kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
7fd841d6de
TensorRT-LLMs/latest/_modules/tensorrt_llm/runtime/session.html
Kaiyu Xie 7fd841d6de Update latest GitHub pages to v0.21.0rc0
2025-06-04 03:35:09 +00:00

989 lines
81 KiB
HTML
Raw Blame History

<!DOCTYPE html>
<html lang="en" data-content_root="../../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>tensorrt_llm.runtime.session &#8212; TensorRT-LLM</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!--
this give us a css class that will be invisible only if js is disabled
-->
<noscript>
<style>
.pst-js-only { display: none !important; }
</style>
</noscript>
<!-- Loaded before other Sphinx assets -->
<link href="../../../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../../../_static/styles/nvidia-sphinx-theme.css?v=df3ac72c" />
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css?v=76b2166b" />
<link rel="stylesheet" type="text/css" href="../../../_static/autodoc_pydantic.css" />
<!-- So that users can add custom icons -->
<script src="../../../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script>
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" />
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" />
<script src="../../../_static/documentation_options.js?v=5929fcd5"></script>
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../../../_static/copybutton.js?v=65e89d2a"></script>
<script>DOCUMENTATION_OPTIONS.pagename = '_modules/tensorrt_llm/runtime/session';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '0.21.0rc0';
DOCUMENTATION_OPTIONS.show_version_warning_banner =
false;
</script>
<link rel="icon" href="../../../_static/favicon.png"/>
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="0.21.0rc0" />
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<dialog id="pst-search-dialog">
<form class="bd-search d-flex align-items-center"
action="../../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form>
</dialog>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
<div class="bd-header__inner bd-page-width">
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
<span class="fa-solid fa-bars"></span>
</button>
<div class="col-lg-3 navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="../../../index.html">
<img src="../../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
<img src="../../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
<p class="title logo__title">TensorRT-LLM</p>
</a></div>
</div>
<div class="col-lg-9 navbar-header-items">
<div class="me-auto navbar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-2"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-2"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-2"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-2">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="navbar-header-items__end">
<div class="navbar-item navbar-persistent--container">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="navbar-persistent--mobile">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
</div>
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<dialog id="pst-primary-sidebar-modal"></dialog>
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
<a class="navbar-brand logo" href="../../../index.html">
<img src="../../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
<img src="../../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
<p class="title logo__title">TensorRT-LLM</p>
</a>
<div class="sidebar-header-items sidebar-primary__section">
<div class="sidebar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-3"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-3"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-3"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-3">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="sidebar-header-items__end">
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<nav class="bd-docs-nav bd-links"
aria-label="Table of Contents">
<p class="bd-links__title" role="heading" aria-level="1">Table of Contents</p>
<div class="bd-toc-item navbar-nav"><p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../quick-start-guide.html">Quick Start Guide</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../key-features.html">Key Features</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../torch.html">PyTorch Backend</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../release-notes.html">Release Notes</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Installation</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../installation/linux.html">Installing on Linux</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../installation/grace-hopper.html">Installing on Grace Hopper</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">LLM API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api/index.html">API Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api/reference.html">API Reference</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Examples</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../examples/index.html">LLM Examples Introduction</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_eagle_decoding.html">Generate Text Using Eagle Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_async.html">Generate Text Asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_logits_processor.html">Control generated text using logits processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_eagle2_decoding.html">Generate Text Using Eagle2 Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_kv_events.html">Get KV Cache Events</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_quantization.html">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_async_streaming.html">Generate Text in Streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_customize.html">Generate text with customization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../examples/customization.html">LLM Common Customizations</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../examples/llm_api_examples.html">LLM Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_eagle_decoding.html">Generate Text Using Eagle Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_async.html">Generate Text Asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_logits_processor.html">Control generated text using logits processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_eagle2_decoding.html">Generate Text Using Eagle2 Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_kv_events.html">Get KV Cache Events</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_quantization.html">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_async_streaming.html">Generate Text in Streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_customize.html">Generate text with customization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
</ul>
</details></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../examples/trtllm_serve_examples.html">Online Serving Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/curl_chat_client.html">Curl Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/curl_completion_client.html">Curl Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/genai_perf_client.html">Genai Perf Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/genai_perf_client_for_multimodal.html">Genai Perf Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_chat_client.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_chat_client_for_multimodal.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Model Definition API</span></p>
<ul class="nav bd-sidenav">
<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 aria-level="2" class="caption" role="heading"><span class="caption-text">C++ API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/executor.html">Executor</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-build.html">trtllm-build</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-serve.html">trtllm-serve</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Architecture</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/overview.html">TensorRT-LLM Architecture</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/core-concepts.html">Model Definition</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/checkpoint.html">TensorRT-LLM Checkpoint</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/workflow.html">TensorRT-LLM Build Workflow</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/add-model.html">Adding a Model</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Advanced</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/gpt-attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/gpt-runtime.html">C++ GPT Runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/executor.html">Executor API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/graph-rewriting.html">Graph Rewriting Module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/lora.html">Run gpt-2b + LoRA using Executor / cpp runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/expert-parallelism.html">Expert Parallelism in TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/kv-cache-management.html">KV Cache Management: Pools, Blocks, and Events</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/kv-cache-reuse.html">KV cache reuse</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/speculative-decoding.html">Speculative Sampling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/disaggregated-service.html">Disaggregated-Service (experimental)</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Performance</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-benchmarking.html">Benchmarking</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../performance/performance-tuning-guide/index.html">Performance Tuning Guide</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/benchmarking-default-performance.html">Benchmarking Default Performance</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/useful-build-time-flags.html">Useful Build-Time Flags</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.html">Tuning Max Batch Size and Max Num Tokens</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/deciding-model-sharding-strategy.html">Deciding Model Sharding Strategy</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/fp8-quantization.html">FP8 Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/useful-runtime-flags.html">Useful Runtime Options</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-analysis.html">Performance Analysis</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../reference/troubleshooting.html">Troubleshooting</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../reference/support-matrix.html">Support Matrix</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../reference/precision.html">Numerical Precision</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../reference/memory.html">Memory Usage of TensorRT-LLM</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/Falcon180B-H200.html">Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/quantization-in-TRT-LLM.html">Speed up inference with SOTA quantization techniques in TRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html">Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html">DeepSeek R1 MTP Implementation and Optimization</a></li>
</ul>
</div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item">
<nav aria-label="Breadcrumb" class="d-print-none">
<ul class="bd-breadcrumbs">
<li class="breadcrumb-item breadcrumb-home">
<a href="../../../index.html" class="nav-link" aria-label="Home">
<i class="fa-solid fa-home"></i>
</a>
</li>
<li class="breadcrumb-item"><a href="../../index.html" class="nav-link">Module code</a></li>
<li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">tensorrt_llm.runtime.session</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<h1>Source code for tensorrt_llm.runtime.session</h1><div class="highlight"><pre>
<span></span><span class="c1"># SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION &amp; AFFILIATES. All rights reserved.</span>
<span class="c1"># SPDX-License-Identifier: Apache-2.0</span>
<span class="c1">#</span>
<span class="c1"># Licensed under the Apache License, Version 2.0 (the &quot;License&quot;);</span>
<span class="c1"># you may not use this file except in compliance with the License.</span>
<span class="c1"># You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">__future__</span><span class="w"> </span><span class="kn">import</span> <span class="n">annotations</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">contextlib</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">dataclasses</span><span class="w"> </span><span class="kn">import</span> <span class="n">dataclass</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">math</span><span class="w"> </span><span class="kn">import</span> <span class="n">prod</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Optional</span>
<span class="c1"># isort: off</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">tensorrt</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">trt</span>
<span class="c1"># isort: on</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">.._utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">torch_dtype_to_trt</span><span class="p">,</span> <span class="n">trt_dtype_to_torch</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">..logger</span><span class="w"> </span><span class="kn">import</span> <span class="n">logger</span>
<span class="nd">@contextlib</span><span class="o">.</span><span class="n">contextmanager</span>
<span class="k">def</span><span class="w"> </span><span class="nf">_scoped_stream</span><span class="p">():</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;Create a scoped cuda stream, and synchronize it when the context is destroyed</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="c1">#TODO: delete torch, use cuda native python bindings</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
<span class="n">stream</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">current_stream</span><span class="p">()</span>
<span class="k">try</span><span class="p">:</span>
<span class="c1"># return a handle, trt and other lib does not recognize torch.cuda.Stream</span>
<span class="k">yield</span> <span class="n">stream</span><span class="o">.</span><span class="n">cuda_stream</span>
<span class="k">finally</span><span class="p">:</span>
<span class="n">stream</span><span class="o">.</span><span class="n">synchronize</span><span class="p">()</span>
<div class="viewcode-block" id="TensorInfo">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.TensorInfo">[docs]</a>
<span class="nd">@dataclass</span>
<span class="k">class</span><span class="w"> </span><span class="nc">TensorInfo</span><span class="p">:</span>
<span class="n">name</span><span class="p">:</span> <span class="nb">str</span>
<span class="n">dtype</span><span class="p">:</span> <span class="n">trt</span><span class="o">.</span><span class="n">DataType</span>
<span class="n">shape</span><span class="p">:</span> <span class="nb">tuple</span>
<span class="c1"># add more info like strides, formats if needed</span>
<div class="viewcode-block" id="TensorInfo.numel">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.TensorInfo.numel">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">numel</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="n">prod</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span></div>
<div class="viewcode-block" id="TensorInfo.view">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.TensorInfo.view">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">view</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">shape</span><span class="p">):</span>
<span class="k">assert</span> <span class="nb">set</span><span class="p">(</span><span class="nb">map</span><span class="p">(</span><span class="nb">type</span><span class="p">,</span> <span class="n">shape</span><span class="p">))</span> <span class="o">==</span> <span class="p">{</span><span class="nb">int</span><span class="p">}</span>
<span class="n">n_unknown</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="nb">tuple</span><span class="p">(</span><span class="nb">filter</span><span class="p">(</span><span class="k">lambda</span> <span class="n">l</span><span class="p">:</span> <span class="n">l</span> <span class="o">&lt;</span> <span class="mi">0</span><span class="p">,</span> <span class="n">shape</span><span class="p">)))</span>
<span class="n">new_shape</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">shape</span><span class="p">)</span>
<span class="k">if</span> <span class="n">n_unknown</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">prod</span><span class="p">(</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">numel</span><span class="p">()</span>
<span class="k">elif</span> <span class="n">n_unknown</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="n">n_known_elements</span> <span class="o">=</span> <span class="n">prod</span><span class="p">(</span><span class="nb">filter</span><span class="p">(</span><span class="k">lambda</span> <span class="n">l</span><span class="p">:</span> <span class="n">l</span> <span class="o">&gt;=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">shape</span><span class="p">))</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">l</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">new_shape</span><span class="p">):</span>
<span class="k">if</span> <span class="n">l</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">numel</span><span class="p">()</span> <span class="o">%</span> <span class="n">n_known_elements</span> <span class="o">==</span> <span class="mi">0</span>
<span class="n">new_shape</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">numel</span><span class="p">()</span> <span class="o">//</span> <span class="n">n_known_elements</span>
<span class="k">break</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;More than one dimensions need to be inferred!&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">TensorInfo</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">new_shape</span><span class="p">))</span></div>
<span class="k">def</span><span class="w"> </span><span class="fm">__len__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<div class="viewcode-block" id="TensorInfo.squeeze">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.TensorInfo.squeeze">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">squeeze</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dim</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="n">dim</span><span class="p">]</span> <span class="o">!=</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;dim </span><span class="si">{</span><span class="n">dim</span><span class="si">}</span><span class="s2"> is </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="n">dim</span><span class="p">]</span><span class="si">}</span><span class="s2"> instead of 1!&quot;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">TensorInfo</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">shape</span><span class="p">[:</span><span class="n">dim</span><span class="p">]</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="n">dim</span> <span class="o">+</span> <span class="mi">1</span><span class="p">:])</span></div>
</div>
<div class="viewcode-block" id="Session">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.Session">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">Session</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39; Session is a managed TensorRT runtime. &#39;&#39;&#39;</span>
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="c1"># use Session.from_serialized_engine to create a session</span>
<span class="k">pass</span>
<span class="k">def</span><span class="w"> </span><span class="nf">_init</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">engine_buffer</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> @brief: Setup TensorRT engines and context from a serialized engine file</span>
<span class="sd"> @param engine_buffer: a buffer holds the serialized TRT engine</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_runtime</span> <span class="o">=</span> <span class="n">trt</span><span class="o">.</span><span class="n">Runtime</span><span class="p">(</span><span class="n">logger</span><span class="o">.</span><span class="n">trt_logger</span><span class="p">)</span>
<span class="k">if</span> <span class="n">engine_buffer</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_engine</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">runtime</span><span class="o">.</span><span class="n">deserialize_cuda_engine</span><span class="p">(</span><span class="n">engine_buffer</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_context</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">streamable_weights_size</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">__prepare_execution_contexts</span><span class="p">()</span>
<span class="k">return</span> <span class="bp">self</span>
<span class="k">def</span><span class="w"> </span><span class="nf">__prepare_execution_contexts</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_context</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">create_execution_context</span><span class="p">()</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_context</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">,</span> <span class="s2">&quot;Failed to create an execution context!&quot;</span>
<span class="k">with</span> <span class="n">_scoped_stream</span><span class="p">()</span> <span class="k">as</span> <span class="n">stream</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_context</span><span class="o">.</span><span class="n">set_optimization_profile_async</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">stream</span><span class="p">)</span>
<div class="viewcode-block" id="Session.from_serialized_engine">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.Session.from_serialized_engine">[docs]</a>
<span class="nd">@staticmethod</span>
<span class="k">def</span><span class="w"> </span><span class="nf">from_serialized_engine</span><span class="p">(</span><span class="n">engine</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Session</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> @brief: Create a session from a serialized engine</span>
<span class="sd"> @param engine: a serialized engine</span>
<span class="sd"> @return: a Session object</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="n">session</span> <span class="o">=</span> <span class="n">Session</span><span class="p">()</span>
<span class="k">return</span> <span class="n">session</span><span class="o">.</span><span class="n">_init</span><span class="p">(</span><span class="n">engine</span><span class="p">)</span></div>
<div class="viewcode-block" id="Session.from_engine">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.Session.from_engine">[docs]</a>
<span class="nd">@staticmethod</span>
<span class="k">def</span><span class="w"> </span><span class="nf">from_engine</span><span class="p">(</span><span class="n">engine</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Session</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> @brief: Create a session from an existing ICudaEngine engine</span>
<span class="sd"> @param engine: an ICudaEngine</span>
<span class="sd"> @return: a Session object</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="n">session</span> <span class="o">=</span> <span class="n">Session</span><span class="p">()</span>
<span class="n">session</span><span class="o">.</span><span class="n">engine</span> <span class="o">=</span> <span class="n">engine</span>
<span class="k">return</span> <span class="n">session</span><span class="o">.</span><span class="n">_init</span><span class="p">()</span></div>
<span class="nd">@property</span>
<span class="k">def</span><span class="w"> </span><span class="nf">runtime</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">trt</span><span class="o">.</span><span class="n">Runtime</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_runtime</span>
<span class="nd">@property</span>
<span class="k">def</span><span class="w"> </span><span class="nf">engine</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">trt</span><span class="o">.</span><span class="n">ICudaEngine</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_engine</span>
<span class="nd">@engine</span><span class="o">.</span><span class="n">setter</span>
<span class="k">def</span><span class="w"> </span><span class="nf">engine</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">engine</span><span class="p">:</span> <span class="n">trt</span><span class="o">.</span><span class="n">ICudaEngine</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_engine</span> <span class="o">=</span> <span class="n">engine</span>
<span class="nd">@property</span>
<span class="k">def</span><span class="w"> </span><span class="nf">context</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">trt</span><span class="o">.</span><span class="n">IExecutionContext</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> @brief: Get the default TensorRT execution context,</span>
<span class="sd"> use self.engine.create_execution_context() to create a new context if needed</span>
<span class="sd"> @return: one TensorRT execution context object</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_context</span>
<span class="nd">@property</span>
<span class="k">def</span><span class="w"> </span><span class="nf">context_mem_size</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">device_memory_size_v2</span>
<span class="k">def</span><span class="w"> </span><span class="nf">_print_engine_info</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;print engine info for debug purpose, internal use only.</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="n">refittable</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">refittable</span>
<span class="n">num_layers</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">num_layers</span>
<span class="n">device_memory_size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">device_memory_size_v2</span>
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">name</span>
<span class="n">nb_profiles</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">num_optimization_profiles</span>
<span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Engine:</span><span class="si">{</span><span class="n">name</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">refittable</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">num_layers</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">device_memory_size</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">nb_profiles</span><span class="si">=:}</span><span class="s2">&quot;</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_print_io_info</span><span class="p">()</span>
<span class="k">def</span><span class="w"> </span><span class="nf">_print_io_info</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;print engine i/o info for debug purpose, internal use only.</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">num_io_tensors</span><span class="p">):</span>
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_name</span><span class="p">(</span><span class="n">i</span><span class="p">)</span>
<span class="n">mode</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_mode</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
<span class="n">shape</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_shape</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
<span class="n">dtype</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_dtype</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
<span class="n">tformat</span> <span class="o">=</span> <span class="s2">&quot;;&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span>
<span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_format_desc</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">p</span><span class="p">)</span>
<span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">num_optimization_profiles</span><span class="p">)</span>
<span class="p">])</span>
<span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Tensor:</span><span class="si">{</span><span class="n">name</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">mode</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">shape</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">dtype</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">tformat</span><span class="si">=:}</span><span class="s2">&quot;</span><span class="p">)</span>
<div class="viewcode-block" id="Session.set_shapes">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.Session.set_shapes">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">set_shapes</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">tensor_dict</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">],</span>
<span class="n">context</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">trt</span><span class="o">.</span><span class="n">IExecutionContext</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
<span class="k">if</span> <span class="n">context</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">context</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">context</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">num_io_tensors</span><span class="p">):</span>
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_name</span><span class="p">(</span><span class="n">i</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_mode</span><span class="p">(</span><span class="n">name</span><span class="p">)</span> <span class="o">==</span> <span class="n">trt</span><span class="o">.</span><span class="n">TensorIOMode</span><span class="o">.</span><span class="n">INPUT</span><span class="p">:</span>
<span class="n">ok</span> <span class="o">=</span> <span class="n">context</span><span class="o">.</span><span class="n">set_input_shape</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">tensor_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;setting input tensor </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> with shape </span><span class="si">{</span><span class="n">tensor_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">ok</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Couldn&#39;t assign </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> with shape </span><span class="si">{</span><span class="n">tensor_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2">, &quot;</span>
<span class="sa">f</span><span class="s2">&quot;engine supports [min, opt, max] = </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_profile_shape</span><span class="p">(</span><span class="n">name</span><span class="p">,</span><span class="w"> </span><span class="n">context</span><span class="o">.</span><span class="n">active_optimization_profile</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="p">)</span></div>
<div class="viewcode-block" id="Session.infer_shapes">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.Session.infer_shapes">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">infer_shapes</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">inputs</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">TensorInfo</span><span class="p">],</span>
<span class="n">context</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">trt</span><span class="o">.</span><span class="n">IExecutionContext</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="n">TensorInfo</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> @brief: Set input shapes to given context, and infer the output shapes from the given input shapes.</span>
<span class="sd"> This function should be called every time when the input shapes are changed before calling run().</span>
<span class="sd"> Or call the context.set_input_shape on all dynamic shaped input tensors manually.</span>
<span class="sd"> @param inputs: list of TensorInfo object, each item represents an input tensor</span>
<span class="sd"> @param context: TensorRT execution context, if None, use the default context</span>
<span class="sd"> @return: list of TensorInfo object, each item represents an output tensor, returns None if failed</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="c1"># set shape to the default context if context is not specified</span>
<span class="k">if</span> <span class="n">context</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">context</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">context</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">inputs</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_mode</span><span class="p">(</span><span class="n">i</span><span class="o">.</span><span class="n">name</span><span class="p">)</span> <span class="o">!=</span> <span class="n">trt</span><span class="o">.</span><span class="n">TensorIOMode</span><span class="o">.</span><span class="n">INPUT</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Tensor:</span><span class="si">{</span><span class="n">i</span><span class="o">.</span><span class="n">name</span><span class="si">}</span><span class="s2"> is not an input tensor&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_dtype</span><span class="p">(</span><span class="n">i</span><span class="o">.</span><span class="n">name</span><span class="p">)</span> <span class="o">!=</span> <span class="n">i</span><span class="o">.</span><span class="n">dtype</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Tensor:</span><span class="si">{</span><span class="n">i</span><span class="o">.</span><span class="n">name</span><span class="si">}</span><span class="s2"> has wrong dtype&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">context</span><span class="o">.</span><span class="n">set_input_shape</span><span class="p">(</span><span class="n">i</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">i</span><span class="o">.</span><span class="n">shape</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Could not set shape </span><span class="si">{</span><span class="n">i</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2"> for tensor </span><span class="si">{</span><span class="n">i</span><span class="o">.</span><span class="n">name</span><span class="si">}</span><span class="s2">. Please check the profile range for which your model was build.&quot;</span>
<span class="p">)</span>
<span class="n">outputs</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">num_io_tensors</span><span class="p">):</span>
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_name</span><span class="p">(</span><span class="n">i</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_mode</span><span class="p">(</span><span class="n">name</span><span class="p">)</span> <span class="o">==</span> <span class="n">trt</span><span class="o">.</span><span class="n">TensorIOMode</span><span class="o">.</span><span class="n">OUTPUT</span><span class="p">:</span>
<span class="n">shape</span> <span class="o">=</span> <span class="n">context</span><span class="o">.</span><span class="n">get_tensor_shape</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
<span class="n">dtype</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_dtype</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
<span class="n">outputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">TensorInfo</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">dtype</span><span class="p">,</span> <span class="n">shape</span><span class="p">))</span>
<span class="k">return</span> <span class="n">outputs</span></div>
<span class="k">def</span><span class="w"> </span><span class="nf">_set_weight_streaming</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">gpu_weights_percent</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">streamable_weights_size</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">gpu_weights_percent</span> <span class="o">==</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">&quot;Engine built without weight streaming. Cannot set gpu_weights_percent to a value other than 1.&quot;</span>
<span class="k">return</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_context</span> <span class="o">=</span> <span class="kc">None</span>
<span class="nb">min</span> <span class="o">=</span> <span class="mi">0</span>
<span class="nb">max</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">streamable_weights_size</span>
<span class="n">budget</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">gpu_weights_percent</span> <span class="o">*</span> <span class="nb">max</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">weight_streaming_budget_v2</span> <span class="o">=</span> <span class="n">budget</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">weight_streaming_budget_v2</span> <span class="o">==</span> <span class="n">budget</span><span class="p">,</span> <span class="s2">&quot;Failed to set weight streaming budget!&quot;</span>
<span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Set gpu weights percent to </span><span class="si">{</span><span class="n">gpu_weights_percent</span><span class="si">}</span><span class="s2">, which is </span><span class="si">{</span><span class="n">budget</span><span class="si">}</span><span class="s2"> bytes. Valid range: </span><span class="si">{</span><span class="nb">min</span><span class="si">}</span><span class="s2"> bytes ~ </span><span class="si">{</span><span class="nb">max</span><span class="si">}</span><span class="s2"> bytes.&quot;</span>
<span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">__prepare_execution_contexts</span><span class="p">()</span>
<span class="k">except</span><span class="p">:</span>
<span class="n">free_mem</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">mem_get_info</span><span class="p">()[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">if</span> <span class="n">free_mem</span> <span class="o">&lt;</span> <span class="n">budget</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">OutOfMemoryError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Out of Memory: Memory budget is </span><span class="si">{</span><span class="n">budget</span><span class="si">}</span><span class="s2"> bytes but only </span><span class="si">{</span><span class="n">free_mem</span><span class="si">}</span><span class="s2"> bytes are available on the GPU.&quot;</span>
<span class="p">)</span>
<span class="k">raise</span>
<div class="viewcode-block" id="Session.run">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.Session.run">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">run</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">inputs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">],</span>
<span class="n">outputs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">],</span>
<span class="n">stream</span><span class="p">,</span>
<span class="n">context</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> @brief: Run the TensorRT engine with the given inputs and outputs</span>
<span class="sd"> @param inputs: dict of input tensors, key is tensor name, value is tensor pointer or torch tensor</span>
<span class="sd"> @param outputs: dict of output tensors, key is tensor name, value is tensor pointer or torch tensor</span>
<span class="sd"> @param stream: cuda stream to enqueue the TensorRT engine on</span>
<span class="sd"> @param context: TensorRT execution context, if None, use the default context</span>
<span class="sd"> @return: True if enqueue succeeded, note the enqueue is an async call,</span>
<span class="sd"> returning True does not mean the execution is finished</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="c1"># enqueue to the default context if context is not specified</span>
<span class="k">if</span> <span class="n">context</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">context</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">context</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
<span class="k">for</span> <span class="n">tensor_name</span> <span class="ow">in</span> <span class="n">inputs</span><span class="p">:</span>
<span class="n">tensor</span> <span class="o">=</span> <span class="n">inputs</span><span class="p">[</span><span class="n">tensor_name</span><span class="p">]</span>
<span class="n">ptr</span> <span class="o">=</span> <span class="n">tensor</span><span class="o">.</span><span class="n">data_ptr</span><span class="p">()</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">tensor</span><span class="p">,</span>
<span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">)</span> <span class="k">else</span> <span class="n">tensor</span>
<span class="n">context</span><span class="o">.</span><span class="n">set_tensor_address</span><span class="p">(</span><span class="n">tensor_name</span><span class="p">,</span> <span class="n">ptr</span><span class="p">)</span>
<span class="k">for</span> <span class="n">tensor_name</span> <span class="ow">in</span> <span class="n">outputs</span><span class="p">:</span>
<span class="n">tensor</span> <span class="o">=</span> <span class="n">outputs</span><span class="p">[</span><span class="n">tensor_name</span><span class="p">]</span>
<span class="n">ptr</span> <span class="o">=</span> <span class="n">tensor</span><span class="o">.</span><span class="n">data_ptr</span><span class="p">()</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">tensor</span><span class="p">,</span>
<span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">)</span> <span class="k">else</span> <span class="n">tensor</span>
<span class="n">context</span><span class="o">.</span><span class="n">set_tensor_address</span><span class="p">(</span><span class="n">tensor_name</span><span class="p">,</span> <span class="n">ptr</span><span class="p">)</span>
<span class="n">ok</span> <span class="o">=</span> <span class="n">context</span><span class="o">.</span><span class="n">execute_async_v3</span><span class="p">(</span><span class="n">stream</span><span class="p">)</span>
<span class="k">return</span> <span class="n">ok</span></div>
<span class="k">def</span><span class="w"> </span><span class="nf">_debug_run</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">inputs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="s2">&quot;torch.Tensor&quot;</span><span class="p">],</span>
<span class="n">context</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="s2">&quot;torch.Tensor&quot;</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;Run the engine enqueue with allocated output tensors, for debug purpose, since it is a sync call and slower than run</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
<span class="n">inputs_info</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">TensorInfo</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">torch_dtype_to_trt</span><span class="p">(</span><span class="n">tensor</span><span class="o">.</span><span class="n">dtype</span><span class="p">),</span> <span class="n">tensor</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
<span class="k">for</span> <span class="n">name</span><span class="p">,</span> <span class="n">tensor</span> <span class="ow">in</span> <span class="n">inputs</span><span class="o">.</span><span class="n">items</span><span class="p">()</span>
<span class="p">]</span>
<span class="n">outputs_info</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">infer_shapes</span><span class="p">(</span><span class="n">inputs_info</span><span class="p">)</span>
<span class="n">outputs</span> <span class="o">=</span> <span class="p">{</span>
<span class="n">t</span><span class="o">.</span><span class="n">name</span><span class="p">:</span>
<span class="n">torch</span><span class="o">.</span><span class="n">empty</span><span class="p">(</span><span class="nb">tuple</span><span class="p">(</span><span class="n">t</span><span class="o">.</span><span class="n">shape</span><span class="p">),</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt_dtype_to_torch</span><span class="p">(</span><span class="n">t</span><span class="o">.</span><span class="n">dtype</span><span class="p">),</span>
<span class="n">device</span><span class="o">=</span><span class="s1">&#39;cuda&#39;</span><span class="p">)</span>
<span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">outputs_info</span>
<span class="p">}</span>
<span class="k">with</span> <span class="n">_scoped_stream</span><span class="p">()</span> <span class="k">as</span> <span class="n">stream</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">inputs</span><span class="o">=</span><span class="n">inputs</span><span class="p">,</span>
<span class="n">outputs</span><span class="o">=</span><span class="n">outputs</span><span class="p">,</span>
<span class="n">stream</span><span class="o">=</span><span class="n">stream</span><span class="p">,</span>
<span class="n">context</span><span class="o">=</span><span class="n">context</span><span class="p">)</span>
<span class="k">return</span> <span class="n">outputs</span></div>
</pre></div>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
</div>
</footer>
</div>
<div class="bd-sidebar-secondary"></div>
</div>
<footer class="bd-footer-content">
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script defer src="../../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf"></script>
<script defer src="../../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf"></script>
<footer class="bd-footer">
<div class="bd-footer__inner bd-page-width">
<div class="footer-items__start">
<div class="footer-item">
<a class="footer-brand logo" href="https://www.nvidia.com">
<img src="../../../_static/nvidia-logo-horiz-rgb-1c-blk-for-screen.svg" class="logo__image only-light" alt="NVIDIA"/>
<img src="../../../_static/nvidia-logo-horiz-rgb-1c-wht-for-screen.svg" class="logo__image only-dark" alt="NVIDIA"/>
</a></div>
<div class="footer-item">
<div class="footer-links">
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/">Privacy Policy</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-center/">Manage My Privacy</a>
|
<a class="external" href="https://www.nvidia.com/en-us/preferences/start/">Do Not Sell or Share My Data</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/terms-of-service/">Terms of Service</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/accessibility/">Accessibility</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/company-policies/">Corporate Policies</a>
|
<a class="external" href="https://www.nvidia.com/en-us/product-security/">Product Security</a>
|
<a class="external" href="https://www.nvidia.com/en-us/contact/">Contact</a>
</div>
</div>
<div class="footer-item">
<p class="copyright">
Copyright © 2025, NVidia.
<br/>
</p>
</div>
<div class="footer-item">
<div class="extra_footer">
<p>Last updated on June 03, 2025.</p>
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/9ae2ce6">9ae2ce6</a>.</p>
</div></div>
</div>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink