id="tensorrt_llm::runtime::ITensor::wrap__voidP.nvinfer1::DataType.ShapeCR.std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1abb208b99fc6a404a13215fe2d43637a4"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE" title="tensorrt_llm::runtime::ITensor::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">wrap</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">data</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">shape</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">capacity</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5ShapeNSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Wraps the given <code class="docutils literal notranslate"><span class="pre">data</span></code> in an <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1ITensor"><span class="std std-ref"><span class="pre">ITensor</span></span></a></code>. The <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1ITensor"><span class="std std-ref"><span class="pre">ITensor</span></span></a></code> will not own the underlying <code class="docutils literal notranslate"><span class="pre">data</span></code> and cannot be reshaped beyond <code class="docutils literal notranslate"><span class="pre">capacity</span></code>. </p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>data</strong> – The data to wrap. </p></li>
|
||
<li><p><strong>type</strong> – The data type of the <code class="docutils literal notranslate"><span class="pre">data</span></code>. </p></li>
|
||
<li><p><strong>shape</strong> – The shape of the tensor. </p></li>
|
||
<li><p><strong>capacity</strong> – The capacity of the buffer. </p></li>
|
||
</ul>
|
||
</dd>
|
||
<dt class="field-even">Returns<span class="colon">:</span></dt>
|
||
<dd class="field-even"><p>An <code class="docutils literal notranslate"><a class="reference internal" href="#classtensorrt__llm_1_1runtime_1_1ITensor"><span class="std std-ref"><span class="pre">ITensor</span></span></a></code>. </p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape"></span><span id="tensorrt_llm::runtime::ITensor::wrap__voidP.nvinfer1::DataType.ShapeCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a5fdde0b2cc5bb0ee07c042964bb48c85"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE" title="tensorrt_llm::runtime::ITensor::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">wrap</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">data</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">DataType</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">type</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">shape</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor4wrapEPvN8nvinfer18DataTypeERK5Shape" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime7ITensor4wrapEP1TRK5ShapeNSt6size_tE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime7ITensor4wrapEP1TRK5ShapeNSt6size_tE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a6cb1dc1fe13779d7d0bed2062df2c0e0"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE" title="tensorrt_llm::runtime::ITensor::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">wrap</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE" title="tensorrt_llm::runtime::ITensor::wrap::T"><span class="n"><span class="pre">T</span></span></a><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">data</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">shape</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">capacity</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5ShapeNSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime7ITensor4wrapEP1TRK5Shape"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime7ITensor4wrapEP1TRK5Shape"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a496e23f8dcc29f792a7e0f70fca11973"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE" title="tensorrt_llm::runtime::ITensor::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">wrap</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape" title="tensorrt_llm::runtime::ITensor::wrap::T"><span class="n"><span class="pre">T</span></span></a><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">data</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">shape</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrP1TRK5Shape" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime7ITensor4wrapERNSt6vectorI1TEERK5Shape"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime7ITensor4wrapERNSt6vectorI1TEERK5Shape"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1ab27a7a0ae81205699d2b2bc618367857"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9UniquePtrE" title="tensorrt_llm::runtime::ITensor::UniquePtr"><span class="n"><span class="pre">UniquePtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">wrap</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape" title="tensorrt_llm::runtime::ITensor::wrap::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">v</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">shape</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime7ITensor4wrapE9UniquePtrRNSt6vectorI1TEERK5Shape" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI8SizeTypeEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI8SizeTypeEE"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI8SizeTypeEE"></span><span id="tensorrt_llm::runtime::ITensor::makeShape__std::initializer_list:SizeType:CR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a7ba94f17049ee1d6048ae69be48ecb67"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">makeShape</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">initializer_list</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">dims</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9makeShapeERKNSt16initializer_listI8SizeTypeEE" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>A convenience function to create a tensor shape with the given dimensions. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor8toStringERK5Shape">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor8toStringERK5Shape"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor8toStringERK5Shape"></span><span id="tensorrt_llm::runtime::ITensor::toString__ShapeCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1af9ba06b8cbf144ea573e6767af85bd43"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">toString</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">dims</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor8toStringERK5Shape" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>A convenience function for converting a tensor shape to a <code class="docutils literal notranslate"><span class="pre">string</span></code>. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape"></span><span id="tensorrt_llm::runtime::ITensor::shapeEquals__ShapeCR.ShapeCR"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1ae39159cc236f70454983d0193570e1c4"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">shapeEquals</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">lhs</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">rhs</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapeRK5Shape" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>A convenience function to compare shapes. </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T8SizeType">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapePK1T8SizeType"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsERK5ShapePK1T8SizeType"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1aac424f6ed20794f38cbd59006f96c57a"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">shapeEquals</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor5ShapeE" title="tensorrt_llm::runtime::ITensor::Shape"><span class="n"><span class="pre">Shape</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">lhs</span></span>, <a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T8SizeType" title="tensorrt_llm::runtime::ITensor::shapeEquals::T"><span class="n"><span class="pre">T</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">dims</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">count</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime7ITensor11shapeEqualsEbRK5ShapePK1T8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>A convenience function to compare shapes. </p>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-protected-functions">Protected Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor7ITensorEv"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor7ITensorEv"></span><span id="tensorrt_llm::runtime::ITensor::ITensor"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a60742a4752e9d9d5a82fff9e24518953"></span><span class="sig-name descname"><span class="n"><span class="pre">ITensor</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">default</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7ITensorEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-protected-static-functions">Protected Static Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime7ITensor8castSizeE6size_t">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime7ITensor8castSizeE6size_t"></span><span id="_CPPv2N12tensorrt_llm7runtime7ITensor8castSizeE6size_t"></span><span id="tensorrt_llm::runtime::ITensor::castSize__s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1ITensor_1a8966794543216594dab695f03d1e6c9e"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor7DimTypeE" title="tensorrt_llm::runtime::ITensor::DimType"><span class="n"><span class="pre">DimType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">castSize</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">newSize</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime7ITensor8castSizeE6size_t" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="ipcutils-h">
|
||
<h2>ipcUtils.h<a class="headerlink" href="#ipcutils-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-functions">Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime13setPeerAccessE11WorldConfigb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime13setPeerAccessE11WorldConfigb"></span><span id="_CPPv2N12tensorrt_llm7runtime13setPeerAccessE11WorldConfigb"></span><span id="tensorrt_llm::runtime::setPeerAccess__WorldConfig.b"></span><span class="target" id="ipcUtils_8h_1a16050a9ed921a12d13a273478086f95c"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setPeerAccess</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="tensorrt_llm::runtime::WorldConfig"><span class="n"><span class="pre">WorldConfig</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">worldConfig</span></span>, <span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">enable</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">true</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime13setPeerAccessE11WorldConfigb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9IpcMemoryE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9IpcMemoryE"></span><span id="_CPPv2N12tensorrt_llm7runtime9IpcMemoryE"></span><span id="tensorrt_llm::runtime::IpcMemory"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IpcMemory"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">IpcMemory</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemoryE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9IpcMemory9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9IpcMemory9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime9IpcMemory9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IpcMemory_1a1c17fa36835ec34cb3cef927e85967eb"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryE11WorldConfigNSt6size_tE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9IpcMemory9IpcMemoryE11WorldConfigNSt6size_tE"></span><span id="_CPPv2N12tensorrt_llm7runtime9IpcMemory9IpcMemoryE11WorldConfigNSt6size_tE"></span><span id="tensorrt_llm::runtime::IpcMemory::IpcMemory__WorldConfig.std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IpcMemory_1ab60128a164106fe08d754357214b5b82"></span><span class="sig-name descname"><span class="n"><span class="pre">IpcMemory</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="tensorrt_llm::runtime::WorldConfig"><span class="n"><span class="pre">WorldConfig</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">worldConfig</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">bufferSize</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory9IpcMemoryE11WorldConfigNSt6size_tE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9IpcMemoryD0Ev">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9IpcMemoryD0Ev"></span><span id="_CPPv2N12tensorrt_llm7runtime9IpcMemoryD0Ev"></span><span id="tensorrt_llm::runtime::IpcMemory::~IpcMemory"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IpcMemory_1a0f068272bfaeadb2e976b44adf47c484"></span><span class="sig-name descname"><span class="n"><span class="pre">~IpcMemory</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemoryD0Ev" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime9IpcMemory17getCommPtrsTensorEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime9IpcMemory17getCommPtrsTensorEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime9IpcMemory17getCommPtrsTensorEv"></span><span id="tensorrt_llm::runtime::IpcMemory::getCommPtrsTensorC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IpcMemory_1a8bcbdce69d5e3de95a0f742e430f822c"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">void</span></span><span class="p"><span class="pre">*</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getCommPtrsTensor</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime9IpcMemory17getCommPtrsTensorEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9IpcMemory10FLAGS_SIZEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9IpcMemory10FLAGS_SIZEE"></span><span id="_CPPv2N12tensorrt_llm7runtime9IpcMemory10FLAGS_SIZEE"></span><span id="tensorrt_llm::runtime::IpcMemory::FLAGS_SIZE__s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IpcMemory_1a4146075f3f6beba4eab4a765506be9bd"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">FLAGS_SIZE</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">kernels</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">MAX_ALL_REDUCE_BLOCKS</span></span><span class="w"> </span><span class="o"><span class="pre">*</span></span><span class="w"> </span><span class="k"><span class="pre">sizeof</span></span><span class="p"><span class="pre">(</span></span><span class="n"><span class="pre">uint32_t</span></span><span class="p"><span class="pre">)</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory10FLAGS_SIZEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-functions">Private Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryEv"></span><span id="_CPPv2N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryEv"></span><span id="tensorrt_llm::runtime::IpcMemory::allocateIpcMemory"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IpcMemory_1a68e4ab83a9194bdd5cf59a1d4ee68a80"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">allocateIpcMemory</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory17allocateIpcMemoryEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9IpcMemory16destroyIpcMemoryEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9IpcMemory16destroyIpcMemoryEv"></span><span id="_CPPv2N12tensorrt_llm7runtime9IpcMemory16destroyIpcMemoryEv"></span><span id="tensorrt_llm::runtime::IpcMemory::destroyIpcMemory"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IpcMemory_1a7b7c035819f96cb37702472ea179c33b"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">destroyIpcMemory</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory16destroyIpcMemoryEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9IpcMemory12mWorldConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9IpcMemory12mWorldConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime9IpcMemory12mWorldConfigE"></span><span id="tensorrt_llm::runtime::IpcMemory::mWorldConfig__WorldConfig"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IpcMemory_1aab66f175e30581b311c654816aa85ea4"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="tensorrt_llm::runtime::WorldConfig"><span class="n"><span class="pre">WorldConfig</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mWorldConfig</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory12mWorldConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9IpcMemory9mCommPtrsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9IpcMemory9mCommPtrsE"></span><span id="_CPPv2N12tensorrt_llm7runtime9IpcMemory9mCommPtrsE"></span><span id="tensorrt_llm::runtime::IpcMemory::mCommPtrs__std::vector:voidP:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IpcMemory_1aa15ac983a61b79976435b4d067daccc2"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">void</span></span><span class="p"><span class="pre">*</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mCommPtrs</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory9mCommPtrsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9IpcMemory11mBufferSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9IpcMemory11mBufferSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime9IpcMemory11mBufferSizeE"></span><span id="tensorrt_llm::runtime::IpcMemory::mBufferSize__std::s"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IpcMemory_1a95b1167806fe77f1f22810ac7477d27d"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mBufferSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory11mBufferSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime9IpcMemory10mBufferPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime9IpcMemory10mBufferPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime9IpcMemory10mBufferPtrE"></span><span id="tensorrt_llm::runtime::IpcMemory::mBufferPtr__voidP"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1IpcMemory_1adf62ec2d27e1382c5414188fd3982f8b"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="sig-name descname"><span class="n"><span class="pre">mBufferPtr</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime9IpcMemory10mBufferPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="memorycounters-h">
|
||
<h2>memoryCounters.h<a class="headerlink" href="#memorycounters-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCountersE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCountersE"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCountersE"></span><span id="tensorrt_llm::runtime::MemoryCounters"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">MemoryCounters</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCountersE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a5aa02d808601c67ba934f8a0a9534d6e"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">SizeType</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">size_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1ab5afaef89516ec27d7934229de37e387"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">DiffType</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">ptrdiff_t</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters14MemoryCountersEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters14MemoryCountersEv"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters14MemoryCountersEv"></span><span id="tensorrt_llm::runtime::MemoryCounters::MemoryCounters"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a97911bd1f11691ed4a652bf78e049e08"></span><span class="sig-name descname"><span class="n"><span class="pre">MemoryCounters</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">default</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters14MemoryCountersEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getGpuEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14MemoryCounters6getGpuEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14MemoryCounters6getGpuEv"></span><span id="tensorrt_llm::runtime::MemoryCounters::getGpuC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a09119207f2dfca61e4e7bd5a66c36654"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE" title="tensorrt_llm::runtime::MemoryCounters::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getGpu</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getGpuEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getCpuEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14MemoryCounters6getCpuEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14MemoryCounters6getCpuEv"></span><span id="tensorrt_llm::runtime::MemoryCounters::getCpuC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1af643b8967c9f99d8efd647d7b3efe281"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE" title="tensorrt_llm::runtime::MemoryCounters::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getCpu</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters6getCpuEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14MemoryCounters9getPinnedEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14MemoryCounters9getPinnedEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14MemoryCounters9getPinnedEv"></span><span id="tensorrt_llm::runtime::MemoryCounters::getPinnedC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1ae37c0265530ae4fac20d31da5712d3c0"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE" title="tensorrt_llm::runtime::MemoryCounters::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getPinned</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters9getPinnedEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getGpuDiffEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14MemoryCounters10getGpuDiffEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14MemoryCounters10getGpuDiffEv"></span><span id="tensorrt_llm::runtime::MemoryCounters::getGpuDiffC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a399a7926f7819096b4f29fa04b3290de"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE" title="tensorrt_llm::runtime::MemoryCounters::DiffType"><span class="n"><span class="pre">DiffType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getGpuDiff</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getGpuDiffEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getCpuDiffEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14MemoryCounters10getCpuDiffEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14MemoryCounters10getCpuDiffEv"></span><span id="tensorrt_llm::runtime::MemoryCounters::getCpuDiffC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a62f4e6d3f0dd20c4ec6b35b4b6df0d47"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE" title="tensorrt_llm::runtime::MemoryCounters::DiffType"><span class="n"><span class="pre">DiffType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getCpuDiff</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters10getCpuDiffEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedDiffEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14MemoryCounters13getPinnedDiffEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14MemoryCounters13getPinnedDiffEv"></span><span id="tensorrt_llm::runtime::MemoryCounters::getPinnedDiffC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a4571ac85d01e0844b946d57615523ad0"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE" title="tensorrt_llm::runtime::MemoryCounters::DiffType"><span class="n"><span class="pre">DiffType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getPinnedDiff</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters13getPinnedDiffEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv8SizeType">
|
||
<span id="_CPPv3I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateE8SizeType"></span><span id="_CPPv2I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateE8SizeType"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a891aab52104e74b95138f4bf20c111c2"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">allocate</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE" title="tensorrt_llm::runtime::MemoryCounters::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters8allocateEv8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType8SizeType"></span><span id="tensorrt_llm::runtime::MemoryCounters::allocate__MemoryType.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a0b437c35c4af66d2f2b2379a40c136d6"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">allocate</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">memoryType</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE" title="tensorrt_llm::runtime::MemoryCounters::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8allocateE10MemoryType8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv8SizeType">
|
||
<span id="_CPPv3I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateE8SizeType"></span><span id="_CPPv2I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateE8SizeType"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a6301480be8d33d2a3e7dbd54119467c9"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">deallocate</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE" title="tensorrt_llm::runtime::MemoryCounters::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4I_10MemoryTypeEN12tensorrt_llm7runtime14MemoryCounters10deallocateEv8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType8SizeType"></span><span id="tensorrt_llm::runtime::MemoryCounters::deallocate__MemoryType.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a4cbe26fb0d89352c1de2cb6f63220aa2"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">deallocate</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime10MemoryTypeE" title="tensorrt_llm::runtime::MemoryType"><span class="n"><span class="pre">MemoryType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">memoryType</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE" title="tensorrt_llm::runtime::MemoryCounters::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">size</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters10deallocateE10MemoryType8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime14MemoryCounters8toStringEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime14MemoryCounters8toStringEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime14MemoryCounters8toStringEv"></span><span id="tensorrt_llm::runtime::MemoryCounters::toStringC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1ad6981e0fc09bbeefdf4b2854fd03d77a"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">toString</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime14MemoryCounters8toStringEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-functions">Public Static Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters11getInstanceEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters11getInstanceEv"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters11getInstanceEv"></span><span id="tensorrt_llm::runtime::MemoryCounters::getInstance"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a5fd849b9f6dd583910a3aa4acb8ea391"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCountersE" title="tensorrt_llm::runtime::MemoryCounters"><span class="n"><span class="pre">MemoryCounters</span></span></a><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="sig-name descname"><span class="n"><span class="pre">getInstance</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters11getInstanceEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8SizeTypei">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8SizeTypei"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8SizeTypei"></span><span id="tensorrt_llm::runtime::MemoryCounters::bytesToString__SizeType.i"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1ad3e1b845f41a4245556557b1393881f9"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">bytesToString</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE" title="tensorrt_llm::runtime::MemoryCounters::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">bytes</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">precision</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">2</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8SizeTypei" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei"></span><span id="tensorrt_llm::runtime::MemoryCounters::bytesToString__DiffType.i"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1ae644945f3b01297e95a0f1724b5b4d8a"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">string</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">bytesToString</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE" title="tensorrt_llm::runtime::MemoryCounters::DiffType"><span class="n"><span class="pre">DiffType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">bytes</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">precision</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">2</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters13bytesToStringE8DiffTypei" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mGpuE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters4mGpuE"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters4mGpuE"></span><span id="tensorrt_llm::runtime::MemoryCounters::mGpu__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a641ecc1e58aa222f4a7e269aa589e70f"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE" title="tensorrt_llm::runtime::MemoryCounters::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mGpu</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mGpuE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mCpuE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters4mCpuE"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters4mCpuE"></span><span id="tensorrt_llm::runtime::MemoryCounters::mCpu__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a27771c9783292c51de1b8a59aca33d71"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE" title="tensorrt_llm::runtime::MemoryCounters::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mCpu</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters4mCpuE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters7mPinnedE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters7mPinnedE"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters7mPinnedE"></span><span id="tensorrt_llm::runtime::MemoryCounters::mPinned__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a7eaaa821b0f7cbf8f1a2264e5f1b1c25"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8SizeTypeE" title="tensorrt_llm::runtime::MemoryCounters::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mPinned</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters7mPinnedE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mGpuDiffE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters8mGpuDiffE"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters8mGpuDiffE"></span><span id="tensorrt_llm::runtime::MemoryCounters::mGpuDiff__DiffType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a091075678e2a77da992d619ccc27ee69"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE" title="tensorrt_llm::runtime::MemoryCounters::DiffType"><span class="n"><span class="pre">DiffType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mGpuDiff</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mGpuDiffE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mCpuDiffE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters8mCpuDiffE"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters8mCpuDiffE"></span><span id="tensorrt_llm::runtime::MemoryCounters::mCpuDiff__DiffType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a55b97586df47d83ece390da5b9da7ace"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE" title="tensorrt_llm::runtime::MemoryCounters::DiffType"><span class="n"><span class="pre">DiffType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mCpuDiff</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8mCpuDiffE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedDiffE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters11mPinnedDiffE"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters11mPinnedDiffE"></span><span id="tensorrt_llm::runtime::MemoryCounters::mPinnedDiff__DiffType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a3ac02c1fc74dd309e7680be2c27ecbf0"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters8DiffTypeE" title="tensorrt_llm::runtime::MemoryCounters::DiffType"><span class="n"><span class="pre">DiffType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mPinnedDiff</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters11mPinnedDiffE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-static-attributes">Private Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14MemoryCounters9mInstanceE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14MemoryCounters9mInstanceE"></span><span id="_CPPv2N12tensorrt_llm7runtime14MemoryCounters9mInstanceE"></span><span id="tensorrt_llm::runtime::MemoryCounters::mInstance__MemoryCounters"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1MemoryCounters_1a6de4abe7564f08c88fedabcff29ffeca"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">thread_local</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCountersE" title="tensorrt_llm::runtime::MemoryCounters"><span class="n"><span class="pre">MemoryCounters</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mInstance</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14MemoryCounters9mInstanceE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="prompttuningparams-h">
|
||
<h2>promptTuningParams.h<a class="headerlink" href="#prompttuningparams-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TTensor</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericPromptTuningParams"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GenericPromptTuningParams</span></span></span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericPromptTuningParams_1a7f0226e537f0c4a164c298adf9731e67"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE" title="tensorrt_llm::runtime::GenericPromptTuningParams::TTensor"><span class="n"><span class="pre">TTensor</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams8SizeTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime25GenericPromptTuningParams8SizeTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime25GenericPromptTuningParams8SizeTypeE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericPromptTuningParams_1a1dc6277cb0a7c8768f9b3e7609189c8c"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">SizeType</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv412tensorrt_llm" title="tensorrt_llm"><span class="n"><span class="pre">tensorrt_llm</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimeE" title="tensorrt_llm::runtime"><span class="n"><span class="pre">runtime</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams8SizeTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr"></span><span id="tensorrt_llm::runtime::GenericPromptTuningParams::GenericPromptTuningParams__TensorPtr.TensorPtr.TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericPromptTuningParams_1a08b54a1a315a75cada66405e31709668"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">GenericPromptTuningParams</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::GenericPromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">embeddingTable</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::GenericPromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="p"><span class="pre">(</span></span><span class="p"><span class="pre">)</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::GenericPromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">tasks</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::GenericPromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="p"><span class="pre">(</span></span><span class="p"><span class="pre">)</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::GenericPromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">vocabSize</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::GenericPromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="p"><span class="pre">(</span></span><span class="p"><span class="pre">)</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams25GenericPromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams14embeddingTableE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime25GenericPromptTuningParams14embeddingTableE"></span><span id="_CPPv2N12tensorrt_llm7runtime25GenericPromptTuningParams14embeddingTableE"></span><span id="tensorrt_llm::runtime::GenericPromptTuningParams::embeddingTable__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericPromptTuningParams_1a718fcc98779017166cbe0a748c081414"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::GenericPromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">embeddingTable</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams14embeddingTableE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams5tasksE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime25GenericPromptTuningParams5tasksE"></span><span id="_CPPv2N12tensorrt_llm7runtime25GenericPromptTuningParams5tasksE"></span><span id="tensorrt_llm::runtime::GenericPromptTuningParams::tasks__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericPromptTuningParams_1aea7aafec3a272782a1a467eb159af6e1"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::GenericPromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tasks</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams5tasksE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9vocabSizeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime25GenericPromptTuningParams9vocabSizeE"></span><span id="_CPPv2N12tensorrt_llm7runtime25GenericPromptTuningParams9vocabSizeE"></span><span id="tensorrt_llm::runtime::GenericPromptTuningParams::vocabSize__TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericPromptTuningParams_1acb732cd787508ea7013cf1e9002590ea"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::GenericPromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">vocabSize</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams9vocabSizeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams19promptTuningEnabledE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime25GenericPromptTuningParams19promptTuningEnabledE"></span><span id="_CPPv2N12tensorrt_llm7runtime25GenericPromptTuningParams19promptTuningEnabledE"></span><span id="tensorrt_llm::runtime::GenericPromptTuningParams::promptTuningEnabled__std::vector:b:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1GenericPromptTuningParams_1a4f994aa4122125396dee70846aec1318"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">bool</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">promptTuningEnabled</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams19promptTuningEnabledE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime18PromptTuningParamsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime18PromptTuningParamsE"></span><span id="_CPPv2N12tensorrt_llm7runtime18PromptTuningParamsE"></span><span id="tensorrt_llm::runtime::PromptTuningParams"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1PromptTuningParams"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">PromptTuningParams</span></span></span><span class="w"> </span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="k"><span class="pre">public</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv412tensorrt_llm" title="tensorrt_llm"><span class="n"><span class="pre">tensorrt_llm</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtimeE" title="tensorrt_llm::runtime"><span class="n"><span class="pre">runtime</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE" title="tensorrt_llm::runtime::GenericPromptTuningParams"><span class="n"><span class="pre">GenericPromptTuningParams</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParamsE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-types">Public Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE"></span><span id="_CPPv2N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1PromptTuningParams_1acf57960de488b9fcc3021a34690f003a"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TensorPtr</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensorE" title="tensorrt_llm::runtime::ITensor"><span class="n"><span class="pre">ITensor</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime7ITensor9SharedPtrE" title="tensorrt_llm::runtime::ITensor::SharedPtr"><span class="n"><span class="pre">SharedPtr</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime18PromptTuningParams8SizeTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime18PromptTuningParams8SizeTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime18PromptTuningParams8SizeTypeE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1PromptTuningParams_1a1d6aab181a91c9a97b57429f08b53b55"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">SizeType</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime25GenericPromptTuningParamsE" title="tensorrt_llm::runtime::GenericPromptTuningParams"><span class="n"><span class="pre">GenericPromptTuningParams</span></span></a><span class="p"><span class="pre">::</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime25GenericPromptTuningParams8SizeTypeE" title="tensorrt_llm::runtime::GenericPromptTuningParams::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams8SizeTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr"></span><span id="_CPPv2N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr"></span><span id="tensorrt_llm::runtime::PromptTuningParams::PromptTuningParams__TensorPtr.TensorPtr.TensorPtr"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1PromptTuningParams_1a6439bfa322d7dc1f589cd3877640a952"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">PromptTuningParams</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::PromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">embeddingTable</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">nullptr</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::PromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">tasks</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">nullptr</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::PromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">vocabSize</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="k"><span class="pre">nullptr</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams18PromptTuningParamsE9TensorPtr9TensorPtr9TensorPtr" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK8SizeTypeK8SizeTypeRKNSt6vectorI8SizeTypeEERKNSt6vectorI8SizeTypeEERK13BufferManagerb">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK8SizeTypeK8SizeTypeRKNSt6vectorI8SizeTypeEERKNSt6vectorI8SizeTypeEERK13BufferManagerb"></span><span id="_CPPv2N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK8SizeTypeK8SizeTypeRKNSt6vectorI8SizeTypeEERKNSt6vectorI8SizeTypeEERK13BufferManagerb"></span><span id="tensorrt_llm::runtime::PromptTuningParams::fillTasksTensor__TensorPtr.SizeTypeC.SizeTypeC.std::vector:SizeType:CR.std::vector:SizeType:CR.BufferManagerCR.b"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1PromptTuningParams_1a95c1342b784bdf139c4d0f0502851735"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">fillTasksTensor</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams9TensorPtrE" title="tensorrt_llm::runtime::PromptTuningParams::TensorPtr"><span class="n"><span class="pre">TensorPtr</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">tasksHost</span></span>, <span class="k"><span class="pre">const</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams8SizeTypeE" title="tensorrt_llm::runtime::PromptTuningParams::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">batchSize</span></span>, <span class="k"><span class="pre">const</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams8SizeTypeE" title="tensorrt_llm::runtime::PromptTuningParams::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">numContextRequests</span></span>, <span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams8SizeTypeE" title="tensorrt_llm::runtime::PromptTuningParams::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">reqBeamWidths</span></span>, <span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams8SizeTypeE" title="tensorrt_llm::runtime::PromptTuningParams::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">reqPromptLengths</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime13BufferManagerE" title="tensorrt_llm::runtime::BufferManager"><span class="n"><span class="pre">BufferManager</span></span></a><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">manager</span></span>, <span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">packedInput</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime18PromptTuningParams15fillTasksTensorE9TensorPtrK8SizeTypeK8SizeTypeRKNSt6vectorI8SizeTypeEERKNSt6vectorI8SizeTypeEERK13BufferManagerb" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="samplingconfig-h">
|
||
<h2>samplingConfig.h<a class="headerlink" href="#samplingconfig-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfigE"></span><span id="tensorrt_llm::runtime::SamplingConfig"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">SamplingConfig</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE8SizeType"></span><span id="tensorrt_llm::runtime::SamplingConfig::SamplingConfig__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1a1b84a281c4413d5a4df922e9074d85ac"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">SamplingConfig</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">beamWidth</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">1</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig14SamplingConfigE8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-members">Public Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig9beamWidthE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig9beamWidthE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig9beamWidthE"></span><span id="tensorrt_llm::runtime::SamplingConfig::beamWidth__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1a871887c0857fa88f45fadcd659c20824"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">beamWidth</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9beamWidthE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig11temperatureE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig11temperatureE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig11temperatureE"></span><span id="tensorrt_llm::runtime::SamplingConfig::temperature__OptVec:FloatType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1aa0234e25caafb8f7e2540e635354f1a7"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE" title="tensorrt_llm::runtime::SamplingConfig::FloatType"><span class="n"><span class="pre">FloatType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">temperature</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig11temperatureE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig9minLengthE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig9minLengthE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig9minLengthE"></span><span id="tensorrt_llm::runtime::SamplingConfig::minLength__OptVec:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1aacc380bc9c6ff46fd2edd112b1eac9c0"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">minLength</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9minLengthE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig17repetitionPenaltyE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig17repetitionPenaltyE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig17repetitionPenaltyE"></span><span id="tensorrt_llm::runtime::SamplingConfig::repetitionPenalty__OptVec:FloatType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1ab267d53af1ff989a2cda73069dfd42fa"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE" title="tensorrt_llm::runtime::SamplingConfig::FloatType"><span class="n"><span class="pre">FloatType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">repetitionPenalty</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig17repetitionPenaltyE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig15presencePenaltyE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig15presencePenaltyE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig15presencePenaltyE"></span><span id="tensorrt_llm::runtime::SamplingConfig::presencePenalty__OptVec:FloatType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1af40f62527a6a93da70def3daafdc8001"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE" title="tensorrt_llm::runtime::SamplingConfig::FloatType"><span class="n"><span class="pre">FloatType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">presencePenalty</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig15presencePenaltyE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topKE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig4topKE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig4topKE"></span><span id="tensorrt_llm::runtime::SamplingConfig::topK__OptVec:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1ab1588865e1c6e97bfebfe12b7ee34e37"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">topK</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topKE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topPE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig4topPE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig4topPE"></span><span id="tensorrt_llm::runtime::SamplingConfig::topP__OptVec:FloatType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1a6d960ae9fb60fa44c616cf4b16a6977d"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE" title="tensorrt_llm::runtime::SamplingConfig::FloatType"><span class="n"><span class="pre">FloatType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">topP</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig4topPE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig10randomSeedE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig10randomSeedE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig10randomSeedE"></span><span id="tensorrt_llm::runtime::SamplingConfig::randomSeed__OptVec:unsigned-l-l:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1a6468682988b1992a5be330aaadc9641e"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><span class="kt"><span class="pre">unsigned</span></span><span class="w"> </span><span class="kt"><span class="pre">long</span></span><span class="w"> </span><span class="kt"><span class="pre">long</span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">randomSeed</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig10randomSeedE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig9topPDecayE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig9topPDecayE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig9topPDecayE"></span><span id="tensorrt_llm::runtime::SamplingConfig::topPDecay__OptVec:FloatType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1ad25e0aec9100bf05d100885677dfaa03"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE" title="tensorrt_llm::runtime::SamplingConfig::FloatType"><span class="n"><span class="pre">FloatType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">topPDecay</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9topPDecayE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig7topPMinE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig7topPMinE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig7topPMinE"></span><span id="tensorrt_llm::runtime::SamplingConfig::topPMin__OptVec:FloatType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1a2f772d5c0be4d9fe80fdf0e142a731d5"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE" title="tensorrt_llm::runtime::SamplingConfig::FloatType"><span class="n"><span class="pre">FloatType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">topPMin</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig7topPMinE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig12topPResetIdsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig12topPResetIdsE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig12topPResetIdsE"></span><span id="tensorrt_llm::runtime::SamplingConfig::topPResetIds__OptVec:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1ae2a3d686956933a6938925309496a33e"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">topPResetIds</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig12topPResetIdsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig23beamSearchDiversityRateE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig23beamSearchDiversityRateE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig23beamSearchDiversityRateE"></span><span id="tensorrt_llm::runtime::SamplingConfig::beamSearchDiversityRate__OptVec:FloatType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1a58a44a42e3086649b6b510222b007ac6"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE" title="tensorrt_llm::runtime::SamplingConfig::FloatType"><span class="n"><span class="pre">FloatType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">beamSearchDiversityRate</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig23beamSearchDiversityRateE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig13lengthPenaltyE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig13lengthPenaltyE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig13lengthPenaltyE"></span><span id="tensorrt_llm::runtime::SamplingConfig::lengthPenalty__OptVec:FloatType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1a393378cbfb39e5a147b88a8601050947"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE" title="tensorrt_llm::runtime::SamplingConfig::FloatType"><span class="n"><span class="pre">FloatType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">lengthPenalty</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig13lengthPenaltyE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig24draftAcceptanceThresholdE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig24draftAcceptanceThresholdE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig24draftAcceptanceThresholdE"></span><span id="tensorrt_llm::runtime::SamplingConfig::draftAcceptanceThreshold__OptVec:FloatType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1a914d673110a9a51924ec03567f2b6fb5"></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec"><span class="n"><span class="pre">OptVec</span></span></a><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE" title="tensorrt_llm::runtime::SamplingConfig::FloatType"><span class="n"><span class="pre">FloatType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">draftAcceptanceThreshold</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig24draftAcceptanceThresholdE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-types">Private Types</p>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE"></span><span id="_CPPv2N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1a78311bb676349c17d54fee63f3d54396"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">FloatType</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="kt"><span class="pre">float</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime14SamplingConfig9FloatTypeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp" id="_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE">
|
||
<span id="_CPPv3I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE"></span><span id="_CPPv2I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE"></span><span class="k"><span class="pre">template</span></span><span class="p"><span class="pre"><</span></span><span class="k"><span class="pre">typename</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">T</span></span></span><span class="p"><span class="pre">></span></span><br /><span class="target" id="classtensorrt__llm_1_1runtime_1_1SamplingConfig_1a82ed7012baf2949351e80937329b530a"></span><span class="k"><span class="pre">using</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">OptVec</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="tensorrt_llm::runtime::SamplingConfig::OptVec::T"><span class="n"><span class="pre">T</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><a class="headerlink" href="#_CPPv4I0EN12tensorrt_llm7runtime14SamplingConfig6OptVecE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="tllmlogger-h">
|
||
<h2>tllmLogger.h<a class="headerlink" href="#tllmlogger-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10TllmLoggerE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10TllmLoggerE"></span><span id="_CPPv2N12tensorrt_llm7runtime10TllmLoggerE"></span><span id="tensorrt_llm::runtime::TllmLogger"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1TllmLogger"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">TllmLogger</span></span></span><span class="w"> </span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="k"><span class="pre">public</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">ILogger</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10TllmLoggerE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE"></span><span id="_CPPv2N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE"></span><span id="tensorrt_llm::runtime::TllmLogger::log__Severity.nvinfer1::AsciiCharCP"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1TllmLogger_1a052c775ee14bc0d741d26d28c5b3f311"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">log</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">Severity</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">severity</span></span>, <a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">AsciiChar</span></span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n sig-param"><span class="pre">msg</span></span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><span class="w"> </span><span class="k"><span class="pre">override</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10TllmLogger3logE8SeverityPKN8nvinfer19AsciiCharE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10TllmLogger8getLevelEv">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10TllmLogger8getLevelEv"></span><span id="_CPPv2N12tensorrt_llm7runtime10TllmLogger8getLevelEv"></span><span id="tensorrt_llm::runtime::TllmLogger::getLevel"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1TllmLogger_1ae6b565ac5ee12cfcd305c0f2c0bd4b1e"></span><span class="n"><span class="pre">Severity</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getLevel</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10TllmLogger8getLevelEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity"></span><span id="_CPPv2N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity"></span><span id="tensorrt_llm::runtime::TllmLogger::setLevel__Severity"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1TllmLogger_1a02ca7ebe0eec266f8b6ab4b66e9f0275"></span><span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">setLevel</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">Severity</span></span><span class="w"> </span><span class="n sig-param"><span class="pre">level</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime10TllmLogger8setLevelE8Severity" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="worldconfig-h">
|
||
<h2>worldConfig.h<a class="headerlink" href="#worldconfig-h" title="Link to this heading"></a></h2>
|
||
<dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">tensorrt_llm</span></span></span><br /></dt>
|
||
<dd><dl class="cpp type">
|
||
<dt class="sig sig-object cpp">
|
||
<span class="target" id="namespacetensorrt__llm_1_1runtime"></span><span class="k"><span class="pre">namespace</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">runtime</span></span></span><br /></dt>
|
||
<dd><dl class="cpp class">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11WorldConfigE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11WorldConfigE"></span><span id="_CPPv2N12tensorrt_llm7runtime11WorldConfigE"></span><span id="tensorrt_llm::runtime::WorldConfig"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig"></span><span class="k"><span class="pre">class</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">WorldConfig</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="Link to this definition"></a><br /></dt>
|
||
<dd><div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-functions">Public Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE8SizeType8SizeType8SizeType8SizeTypeNSt6vectorI8SizeTypeEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11WorldConfig11WorldConfigE8SizeType8SizeType8SizeType8SizeTypeNSt6vectorI8SizeTypeEE"></span><span id="_CPPv2N12tensorrt_llm7runtime11WorldConfig11WorldConfigE8SizeType8SizeType8SizeType8SizeTypeNSt6vectorI8SizeTypeEE"></span><span id="tensorrt_llm::runtime::WorldConfig::WorldConfig__SizeType.SizeType.SizeType.SizeType.std::vector:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a9ea2724695c1126cdce24ce8046ae540"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">explicit</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">WorldConfig</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">tensorParallelism</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">1</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">pipelineParallelism</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">1</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">rank</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">0</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">gpusPerNode</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE" title="tensorrt_llm::runtime::WorldConfig::kDefaultGpusPerNode"><span class="n"><span class="pre">kDefaultGpusPerNode</span></span></a>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="n sig-param"><span class="pre">deviceIds</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="p"><span class="pre">{</span></span><span class="p"><span class="pre">}</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig11WorldConfigE8SizeType8SizeType8SizeType8SizeTypeNSt6vectorI8SizeTypeEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getSizeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig7getSizeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig7getSizeEv"></span><span id="tensorrt_llm::runtime::WorldConfig::getSizeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1ab015227c42d7122c0e33f22e03ac8228"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getSize</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getSizeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig20getTensorParallelismEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig20getTensorParallelismEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig20getTensorParallelismEv"></span><span id="tensorrt_llm::runtime::WorldConfig::getTensorParallelismCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a389ba0bc53cd7fe0259bdb2124ee156f"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getTensorParallelism</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig20getTensorParallelismEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig16isTensorParallelEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig16isTensorParallelEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig16isTensorParallelEv"></span><span id="tensorrt_llm::runtime::WorldConfig::isTensorParallelCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1af3627cbcb19d1519338fea2e43335633"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">isTensorParallel</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig16isTensorParallelEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getPipelineParallelismEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig22getPipelineParallelismEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig22getPipelineParallelismEv"></span><span id="tensorrt_llm::runtime::WorldConfig::getPipelineParallelismCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1ab90953f5e50d6fdef2d3c76ad8295f98"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getPipelineParallelism</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig22getPipelineParallelismEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig18isPipelineParallelEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig18isPipelineParallelEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig18isPipelineParallelEv"></span><span id="tensorrt_llm::runtime::WorldConfig::isPipelineParallelCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a37ec8744e7dc7ff6211c319a33ecc628"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">isPipelineParallel</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig18isPipelineParallelEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getRankEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig7getRankEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig7getRankEv"></span><span id="tensorrt_llm::runtime::WorldConfig::getRankCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1ab99195015c992ba7a735c7880cc62bb6"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getRank</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig7getRankEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig14getGpusPerNodeEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig14getGpusPerNodeEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig14getGpusPerNodeEv"></span><span id="tensorrt_llm::runtime::WorldConfig::getGpusPerNodeCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a32f320679d97d1a278e84bb21af89494"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getGpusPerNode</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig14getGpusPerNodeEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig9getDeviceEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig9getDeviceEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig9getDeviceEv"></span><span id="tensorrt_llm::runtime::WorldConfig::getDeviceC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a19ad2c39ad0a62faf879966e3ee57974"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getDevice</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig9getDeviceEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getPipelineParallelRankEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig23getPipelineParallelRankEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig23getPipelineParallelRankEv"></span><span id="tensorrt_llm::runtime::WorldConfig::getPipelineParallelRankCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a619d3cbd60a9cad3d0232844e8693739"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getPipelineParallelRank</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig23getPipelineParallelRankEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getTensorParallelRankEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig21getTensorParallelRankEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig21getTensorParallelRankEv"></span><span id="tensorrt_llm::runtime::WorldConfig::getTensorParallelRankCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1ab00da06440a9b4f3305d9811dcd7b61b"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getTensorParallelRank</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig21getTensorParallelRankEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig27isFirstPipelineParallelRankEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig27isFirstPipelineParallelRankEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig27isFirstPipelineParallelRankEv"></span><span id="tensorrt_llm::runtime::WorldConfig::isFirstPipelineParallelRankCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a6a5a2512cce31560ae828d7fd1968c22"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">isFirstPipelineParallelRank</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig27isFirstPipelineParallelRankEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isLastPipelineParallelRankEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig26isLastPipelineParallelRankEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig26isLastPipelineParallelRankEv"></span><span id="tensorrt_llm::runtime::WorldConfig::isLastPipelineParallelRankCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a7e9cc05c32f9a1edf82d4017e34a3bef"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">isLastPipelineParallelRank</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig26isLastPipelineParallelRankEv" title="Link to this definition"></a><br /></dt>
|
||
<dd><p>Is my rank the last rank in its pipeline? </p>
|
||
</dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getLastRankEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig11getLastRankEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig11getLastRankEv"></span><span id="tensorrt_llm::runtime::WorldConfig::getLastRankCCE"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a64bb69b0f709d7081da9201c9990457c"></span><span class="k"><span class="pre">inline</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getLastRank</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><span class="w"> </span><span class="k"><span class="pre">noexcept</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig11getLastRankEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4NK12tensorrt_llm7runtime11WorldConfig24getPipelineParallelGroupEv">
|
||
<span id="_CPPv3NK12tensorrt_llm7runtime11WorldConfig24getPipelineParallelGroupEv"></span><span id="_CPPv2NK12tensorrt_llm7runtime11WorldConfig24getPipelineParallelGroupEv"></span><span id="tensorrt_llm::runtime::WorldConfig::getPipelineParallelGroupC"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a79368880ccca35154c16cbf409c97430"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">getPipelineParallelGroup</span></span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><span class="w"> </span><span class="k"><span class="pre">const</span></span><a class="headerlink" href="#_CPPv4NK12tensorrt_llm7runtime11WorldConfig24getPipelineParallelGroupEv" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-functions">Public Static Functions</p>
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11WorldConfig11validConfigERN8nvinfer17ILoggerE8SizeType8SizeType">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11WorldConfig11validConfigERN8nvinfer17ILoggerE8SizeType8SizeType"></span><span id="_CPPv2N12tensorrt_llm7runtime11WorldConfig11validConfigERN8nvinfer17ILoggerE8SizeType8SizeType"></span><span id="tensorrt_llm::runtime::WorldConfig::validConfig__nvinfer1::ILoggerR.SizeType.SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1ab34b3cafb821617e539a8d736c09e3f5"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="kt"><span class="pre">bool</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">validConfig</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">ILogger</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">logger</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">tensorParallelism</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">pipelineParallelism</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig11validConfigERN8nvinfer17ILoggerE8SizeType8SizeType" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiERN8nvinfer17ILoggerE8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEENSt8optionalINSt6vectorI8SizeTypeEEEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11WorldConfig3mpiERN8nvinfer17ILoggerE8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEENSt8optionalINSt6vectorI8SizeTypeEEEE"></span><span id="_CPPv2N12tensorrt_llm7runtime11WorldConfig3mpiERN8nvinfer17ILoggerE8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEENSt8optionalINSt6vectorI8SizeTypeEEEE"></span><span id="tensorrt_llm::runtime::WorldConfig::mpi__nvinfer1::ILoggerR.SizeType.std::optional:SizeType:.std::optional:SizeType:.std::optional:std::vector:SizeType::"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1acd4fe6137f197f7056ba34302277870b"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="tensorrt_llm::runtime::WorldConfig"><span class="n"><span class="pre">WorldConfig</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mpi</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv48nvinfer1" title="nvinfer1"><span class="n"><span class="pre">nvinfer1</span></span></a><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">ILogger</span></span><span class="w"> </span><span class="p"><span class="pre">&</span></span><span class="n sig-param"><span class="pre">logger</span></span>, <a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">gpusPerNode</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE" title="tensorrt_llm::runtime::WorldConfig::kDefaultGpusPerNode"><span class="n"><span class="pre">kDefaultGpusPerNode</span></span></a>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="n sig-param"><span class="pre">tensorParallelism</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">nullopt</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="n sig-param"><span class="pre">pipelineParallelism</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">nullopt</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="n sig-param"><span class="pre">userSpecifiedDeviceIds</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">nullopt</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiERN8nvinfer17ILoggerE8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEENSt8optionalINSt6vectorI8SizeTypeEEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp function">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEENSt8optionalINSt6vectorI8SizeTypeEEEE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11WorldConfig3mpiE8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEENSt8optionalINSt6vectorI8SizeTypeEEEE"></span><span id="_CPPv2N12tensorrt_llm7runtime11WorldConfig3mpiE8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEENSt8optionalINSt6vectorI8SizeTypeEEEE"></span><span id="tensorrt_llm::runtime::WorldConfig::mpi__SizeType.std::optional:SizeType:.std::optional:SizeType:.std::optional:std::vector:SizeType::"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a15a7e43957af4d0bc28be753ac030b2b"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfigE" title="tensorrt_llm::runtime::WorldConfig"><span class="n"><span class="pre">WorldConfig</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mpi</span></span></span><span class="sig-paren">(</span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="n sig-param"><span class="pre">gpusPerNode</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE" title="tensorrt_llm::runtime::WorldConfig::kDefaultGpusPerNode"><span class="n"><span class="pre">kDefaultGpusPerNode</span></span></a>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="n sig-param"><span class="pre">tensorParallelism</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">nullopt</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="n sig-param"><span class="pre">pipelineParallelism</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">nullopt</span></span>, <span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">optional</span></span><span class="p"><span class="pre"><</span></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="n sig-param"><span class="pre">userSpecifiedDeviceIds</span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">nullopt</span></span><span class="sig-paren">)</span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig3mpiE8SizeTypeNSt8optionalI8SizeTypeEENSt8optionalI8SizeTypeEENSt8optionalINSt6vectorI8SizeTypeEEEE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-public-static-attributes">Public Static Attributes</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE"></span><span id="_CPPv2N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE"></span><span id="tensorrt_llm::runtime::WorldConfig::kDefaultGpusPerNode__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a2d68f68654533c7b0b9be92dae183082"></span><span class="k"><span class="pre">static</span></span><span class="w"> </span><span class="k"><span class="pre">constexpr</span></span><span class="w"> </span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">kDefaultGpusPerNode</span></span></span><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="m"><span class="pre">8</span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig19kDefaultGpusPerNodeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
<div class="breathe-sectiondef docutils container">
|
||
<p class="breathe-sectiondef-title rubric" id="breathe-section-title-private-members">Private Members</p>
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11WorldConfig18mTensorParallelismE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11WorldConfig18mTensorParallelismE"></span><span id="_CPPv2N12tensorrt_llm7runtime11WorldConfig18mTensorParallelismE"></span><span id="tensorrt_llm::runtime::WorldConfig::mTensorParallelism__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a60d3f95841a56216582ff4d1749841db"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mTensorParallelism</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig18mTensorParallelismE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11WorldConfig20mPipelineParallelismE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11WorldConfig20mPipelineParallelismE"></span><span id="_CPPv2N12tensorrt_llm7runtime11WorldConfig20mPipelineParallelismE"></span><span id="tensorrt_llm::runtime::WorldConfig::mPipelineParallelism__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a455c07380f4ab9f5d299de40011d03be"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mPipelineParallelism</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig20mPipelineParallelismE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11WorldConfig5mRankE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11WorldConfig5mRankE"></span><span id="_CPPv2N12tensorrt_llm7runtime11WorldConfig5mRankE"></span><span id="tensorrt_llm::runtime::WorldConfig::mRank__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a834b8b05fadab2839ad94c0389385330"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mRank</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig5mRankE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11WorldConfig12mGpusPerNodeE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11WorldConfig12mGpusPerNodeE"></span><span id="_CPPv2N12tensorrt_llm7runtime11WorldConfig12mGpusPerNodeE"></span><span id="tensorrt_llm::runtime::WorldConfig::mGpusPerNode__SizeType"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1a3c6d093540443a20a3204d0129d8be79"></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mGpusPerNode</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig12mGpusPerNodeE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="cpp var">
|
||
<dt class="sig sig-object cpp" id="_CPPv4N12tensorrt_llm7runtime11WorldConfig10mDeviceIdsE">
|
||
<span id="_CPPv3N12tensorrt_llm7runtime11WorldConfig10mDeviceIdsE"></span><span id="_CPPv2N12tensorrt_llm7runtime11WorldConfig10mDeviceIdsE"></span><span id="tensorrt_llm::runtime::WorldConfig::mDeviceIds__std::vector:SizeType:"></span><span class="target" id="classtensorrt__llm_1_1runtime_1_1WorldConfig_1afdf8c7fe626bc4d7d058404882f5b588"></span><span class="n"><span class="pre">std</span></span><span class="p"><span class="pre">::</span></span><span class="n"><span class="pre">vector</span></span><span class="p"><span class="pre"><</span></span><a class="reference internal" href="#_CPPv4N12tensorrt_llm7runtime8SizeTypeE" title="tensorrt_llm::runtime::SizeType"><span class="n"><span class="pre">SizeType</span></span></a><span class="p"><span class="pre">></span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">mDeviceIds</span></span></span><a class="headerlink" href="#_CPPv4N12tensorrt_llm7runtime11WorldConfig10mDeviceIdsE" title="Link to this definition"></a><br /></dt>
|
||
<dd></dd></dl>
|
||
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
</section>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
|
||
<a href="../python-api/tensorrt_llm.runtime.html" class="btn btn-neutral float-left" title="Runtime" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
|
||
<a href="../blogs/H100vsA100.html" class="btn btn-neutral float-right" title="H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
|
||
</div>
|
||
|
||
<hr/>
|
||
|
||
<div role="contentinfo">
|
||
<p>© Copyright 2023, NVidia.</p>
|
||
</div>
|
||
|
||
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
|
||
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
|
||
provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||
|
||
|
||
</footer>
|
||
</div>
|
||
</div>
|
||
</section>
|
||
</div>
|
||
<script>
|
||
jQuery(function () {
|
||
SphinxRtdTheme.Navigation.enable(true);
|
||
});
|
||
</script>
|
||
|
||
</body>
|
||
</html> |