mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
1488 lines
143 KiB
HTML
1488 lines
143 KiB
HTML
|
||
|
||
<!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.plugin.plugin — 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" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/togglebutton.css?v=13237357" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/custom.css?v=19d20f17" />
|
||
|
||
<!-- 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>let toggleHintShow = 'Click to show';</script>
|
||
<script>let toggleHintHide = 'Click to hide';</script>
|
||
<script>let toggleOpenOnPrint = 'true';</script>
|
||
<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
|
||
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
|
||
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
|
||
<script>DOCUMENTATION_OPTIONS.pagename = '_modules/tensorrt_llm/plugin/plugin';</script>
|
||
<script>
|
||
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.2.0rc0';
|
||
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="1.2.0rc0" />
|
||
|
||
|
||
</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 has-children"><a class="reference internal" href="../../../installation/index.html">Installation</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="../../../installation/containers.html">Pre-built release container images on NGC</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../installation/linux.html">Installing on Linux via <code class="docutils literal notranslate"><span class="pre">pip</span></code></a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Deployment Guide</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<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_inference.html">Generate text</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_async_streaming.html">Generate text in streaming</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_guided_decoding.html">Generate text with guided decoding</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_multilora.html">Generate text with multiple LoRA adapters</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_speculative_decoding.html">Speculative Decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_kv_cache_connector.html">KV Cache Connector</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_kv_cache_offloading.html">KV Cache Offloading</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_runtime.html">Runtime Configuration Examples</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_sampling.html">Sampling Techniques Showcase</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_llm_distributed.html">Run LLM-API with pytorch backend on Slurm</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_trtllm_bench.html">Run trtllm-bench with pytorch backend on Slurm</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_trtllm_serve.html">Run trtllm-serve with pytorch backend on Slurm</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 for Multimodal</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client_for_lora.html">Openai Completion Client For Lora</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client_json_schema.html">OpenAI Completion Client with JSON Schema</a></li>
|
||
</ul>
|
||
</details></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../examples/dynamo_k8s_example.html">Dynamo K8s Example</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../deployment-guide/index.html">Model Recipes</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="../../../deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.html">Quick Start Recipe for DeepSeek R1 on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/quick-start-recipe-for-llama3.3-70b-on-trtllm.html">Quick Start Recipe for Llama3.3 70B on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/quick-start-recipe-for-llama4-scout-on-trtllm.html">Quick Start Recipe for Llama4 Scout 17B on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/quick-start-recipe-for-gpt-oss-on-trtllm.html">Quick Start Recipe for GPT-OSS on TensorRT-LLM - Blackwell Hardware</a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Models</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../models/supported-models.html">Supported Models</a></li>
|
||
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../models/adding-new-model.html">Adding a New Model</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">CLI Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-bench.html">trtllm-bench</a></li>
|
||
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-eval.html">trtllm-eval</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../commands/trtllm-serve/index.html">trtllm-serve</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="../../../commands/trtllm-serve/trtllm-serve.html">trtllm-serve</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../commands/trtllm-serve/run-benchmark-with-trtllm-serve.html">Run benchmarking with <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code></a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">API Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api/index.html">LLM 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">Features</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/feature-combination-matrix.html">Feature Combination Matrix</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/disagg-serving.html">Disaggregated Serving (Beta)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/kvcache.html">KV Cache System</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/long-sequence.html">Long Sequences</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/lora.html">LoRA (Low-Rank Adaptation)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/multi-modality.html">Multimodal Support in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/overlap-scheduler.html">Overlap Scheduler</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/paged-attention-ifb-scheduler.html">Paged Attention, IFB, and Request Scheduling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/parallel-strategy.html">Parallelism in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/quantization.html">Quantization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/sampling.html">Sampling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/speculative-decoding.html">Speculative Decoding</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/checkpoint-loading.html">Checkpoint Loading</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/auto_deploy/auto-deploy.html">AutoDeploy (Prototype)</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Developer Guide</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/overview.html">Architecture Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/perf-analysis.html">Performance Analysis</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/perf-benchmarking.html">TensorRT LLM Benchmarking</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/ci-overview.html">Continuous Integration Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/dev-containers.html">Using Dev Containers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/api-change.html">LLM API Change Guide</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/tech_blog/blog10_ADP_Balance_Strategy.html">ADP Balance Strategy</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog11_GPT_OSS_Eagle3.html">Running GPT-OSS-120B with Eagle3 Speculative Decoding on GB200/B200 (TensorRT LLM)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.html">Combining Guided Decoding and Speculative Decoding: Making CPU and GPU Cooperate Seamlessly</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog13_Inference_Time_Compute_Implementation_in_TensorRT-LLM.html">Inference Time Compute Implementation in TensorRT LLM</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>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html">Optimizing DeepSeek R1 Throughput on NVIDIA Blackwell GPUs: A Deep Dive for Developers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html">Scaling Expert Parallelism in TensorRT LLM (Part 1: Design and Implementation of Large-scale EP)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html">Disaggregated Serving in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html">How to launch Llama4 Maverick + Eagle3 TensorRT LLM server</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html">N-Gram Speculative Decoding in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html">Scaling Expert Parallelism in TensorRT LLM (Part 2: Performance Status and Optimization)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html">Running a High Performance GPT-OSS-120B Inference Server with TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.html">How to get best performance on DeepSeek-R1 in TensorRT LLM</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/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/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Quick Links</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/releases">Releases</a></li>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM">Github Code</a></li>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/issues?q=is%3Aissue%20state%3Aopen%20label%3Aroadmap">Roadmap</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Use TensorRT Engine</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../legacy/tensorrt_quickstart.html">LLM API with TensorRT Engine</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.plugin.plugin</span></li>
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<div id="searchbox"></div>
|
||
<article class="bd-article">
|
||
|
||
<h1>Source code for tensorrt_llm.plugin.plugin</h1><div class="highlight"><pre>
|
||
<span></span><span class="c1"># SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & 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 "License");</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 "AS IS" 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">import</span><span class="w"> </span><span class="nn">argparse</span>
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">ctypes</span>
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">platform</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">collections</span><span class="w"> </span><span class="kn">import</span> <span class="n">OrderedDict</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">asdict</span><span class="p">,</span> <span class="n">dataclass</span><span class="p">,</span> <span class="n">field</span><span class="p">,</span> <span class="n">fields</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">enum</span><span class="w"> </span><span class="kn">import</span> <span class="n">IntEnum</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">pathlib</span><span class="w"> </span><span class="kn">import</span> <span class="n">Path</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">textwrap</span><span class="w"> </span><span class="kn">import</span> <span class="n">dedent</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">List</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Tuple</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="kn">from</span><span class="w"> </span><span class="nn">.._ipc_utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">IpcMemory</span><span class="p">,</span> <span class="n">can_access_peer</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">get_sm_version</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">..bindings.internal.runtime</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span><span class="n">lamport_initialize</span><span class="p">,</span>
|
||
<span class="n">lamport_initialize_all</span><span class="p">,</span>
|
||
<span class="n">max_workspace_size_lowprecision</span><span class="p">)</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="kn">from</span><span class="w"> </span><span class="nn">..mapping</span><span class="w"> </span><span class="kn">import</span> <span class="n">Mapping</span>
|
||
|
||
<span class="n">TRT_LLM_PLUGIN_NAMESPACE</span> <span class="o">=</span> <span class="s1">'tensorrt_llm'</span>
|
||
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">plugin_lib_path</span><span class="p">()</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span>
|
||
<span class="n">project_dir</span> <span class="o">=</span> <span class="n">Path</span><span class="p">(</span><span class="vm">__file__</span><span class="p">)</span><span class="o">.</span><span class="n">parent</span><span class="o">.</span><span class="n">parent</span><span class="o">.</span><span class="n">absolute</span><span class="p">()</span>
|
||
<span class="n">dyn_lib</span> <span class="o">=</span> <span class="s2">"libnvinfer_plugin_tensorrt_llm.so"</span> <span class="k">if</span> <span class="n">platform</span><span class="o">.</span><span class="n">system</span><span class="p">(</span>
|
||
<span class="p">)</span> <span class="o">!=</span> <span class="s2">"Windows"</span> <span class="k">else</span> <span class="s2">"nvinfer_plugin_tensorrt_llm.dll"</span>
|
||
<span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">project_dir</span><span class="o">.</span><span class="n">joinpath</span><span class="p">(</span><span class="s2">"libs"</span><span class="p">,</span> <span class="n">dyn_lib</span><span class="p">))</span>
|
||
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">_load_plugin_lib</span><span class="p">():</span>
|
||
<span class="n">on_windows</span> <span class="o">=</span> <span class="n">platform</span><span class="o">.</span><span class="n">system</span><span class="p">()</span> <span class="o">==</span> <span class="s2">"Windows"</span>
|
||
<span class="n">winmode</span> <span class="o">=</span> <span class="mi">0</span> <span class="k">if</span> <span class="n">on_windows</span> <span class="k">else</span> <span class="kc">None</span>
|
||
<span class="n">handle</span> <span class="o">=</span> <span class="n">ctypes</span><span class="o">.</span><span class="n">CDLL</span><span class="p">(</span><span class="n">plugin_lib_path</span><span class="p">(),</span>
|
||
<span class="n">mode</span><span class="o">=</span><span class="n">ctypes</span><span class="o">.</span><span class="n">RTLD_GLOBAL</span><span class="p">,</span>
|
||
<span class="n">winmode</span><span class="o">=</span><span class="n">winmode</span><span class="p">)</span>
|
||
<span class="k">try</span><span class="p">:</span>
|
||
<span class="n">handle</span><span class="o">.</span><span class="n">initTrtLlmPlugins</span><span class="o">.</span><span class="n">argtypes</span> <span class="o">=</span> <span class="p">[</span><span class="n">ctypes</span><span class="o">.</span><span class="n">c_void_p</span><span class="p">,</span> <span class="n">ctypes</span><span class="o">.</span><span class="n">c_char_p</span><span class="p">]</span>
|
||
<span class="n">handle</span><span class="o">.</span><span class="n">initTrtLlmPlugins</span><span class="o">.</span><span class="n">restype</span> <span class="o">=</span> <span class="n">ctypes</span><span class="o">.</span><span class="n">c_bool</span>
|
||
<span class="k">except</span> <span class="ne">AttributeError</span> <span class="k">as</span> <span class="n">err</span><span class="p">:</span>
|
||
<span class="k">raise</span> <span class="ne">ImportError</span><span class="p">(</span><span class="s1">'TensorRT LLM Plugin is unavailable'</span><span class="p">)</span> <span class="kn">from</span><span class="w"> </span><span class="nn">err</span>
|
||
|
||
<span class="k">try</span><span class="p">:</span>
|
||
<span class="k">assert</span> <span class="n">handle</span><span class="o">.</span><span class="n">initTrtLlmPlugins</span><span class="p">(</span>
|
||
<span class="kc">None</span><span class="p">,</span> <span class="n">TRT_LLM_PLUGIN_NAMESPACE</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">))</span>
|
||
<span class="k">except</span> <span class="ne">OSError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
|
||
<span class="n">windows_err</span> <span class="o">=</span> <span class="s2">"""</span>
|
||
<span class="s2"> The error above may be caused by an outdated Microsoft Visual C++ Redistributable Version.</span>
|
||
<span class="s2"> Please install the latest MSVC from the link below and re-launch.</span>
|
||
|
||
<span class="s2"> https://learn.microsoft.com/en-us/cpp/windows/latest-supported-vc-redist?view=msvc-170#latest-microsoft-visual-c-redistributable-version</span>
|
||
<span class="s2"> """</span>
|
||
<span class="n">err_msg</span> <span class="o">=</span> <span class="n">dedent</span><span class="p">(</span><span class="n">windows_err</span> <span class="k">if</span> <span class="n">on_windows</span> <span class="k">else</span> <span class="s2">"Unknown error"</span><span class="p">)</span>
|
||
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="n">err_msg</span><span class="p">)</span> <span class="kn">from</span><span class="w"> </span><span class="nn">e</span>
|
||
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
|
||
<span class="k">raise</span> <span class="n">e</span>
|
||
|
||
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">ContextFMHAType</span><span class="p">(</span><span class="n">IntEnum</span><span class="p">):</span>
|
||
<span class="n">disabled</span> <span class="o">=</span> <span class="mi">0</span>
|
||
<span class="c1"># FP16 I/O, FP16 Accumulation</span>
|
||
<span class="n">enabled</span> <span class="o">=</span> <span class="mi">1</span>
|
||
<span class="c1"># FP16 I/O, FP32 Accumulation</span>
|
||
<span class="n">enabled_with_fp32_acc</span> <span class="o">=</span> <span class="mi">2</span>
|
||
|
||
|
||
<span class="n">DEFAULT_PLUGIN_DTYPE_OPTIONS</span> <span class="o">=</span> <span class="p">[</span>
|
||
<span class="s2">"auto"</span><span class="p">,</span> <span class="s2">"float16"</span><span class="p">,</span> <span class="s2">"float32"</span><span class="p">,</span> <span class="s2">"bfloat16"</span><span class="p">,</span> <span class="s2">"int32"</span><span class="p">,</span> <span class="kc">None</span>
|
||
<span class="p">]</span>
|
||
<span class="n">PLUGIN_DTYPE_OPTIONS_MAP</span> <span class="o">=</span> <span class="p">{</span>
|
||
<span class="s2">"gemm_swiglu_plugin"</span><span class="p">:</span> <span class="p">[</span><span class="s2">"fp8"</span><span class="p">,</span> <span class="kc">None</span><span class="p">],</span>
|
||
<span class="s2">"gemm_plugin"</span><span class="p">:</span>
|
||
<span class="p">[</span><span class="s2">"auto"</span><span class="p">,</span> <span class="s2">"float16"</span><span class="p">,</span> <span class="s2">"float32"</span><span class="p">,</span> <span class="s2">"bfloat16"</span><span class="p">,</span> <span class="s2">"int32"</span><span class="p">,</span> <span class="s2">"fp8"</span><span class="p">,</span> <span class="s2">"nvfp4"</span><span class="p">,</span> <span class="kc">None</span><span class="p">],</span>
|
||
<span class="s2">"low_latency_gemm_plugin"</span><span class="p">:</span> <span class="p">[</span><span class="s2">"fp8"</span><span class="p">,</span> <span class="kc">None</span><span class="p">],</span>
|
||
<span class="s2">"low_latency_gemm_swiglu_plugin"</span><span class="p">:</span> <span class="p">[</span><span class="s2">"fp8"</span><span class="p">,</span> <span class="kc">None</span><span class="p">],</span>
|
||
<span class="s2">"gemm_allreduce_plugin"</span><span class="p">:</span> <span class="p">[</span><span class="s2">"float16"</span><span class="p">,</span> <span class="s2">"bfloat16"</span><span class="p">,</span> <span class="kc">None</span><span class="p">]</span>
|
||
<span class="p">}</span>
|
||
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">_make_plugin_property</span><span class="p">(</span><span class="n">field_name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">field_type</span><span class="p">:</span> <span class="nb">type</span><span class="p">):</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">bind</span><span class="p">(</span><span class="n">field_name</span><span class="p">):</span>
|
||
<span class="n">storage_name</span> <span class="o">=</span> <span class="sa">f</span><span class="s1">'_</span><span class="si">{</span><span class="n">field_name</span><span class="si">}</span><span class="s1">'</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">prop</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="n">field_value</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">storage_name</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">field_name</span> <span class="o">!=</span> <span class="s1">'dtype'</span> <span class="ow">and</span> <span class="n">field_value</span> <span class="o">==</span> <span class="s1">'auto'</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">dtype</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="n">field_value</span>
|
||
|
||
<span class="nd">@prop</span><span class="o">.</span><span class="n">setter</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">prop</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
|
||
<span class="k">if</span> <span class="n">field_type</span> <span class="ow">is</span> <span class="nb">bool</span><span class="p">:</span>
|
||
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="nb">bool</span><span class="p">),</span> \
|
||
<span class="sa">f</span><span class="s2">"Plugin </span><span class="si">{</span><span class="n">field_name</span><span class="si">}</span><span class="s2"> expects </span><span class="si">{</span><span class="n">field_type</span><span class="si">}</span><span class="s2">, got </span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="n">value</span><span class="p">)</span><span class="si">}</span><span class="s2">"</span>
|
||
<span class="k">elif</span> <span class="n">field_type</span> <span class="ow">in</span> <span class="p">(</span><span class="nb">str</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]):</span>
|
||
<span class="n">plugin_dtype_options</span> <span class="o">=</span> <span class="n">DEFAULT_PLUGIN_DTYPE_OPTIONS</span>
|
||
<span class="k">if</span> <span class="n">field_name</span> <span class="ow">in</span> <span class="n">PLUGIN_DTYPE_OPTIONS_MAP</span><span class="p">:</span>
|
||
<span class="n">plugin_dtype_options</span> <span class="o">=</span> <span class="n">PLUGIN_DTYPE_OPTIONS_MAP</span><span class="p">[</span><span class="n">field_name</span><span class="p">]</span>
|
||
<span class="k">assert</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">plugin_dtype_options</span><span class="p">,</span> \
|
||
<span class="sa">f</span><span class="s2">"Plugin </span><span class="si">{</span><span class="n">field_name</span><span class="si">}</span><span class="s2"> expects values in </span><span class="si">{</span><span class="n">plugin_dtype_options</span><span class="si">}</span><span class="s2">, got </span><span class="si">{</span><span class="n">value</span><span class="si">}</span><span class="s2">"</span>
|
||
<span class="k">if</span> <span class="n">field_name</span> <span class="o">==</span> <span class="s1">'dtype'</span><span class="p">:</span>
|
||
<span class="k">assert</span> <span class="n">value</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'auto'</span><span class="p">,</span> <span class="kc">None</span><span class="p">],</span> \
|
||
<span class="s2">"Plugin dtype cannot be auto or None"</span>
|
||
<span class="nb">setattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">storage_name</span><span class="p">,</span> <span class="n">value</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">"Set </span><span class="si">{</span><span class="n">field_name</span><span class="si">}</span><span class="s2"> to </span><span class="si">{</span><span class="n">value</span><span class="si">}</span><span class="s2">."</span><span class="p">)</span>
|
||
|
||
<span class="k">return</span> <span class="n">prop</span>
|
||
|
||
<span class="k">return</span> <span class="n">bind</span><span class="p">(</span><span class="n">field_name</span><span class="p">)</span>
|
||
|
||
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">PluginConfigMeta</span><span class="p">(</span><span class="nb">type</span><span class="p">):</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="fm">__new__</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">bases</span><span class="p">,</span> <span class="n">attrs</span><span class="p">):</span>
|
||
<span class="k">for</span> <span class="n">storage_name</span><span class="p">,</span> <span class="n">field_type</span> <span class="ow">in</span> <span class="n">attrs</span><span class="p">[</span><span class="s1">'__annotations__'</span><span class="p">]</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
|
||
<span class="k">assert</span> <span class="n">storage_name</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'_'</span><span class="p">)</span>
|
||
<span class="n">field_name</span> <span class="o">=</span> <span class="n">storage_name</span><span class="o">.</span><span class="n">lstrip</span><span class="p">(</span><span class="s1">'_'</span><span class="p">)</span>
|
||
<span class="n">attrs</span><span class="p">[</span><span class="n">field_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">_make_plugin_property</span><span class="p">(</span><span class="n">field_name</span><span class="p">,</span> <span class="n">field_type</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__new__</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">bases</span><span class="p">,</span> <span class="n">attrs</span><span class="p">)</span>
|
||
|
||
|
||
<div class="viewcode-block" id="PluginConfig">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.plugin.html#tensorrt_llm.plugin.PluginConfig">[docs]</a>
|
||
<span class="nd">@dataclass</span><span class="p">(</span><span class="n">slots</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">PluginConfig</span><span class="p">(</span><span class="n">metaclass</span><span class="o">=</span><span class="n">PluginConfigMeta</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""The config that manages plugin-related options.</span>
|
||
|
||
<span class="sd"> There are two option categories:</span>
|
||
<span class="sd"> * Plugin options (typically with xxx_plugin naming). These options can be assigned with:</span>
|
||
<span class="sd"> * "float16"/"bfloat16"/"float32"/"int32", which means the plugin is enabled with the specified precision; (Some plugins only support limited dtype, i.e., gemm_swiglu_plugin and low_latency_gemm_swiglu_plugin only supports fp8 now)</span>
|
||
<span class="sd"> * "auto", which means the plugin is enabled with the precision of `dtype` field (the `dtype` field must be same to model dtype, i.e., the one in PretrainedConfig);</span>
|
||
<span class="sd"> * None, which means the plugin is disabled.</span>
|
||
<span class="sd"> * Other features. These options can be assigned with boolean:</span>
|
||
<span class="sd"> * True, which means the plugin is enabled;</span>
|
||
<span class="sd"> * False, which means the plugin is disabled.</span>
|
||
|
||
<span class="sd"> Note: All the fields should use a prefix "_"; PluginConfigMeta will wrap each field as a property.</span>
|
||
<span class="sd"> This ensures the fields can only be assigned with allowed values.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="n">_dtype</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span><span class="n">default</span><span class="o">=</span><span class="s2">"float16"</span><span class="p">,</span> <span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||
|
||
<span class="c1"># Plugins</span>
|
||
<span class="n">_bert_attention_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="s2">"auto"</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"The plugin that uses efficient kernels and enables an in-place update of the KV cache for attention layer of BERT-like encoder models."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_gpt_attention_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="s2">"auto"</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"The plugin that uses efficient kernels and enables an in-place update of the KV cache for attention layer of GPT-like decoder models."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_gemm_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"The GEMM plugin that utilizes NVIDIA cuBLASLt to perform GEMM operations. "</span>
|
||
<span class="s2">"Note: it's only affective for non-quantized gemm operations (except FP8)."</span>
|
||
<span class="s2">"Note: For FP8, it also requires same calibration in checkpoint."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_explicitly_disable_gemm_plugin</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span>
|
||
<span class="n">_gemm_swiglu_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"The GEMM + SwiGLU fusion in Gated-MLP combines two Matmul operations and "</span>
|
||
<span class="s2">"one SwiGLU operation into a single kernel. Currently this is only supported for FP8 precision on Hopper."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_fp8_rowwise_gemm_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"The quantized GEMM for fp8, which uses per token dynamic scales for "</span>
|
||
<span class="s2">"activation and per channel static scales for weights."</span>
|
||
<span class="s2">"Note: It also requires same calibration in checkpoint."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_qserve_gemm_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"The quantized GEMM from [QServe](https://arxiv.org/abs/2405.04532), "</span>
|
||
<span class="s2">"which employs 4-bit quantization for weights and 8-bit quantization for activations."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_identity_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"The identity plugin simply copies inputs to outputs, it's used mostly for debugging purpose."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_nccl_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="s2">"auto"</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"The NCCL plugin wraps NCCL operators to support multi-GPU and even multi-nodes."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_lora_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span><span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span><span class="s2">"help"</span><span class="p">:</span> <span class="s2">"Enable LoRA."</span><span class="p">})</span>
|
||
<span class="n">_dora_plugin</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span><span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span><span class="s2">"help"</span><span class="p">:</span> <span class="s2">"Enable DoRA."</span><span class="p">})</span>
|
||
<span class="n">_weight_only_groupwise_quant_matmul_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable weight-only groupwise quantization matmul operators."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_weight_only_quant_matmul_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span><span class="s2">"help"</span><span class="p">:</span> <span class="s2">"Enable weight-only quantization matmul operators."</span><span class="p">})</span>
|
||
<span class="n">_smooth_quant_plugins</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span> <span class="s2">"Enable a group of plugins to support smooth quantization."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_smooth_quant_gemm_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable plugin that supports smooth quantization gemm kernels."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_layernorm_quantization_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable plugin that supports layernorm quantization kernels."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_rmsnorm_quantization_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span> <span class="s2">"Enable plugin that supports rmsnorm quantization kernels."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_quantize_per_token_plugin</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span> <span class="s2">"Enable plugin that supports per-token quantization."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_quantize_tensor_plugin</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span> <span class="s2">"Enable plugin that supports per-tensor quantization."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_moe_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="s2">"auto"</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable some customized kernels to speed up the MoE layer of MoE models."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_mamba_conv1d_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="s2">"auto"</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable customized kernels to speed up conv1d operator for Mamba."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_low_latency_gemm_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"The GEMM plugin that optimized specially for low latency scenarios."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_low_latency_gemm_swiglu_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"The GEMM + SwiGLU fusion plugin that optimized specially for low latency scenarios."</span>
|
||
<span class="p">})</span>
|
||
|
||
<span class="n">_gemm_allreduce_plugin</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span><span class="s2">"help"</span><span class="p">:</span> <span class="s2">"The GEMM + AllReduce kernel fusion plugin."</span><span class="p">})</span>
|
||
|
||
<span class="c1"># Features</span>
|
||
<span class="n">_context_fmha</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable the fused multi-head attention during the context phase, "</span>
|
||
<span class="s2">"will trigger a kernel that performs the MHA/MQA/GQA block using a single kernel."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_bert_context_fmha_fp32_acc</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable the FP32 accumulator for context FMHA in the bert_attention_plugin. "</span>
|
||
<span class="s2">"If disabled, FP16 is used, better performance but potentially worse accuracy is expected."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_paged_kv_cache</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable paged KV cache, which helps manage memory for the KV cache more efficiently, "</span>
|
||
<span class="s2">"and usually leads to an increase in the batch size and an improved efficiency."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_remove_input_padding</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Pack different tokens together, which reduces both the amount of computations and memory consumption."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_norm_quant_fusion</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Fuse the LayerNorm and quantization kernels into a single kernel, "</span>
|
||
<span class="s2">"resulting in improved end-to-end performance."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_reduce_fusion</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Fuse the ResidualAdd and LayerNorm kernels after AllReduce into a single kernel, "</span>
|
||
<span class="s2">"resulting in improved end-to-end performance."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_user_buffer</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Eliminate extra copies from the local buffer to the shared buffer "</span>
|
||
<span class="s2">"in the communication kernel, leading to improved end-to-end performance. "</span>
|
||
<span class="s2">"This feature must be enabled with `--reduce_fusion enable` and "</span>
|
||
<span class="s2">"is currently only supported for the FP8 LLAMA model."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_tokens_per_block</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Define how many tokens are contained in each paged kv cache block."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_use_paged_context_fmha</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Allow advanced features like KV cache reuse and chunked context."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_use_fp8_context_fmha</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"When FP8 quantization is activated, the attention can be further accelerated by enabling FP8 Context FMHA"</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_fuse_fp4_quant</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span> <span class="s2">"Whether to fuse FP4 quantization into attention kernel."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_multiple_profiles</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enables multiple TensorRT optimization profiles in the built engines, "</span>
|
||
<span class="s2">"will benefits the performance especially when GEMM plugin is disabled, "</span>
|
||
<span class="s2">"because more optimization profiles help TensorRT have more chances to select better kernels. "</span>
|
||
<span class="s2">"Note: This feature increases engine build time but no other adverse effects are expected."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_paged_state</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable paged state, which helps manage memory for the RNN state more efficiently."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_streamingllm</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable [StreamingLLM](https://arxiv.org/abs/2309.17453), which uses a window attention to perform efficient and stable LLM on long texts."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_manage_weights</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable TensorRT LLM managed weights to speed up engine building process."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_use_fused_mlp</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable horizontal fusion in Gated-MLP that combines two Matmul "</span>
|
||
<span class="s2">"operations into a single one followed by a separate SwiGLU kernel."</span>
|
||
<span class="p">})</span>
|
||
<span class="n">_pp_reduce_scatter</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="n">field</span><span class="p">(</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">init</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">metadata</span><span class="o">=</span><span class="p">{</span>
|
||
<span class="s2">"help"</span><span class="p">:</span>
|
||
<span class="s2">"Enable a pipeline parallelism optimization with "</span>
|
||
<span class="s2">"ReduceScatter + AllGather targeting large MoE models."</span>
|
||
<span class="p">})</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">update_from_dict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">config</span><span class="p">:</span> <span class="nb">dict</span><span class="p">):</span>
|
||
<span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">config</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span>
|
||
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
|
||
<span class="n">value_to_be_update</span> <span class="o">=</span> <span class="n">config</span><span class="p">[</span><span class="n">name</span><span class="p">]</span>
|
||
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">),</span>
|
||
<span class="nb">bool</span><span class="p">)</span> <span class="ow">or</span> <span class="n">name</span> <span class="o">==</span> <span class="s1">'paged_kv_cache'</span><span class="p">:</span>
|
||
<span class="k">if</span> <span class="n">value_to_be_update</span> <span class="o">==</span> <span class="s2">"enable"</span><span class="p">:</span>
|
||
<span class="n">value_to_be_update</span> <span class="o">=</span> <span class="kc">True</span>
|
||
<span class="k">elif</span> <span class="n">value_to_be_update</span> <span class="o">==</span> <span class="s2">"disable"</span><span class="p">:</span>
|
||
<span class="n">value_to_be_update</span> <span class="o">=</span> <span class="kc">False</span>
|
||
<span class="k">elif</span> <span class="n">value_to_be_update</span> <span class="o">==</span> <span class="s2">"disable"</span><span class="p">:</span>
|
||
<span class="n">value_to_be_update</span> <span class="o">=</span> <span class="kc">None</span>
|
||
<span class="nb">setattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">value_to_be_update</span><span class="p">)</span>
|
||
|
||
<span class="nd">@classmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">from_dict</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">config</span><span class="p">:</span> <span class="nb">dict</span><span class="p">):</span>
|
||
<span class="n">plugin_config</span> <span class="o">=</span> <span class="bp">cls</span><span class="p">()</span>
|
||
<span class="n">plugin_config</span><span class="o">.</span><span class="n">update_from_dict</span><span class="p">(</span><span class="n">config</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">plugin_config</span>
|
||
|
||
<span class="nd">@classmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">from_arguments</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">args</span><span class="p">:</span> <span class="n">argparse</span><span class="o">.</span><span class="n">Namespace</span><span class="p">):</span>
|
||
<span class="n">args</span> <span class="o">=</span> <span class="nb">vars</span><span class="p">(</span><span class="n">args</span><span class="p">)</span>
|
||
<span class="n">obj</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">from_dict</span><span class="p">(</span><span class="n">args</span><span class="p">)</span>
|
||
|
||
<span class="c1"># We want to know if the user explicitly disabled the gemm_plugin</span>
|
||
<span class="c1"># because nvfp4 gemm uses plugin by default currently</span>
|
||
<span class="k">if</span> <span class="s1">'gemm_plugin'</span> <span class="ow">in</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">args</span><span class="p">[</span><span class="s1">'gemm_plugin'</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'disable'</span><span class="p">:</span>
|
||
<span class="n">obj</span><span class="o">.</span><span class="n">_explicitly_disable_gemm_plugin</span> <span class="o">=</span> <span class="kc">True</span>
|
||
|
||
<span class="k">return</span> <span class="n">obj</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">to_dict</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="n">config</span> <span class="o">=</span> <span class="n">asdict</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span>
|
||
<span class="c1"># Remove prefix "_" of the storage name</span>
|
||
<span class="n">config</span> <span class="o">=</span> <span class="p">{</span><span class="n">key</span><span class="o">.</span><span class="n">lstrip</span><span class="p">(</span><span class="s1">'_'</span><span class="p">):</span> <span class="n">value</span> <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">config</span><span class="o">.</span><span class="n">items</span><span class="p">()}</span>
|
||
<span class="k">return</span> <span class="n">config</span>
|
||
|
||
<div class="viewcode-block" id="PluginConfig.to_legacy_setting">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.plugin.html#tensorrt_llm.plugin.PluginConfig.to_legacy_setting">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">to_legacy_setting</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">'''Legacy setting means that all of the plugins and features are</span>
|
||
<span class="sd"> disabled, this is needed for the legacy `build.py` script, which will be</span>
|
||
<span class="sd"> migrated to the centralized building script `tensorrt_llm/commands/build.py`.</span>
|
||
|
||
<span class="sd"> After the migration is done, this function may or may not be deleted.</span>
|
||
<span class="sd"> '''</span>
|
||
<span class="k">for</span> <span class="n">field</span> <span class="ow">in</span> <span class="n">fields</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="c1"># Remove prefix "_" of the storage name</span>
|
||
<span class="n">field_name</span> <span class="o">=</span> <span class="n">field</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">lstrip</span><span class="p">(</span><span class="s1">'_'</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">field_name</span> <span class="o">==</span> <span class="s1">'dtype'</span><span class="p">:</span>
|
||
<span class="k">continue</span>
|
||
<span class="k">if</span> <span class="n">field</span><span class="o">.</span><span class="n">type</span> <span class="ow">in</span> <span class="p">(</span><span class="nb">str</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]):</span>
|
||
<span class="nb">setattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">field_name</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">field</span><span class="o">.</span><span class="n">type</span> <span class="o">==</span> <span class="nb">bool</span> <span class="ow">or</span> <span class="n">field_name</span> <span class="o">==</span> <span class="s1">'paged_kv_cache'</span><span class="p">:</span>
|
||
<span class="nb">setattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">field_name</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span></div>
|
||
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">validate</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="n">unsupported_plugins</span> <span class="o">=</span> <span class="p">{</span>
|
||
<span class="c1"># bert_attention_plugin is handled within BertAttention</span>
|
||
<span class="mi">100</span><span class="p">:</span> <span class="p">[</span>
|
||
<span class="s1">'gemm_swiglu_plugin'</span><span class="p">,</span> <span class="s1">'fp8_rowwise_gemm_plugin'</span><span class="p">,</span>
|
||
<span class="s1">'low_latency_gemm_plugin'</span><span class="p">,</span> <span class="s1">'low_latency_gemm_swiglu_plugin'</span><span class="p">,</span>
|
||
<span class="s1">'bert_context_fmha_fp32_acc'</span>
|
||
<span class="p">]</span>
|
||
<span class="p">}</span>
|
||
<span class="n">sm</span> <span class="o">=</span> <span class="n">get_sm_version</span><span class="p">()</span>
|
||
<span class="k">if</span> <span class="n">sm</span> <span class="ow">in</span> <span class="n">unsupported_plugins</span><span class="p">:</span>
|
||
<span class="k">for</span> <span class="n">plugin</span> <span class="ow">in</span> <span class="n">unsupported_plugins</span><span class="p">[</span><span class="n">sm</span><span class="p">]:</span>
|
||
<span class="n">val</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">plugin</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">val</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">val</span> <span class="o">!=</span> <span class="kc">False</span><span class="p">:</span>
|
||
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">plugin</span><span class="si">}</span><span class="s2">=</span><span class="si">{</span><span class="n">val</span><span class="si">}</span><span class="s2"> is not supported on SM </span><span class="si">{</span><span class="n">sm</span><span class="si">}</span><span class="s2">."</span><span class="p">)</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">context_fmha_type</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">bert_context_fmha_fp32_acc</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="n">ContextFMHAType</span><span class="o">.</span><span class="n">enabled_with_fp32_acc</span>
|
||
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">context_fmha</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="n">ContextFMHAType</span><span class="o">.</span><span class="n">enabled</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="n">ContextFMHAType</span><span class="o">.</span><span class="n">disabled</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">is_context_fmha_enabled</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">context_fmha_type</span> <span class="o">!=</span> <span class="n">ContextFMHAType</span><span class="o">.</span><span class="n">disabled</span>
|
||
|
||
<span class="nd">@context_fmha_type</span><span class="o">.</span><span class="n">setter</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">context_fmha_type</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
|
||
<span class="k">if</span> <span class="n">value</span> <span class="o">==</span> <span class="n">ContextFMHAType</span><span class="o">.</span><span class="n">disabled</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">context_fmha</span> <span class="o">=</span> <span class="kc">False</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">bert_context_fmha_fp32_acc</span> <span class="o">=</span> <span class="kc">False</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">context_fmha</span> <span class="o">=</span> <span class="kc">True</span>
|
||
<span class="k">if</span> <span class="n">value</span> <span class="o">==</span> <span class="n">ContextFMHAType</span><span class="o">.</span><span class="n">enabled</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">bert_context_fmha_fp32_acc</span> <span class="o">=</span> <span class="kc">False</span>
|
||
<span class="k">elif</span> <span class="n">value</span> <span class="o">==</span> <span class="n">ContextFMHAType</span><span class="o">.</span><span class="n">enabled_with_fp32_acc</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">bert_context_fmha_fp32_acc</span> <span class="o">=</span> <span class="kc">True</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_smooth_quant_plugins</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dtype</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"auto"</span><span class="p">):</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">smooth_quant_gemm_plugin</span> <span class="o">=</span> <span class="n">dtype</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">rmsnorm_quantization_plugin</span> <span class="o">=</span> <span class="n">dtype</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">layernorm_quantization_plugin</span> <span class="o">=</span> <span class="n">dtype</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">quantize_per_token_plugin</span> <span class="o">=</span> <span class="kc">True</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">quantize_tensor_plugin</span> <span class="o">=</span> <span class="kc">True</span>
|
||
<span class="k">return</span> <span class="bp">self</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_qserve_plugins</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dtype</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"auto"</span><span class="p">):</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">qserve_gemm_plugin</span> <span class="o">=</span> <span class="n">dtype</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">rmsnorm_quantization_plugin</span> <span class="o">=</span> <span class="n">dtype</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">quantize_per_token_plugin</span> <span class="o">=</span> <span class="kc">True</span>
|
||
<span class="k">return</span> <span class="bp">self</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_fp8_rowwise_quant_plugins</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dtype</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"auto"</span><span class="p">):</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">fp8_rowwise_gemm_plugin</span> <span class="o">=</span> <span class="n">dtype</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">rmsnorm_quantization_plugin</span> <span class="o">=</span> <span class="n">dtype</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">layernorm_quantization_plugin</span> <span class="o">=</span> <span class="n">dtype</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">quantize_per_token_plugin</span> <span class="o">=</span> <span class="kc">True</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">quantize_tensor_plugin</span> <span class="o">=</span> <span class="kc">True</span>
|
||
<span class="k">return</span> <span class="bp">self</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_context_fmha</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context_fmha_type</span><span class="o">=</span><span class="n">ContextFMHAType</span><span class="o">.</span><span class="n">enabled</span><span class="p">):</span>
|
||
<span class="k">assert</span> <span class="nb">type</span><span class="p">(</span><span class="n">context_fmha_type</span><span class="p">)</span> <span class="o">==</span> <span class="n">ContextFMHAType</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">context_fmha_type</span> <span class="o">=</span> <span class="n">context_fmha_type</span>
|
||
<span class="k">return</span> <span class="bp">self</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">enable_paged_kv_cache</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tokens_per_block</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">32</span><span class="p">):</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">paged_kv_cache</span> <span class="o">=</span> <span class="kc">True</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">tokens_per_block</span> <span class="o">=</span> <span class="n">tokens_per_block</span>
|
||
<span class="k">return</span> <span class="bp">self</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_nccl_plugin</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dtype</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"auto"</span><span class="p">):</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">nccl_plugin</span> <span class="o">=</span> <span class="n">dtype</span>
|
||
<span class="n">init_all_reduce_helper</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">set_lora_plugin</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dtype</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">lora_plugin</span> <span class="o">=</span> <span class="n">dtype</span>
|
||
<span class="k">return</span> <span class="bp">self</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_dora_plugin</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">enable</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">):</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">dora_plugin</span> <span class="o">=</span> <span class="n">enable</span>
|
||
<span class="k">return</span> <span class="bp">self</span></div>
|
||
|
||
|
||
|
||
<span class="c1"># Only plugin configs in this list will be exposed as `trtllm-build` arguments,</span>
|
||
<span class="c1"># others are automatically enabled when needed, no need for users to control.</span>
|
||
<span class="n">cli_plugin_args</span> <span class="o">=</span> <span class="p">[</span>
|
||
<span class="c1"># Plugins</span>
|
||
<span class="s2">"bert_attention_plugin"</span><span class="p">,</span>
|
||
<span class="s2">"gpt_attention_plugin"</span><span class="p">,</span>
|
||
<span class="s2">"gemm_plugin"</span><span class="p">,</span>
|
||
<span class="s2">"gemm_swiglu_plugin"</span><span class="p">,</span>
|
||
<span class="s2">"fp8_rowwise_gemm_plugin"</span><span class="p">,</span>
|
||
<span class="s2">"lora_plugin"</span><span class="p">,</span>
|
||
<span class="s2">"dora_plugin"</span><span class="p">,</span>
|
||
<span class="s2">"moe_plugin"</span><span class="p">,</span>
|
||
<span class="s2">"mamba_conv1d_plugin"</span><span class="p">,</span>
|
||
<span class="s2">"nccl_plugin"</span><span class="p">,</span>
|
||
<span class="s2">"low_latency_gemm_plugin"</span><span class="p">,</span>
|
||
<span class="s2">"low_latency_gemm_swiglu_plugin"</span><span class="p">,</span>
|
||
<span class="s2">"gemm_allreduce_plugin"</span><span class="p">,</span>
|
||
|
||
<span class="c1"># Features</span>
|
||
<span class="s2">"context_fmha"</span><span class="p">,</span>
|
||
<span class="s2">"bert_context_fmha_fp32_acc"</span><span class="p">,</span>
|
||
<span class="s2">"remove_input_padding"</span><span class="p">,</span>
|
||
<span class="s2">"tokens_per_block"</span><span class="p">,</span>
|
||
<span class="s2">"use_paged_context_fmha"</span><span class="p">,</span>
|
||
<span class="s2">"use_fp8_context_fmha"</span><span class="p">,</span>
|
||
<span class="s2">"fuse_fp4_quant"</span><span class="p">,</span>
|
||
<span class="s2">"multiple_profiles"</span><span class="p">,</span>
|
||
<span class="s2">"paged_state"</span><span class="p">,</span>
|
||
<span class="s2">"streamingllm"</span><span class="p">,</span>
|
||
<span class="s2">"norm_quant_fusion"</span><span class="p">,</span>
|
||
<span class="s2">"reduce_fusion"</span><span class="p">,</span>
|
||
<span class="s2">"user_buffer"</span><span class="p">,</span>
|
||
<span class="s2">"use_fused_mlp"</span><span class="p">,</span>
|
||
<span class="s2">"pp_reduce_scatter"</span><span class="p">,</span>
|
||
<span class="p">]</span>
|
||
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">add_plugin_argument</span><span class="p">(</span><span class="n">parser</span><span class="p">:</span> <span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentParser</span><span class="p">):</span>
|
||
<span class="n">plugin_config</span> <span class="o">=</span> <span class="n">PluginConfig</span><span class="p">()</span>
|
||
<span class="k">for</span> <span class="n">field</span> <span class="ow">in</span> <span class="n">fields</span><span class="p">(</span><span class="n">plugin_config</span><span class="p">):</span>
|
||
<span class="c1"># Remove prefix "_" of the storage name</span>
|
||
<span class="n">field_name</span> <span class="o">=</span> <span class="n">field</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">lstrip</span><span class="p">(</span><span class="s1">'_'</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">field_name</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">cli_plugin_args</span><span class="p">:</span>
|
||
<span class="k">continue</span>
|
||
<span class="k">if</span> <span class="n">field</span><span class="o">.</span><span class="n">metadata</span> <span class="ow">and</span> <span class="s2">"help"</span> <span class="ow">in</span> <span class="n">field</span><span class="o">.</span><span class="n">metadata</span><span class="p">:</span>
|
||
<span class="n">help_message</span> <span class="o">=</span> <span class="n">field</span><span class="o">.</span><span class="n">metadata</span><span class="p">[</span><span class="s2">"help"</span><span class="p">]</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="k">raise</span> <span class="ne">AttributeError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Please add help message for </span><span class="si">{</span><span class="n">field_name</span><span class="si">}</span><span class="s2">."</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">field</span><span class="o">.</span><span class="n">type</span> <span class="ow">in</span> <span class="p">(</span><span class="nb">str</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]):</span>
|
||
<span class="n">plugin_dtype_options</span> <span class="o">=</span> <span class="n">DEFAULT_PLUGIN_DTYPE_OPTIONS</span>
|
||
<span class="k">if</span> <span class="n">field_name</span> <span class="ow">in</span> <span class="n">PLUGIN_DTYPE_OPTIONS_MAP</span><span class="p">:</span>
|
||
<span class="n">plugin_dtype_options</span> <span class="o">=</span> <span class="n">PLUGIN_DTYPE_OPTIONS_MAP</span><span class="p">[</span><span class="n">field_name</span><span class="p">]</span>
|
||
<span class="k">if</span> <span class="n">field_name</span> <span class="o">==</span> <span class="s2">"gemm_plugin"</span><span class="p">:</span>
|
||
<span class="n">default</span> <span class="o">=</span> <span class="n">field</span><span class="o">.</span><span class="n">default</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">default</span> <span class="o">=</span> <span class="n">field</span><span class="o">.</span><span class="n">default</span> <span class="k">if</span> <span class="n">field</span><span class="o">.</span><span class="n">default</span> <span class="k">else</span> <span class="s2">"disable"</span>
|
||
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
|
||
<span class="s2">"--"</span> <span class="o">+</span> <span class="n">field_name</span><span class="p">,</span>
|
||
<span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="n">default</span><span class="p">,</span>
|
||
<span class="n">choices</span><span class="o">=</span><span class="p">[</span><span class="n">x</span> <span class="k">if</span> <span class="n">x</span> <span class="k">else</span> <span class="s2">"disable"</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">plugin_dtype_options</span><span class="p">],</span>
|
||
<span class="n">help</span><span class="o">=</span><span class="n">help_message</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">field</span><span class="o">.</span><span class="n">type</span> <span class="o">==</span> <span class="nb">bool</span><span class="p">:</span>
|
||
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
|
||
<span class="s2">"--"</span> <span class="o">+</span> <span class="n">field_name</span><span class="p">,</span>
|
||
<span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="s2">"enable"</span> <span class="k">if</span> <span class="n">field</span><span class="o">.</span><span class="n">default</span> <span class="k">else</span> <span class="s2">"disable"</span><span class="p">,</span>
|
||
<span class="n">choices</span><span class="o">=</span><span class="p">[</span><span class="s2">"enable"</span><span class="p">,</span> <span class="s2">"disable"</span><span class="p">],</span>
|
||
<span class="n">help</span><span class="o">=</span><span class="n">help_message</span><span class="p">)</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"--"</span> <span class="o">+</span> <span class="n">field_name</span><span class="p">,</span>
|
||
<span class="nb">type</span><span class="o">=</span><span class="n">field</span><span class="o">.</span><span class="n">type</span><span class="p">,</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="n">field</span><span class="o">.</span><span class="n">default</span><span class="p">,</span>
|
||
<span class="n">help</span><span class="o">=</span><span class="n">help_message</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">parser</span>
|
||
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">force_all_reduce_deterministic</span><span class="p">():</span>
|
||
<span class="k">return</span> <span class="n">os</span><span class="o">.</span><span class="n">getenv</span><span class="p">(</span><span class="s2">"FORCE_DETERMINISTIC"</span><span class="p">,</span> <span class="s2">"0"</span><span class="p">)</span> <span class="o">==</span> <span class="s2">"1"</span> <span class="ow">or</span> <span class="n">os</span><span class="o">.</span><span class="n">getenv</span><span class="p">(</span>
|
||
<span class="s2">"FORCE_ALL_REDUCE_DETERMINISTIC"</span><span class="p">,</span> <span class="s2">"0"</span><span class="p">)</span> <span class="o">==</span> <span class="s2">"1"</span>
|
||
|
||
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">CustomAllReduceHelper</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""</span>
|
||
<span class="sd"> Globally visible class to help usage of custom_all_reduce plugin.</span>
|
||
<span class="sd"> Provides the following utilities:</span>
|
||
|
||
<span class="sd"> workspace: Tensor</span>
|
||
<span class="sd"> When using CUSTOM or AUTO mode, a tensor containing pointers to memory</span>
|
||
<span class="sd"> visible to all GPUs. It should be 3 pointers per TP rank -</span>
|
||
<span class="sd"> ptr to data buffer, ptr to barriers in, ptr to barriers out.</span>
|
||
<span class="sd"> It must be initialized using IpcMemory class.</span>
|
||
|
||
<span class="sd"> Usage:</span>
|
||
<span class="sd"> - Set custom_all_reduce_helper.workspace with the required tensor.</span>
|
||
<span class="sd"> Then, each instance of allreduce will reference that tensor automatically.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="n">POINTERS_PER_RANK</span> <span class="o">=</span> <span class="mi">7</span>
|
||
<span class="n">POINTERS_OF_COUNTER</span> <span class="o">=</span> <span class="mi">3</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="kc">None</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">workspace</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Tensor</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_workspace_tensor</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
|
||
<span class="n">mapping</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">,</span>
|
||
<span class="n">num_profiles</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">..functional</span><span class="w"> </span><span class="kn">import</span> <span class="n">Tensor</span>
|
||
<span class="n">workspace_size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">POINTERS_PER_RANK</span> <span class="o">*</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">POINTERS_OF_COUNTER</span>
|
||
|
||
<span class="n">dim_range</span> <span class="o">=</span> <span class="kc">None</span>
|
||
<span class="k">if</span> <span class="n">num_profiles</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="n">dim_range</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">([(</span><span class="s1">'all_reduce_size'</span><span class="p">,</span>
|
||
<span class="p">[</span><span class="n">workspace_size</span><span class="p">]</span> <span class="o">*</span> <span class="n">num_profiles</span><span class="p">)])</span>
|
||
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">workspace</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
|
||
<span class="n">name</span><span class="o">=</span><span class="s1">'all_reduce_workspace'</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int64</span><span class="p">,</span>
|
||
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="n">workspace_size</span><span class="p">],</span>
|
||
<span class="n">dim_range</span><span class="o">=</span><span class="n">dim_range</span><span class="p">,</span>
|
||
<span class="p">)</span>
|
||
|
||
<span class="nd">@staticmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">max_workspace_size_auto</span><span class="p">(</span><span class="n">tp_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||
<span class="n">support_deterministic</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span>
|
||
<span class="k">if</span> <span class="n">force_all_reduce_deterministic</span><span class="p">()</span> <span class="ow">and</span> <span class="n">support_deterministic</span><span class="p">:</span>
|
||
<span class="n">workspace_size</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">getenv</span><span class="p">(</span><span class="s2">"FORCE_ALLREDUCE_KERNEL_WORKSPACE_SIZE"</span><span class="p">,</span>
|
||
<span class="s2">"1000000000"</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="nb">int</span><span class="p">(</span><span class="n">workspace_size</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">tp_size</span> <span class="o"><=</span> <span class="mi">2</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="mi">16_000_000</span>
|
||
<span class="k">return</span> <span class="mi">8_000_000</span>
|
||
|
||
<span class="nd">@staticmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">max_workspace_size_lowprecision</span><span class="p">(</span><span class="n">tp_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="n">max_workspace_size_lowprecision</span><span class="p">(</span><span class="n">tp_size</span><span class="p">)</span>
|
||
|
||
<span class="nd">@staticmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">initialize_lowprecision_buffers</span><span class="p">(</span><span class="n">workspace</span><span class="p">:</span> <span class="s2">"torch.tensor"</span><span class="p">,</span>
|
||
<span class="n">tp_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
|
||
<span class="k">return</span> <span class="n">torch</span><span class="o">.</span><span class="n">ops</span><span class="o">.</span><span class="n">trtllm</span><span class="o">.</span><span class="n">initialize_static_lowprecision_buffers</span><span class="p">(</span>
|
||
<span class="n">workspace</span><span class="p">,</span> <span class="n">tp_size</span><span class="p">)</span>
|
||
|
||
<span class="nd">@staticmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">allocate_workspace</span><span class="p">(</span><span class="n">mapping</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">,</span>
|
||
<span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">IpcMemory</span><span class="p">],</span> <span class="s2">"torch.tensor"</span><span class="p">]:</span>
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
|
||
|
||
<span class="c1"># Force pull mode and disable lamport when force deterministic is enabled, for reducing device memory usage.</span>
|
||
<span class="n">force_deterministic</span> <span class="o">=</span> <span class="n">force_all_reduce_deterministic</span><span class="p">()</span>
|
||
<span class="n">is_p2p_supported</span> <span class="o">=</span> <span class="n">can_access_peer</span><span class="p">(</span><span class="n">mapping</span><span class="p">)</span>
|
||
<span class="n">ipc_buffers_size</span> <span class="o">=</span> <span class="n">size</span> <span class="k">if</span> <span class="n">force_deterministic</span> <span class="k">else</span> <span class="n">size</span> <span class="o">*</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span>
|
||
<span class="n">ipc_buffers_ping</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span><span class="n">mapping</span><span class="p">,</span> <span class="n">ipc_buffers_size</span><span class="p">,</span>
|
||
<span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="n">ipc_buffers_pong</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span><span class="n">mapping</span><span class="p">,</span> <span class="n">ipc_buffers_size</span><span class="p">,</span>
|
||
<span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="n">ipc_barriers_in</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span>
|
||
<span class="n">mapping</span><span class="p">,</span> <span class="n">IpcMemory</span><span class="o">.</span><span class="n">IPC_BARRIERS_SIZE_PER_GPU</span> <span class="o">*</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">*</span> <span class="mi">2</span> <span class="o">*</span>
|
||
<span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">,</span> <span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="n">ipc_barriers_out</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span>
|
||
<span class="n">mapping</span><span class="p">,</span> <span class="n">IpcMemory</span><span class="o">.</span><span class="n">IPC_BARRIERS_SIZE_PER_GPU</span> <span class="o">*</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">*</span> <span class="mi">2</span> <span class="o">*</span>
|
||
<span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">,</span> <span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="n">lamport_buffers_size</span> <span class="o">=</span> <span class="mi">1</span> <span class="k">if</span> <span class="n">force_deterministic</span> <span class="k">else</span> <span class="n">size</span> <span class="o">*</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span>
|
||
<span class="n">lamport_buffers_0</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span><span class="n">mapping</span><span class="p">,</span> <span class="n">lamport_buffers_size</span><span class="p">,</span>
|
||
<span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="n">lamport_buffers_1</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span><span class="n">mapping</span><span class="p">,</span> <span class="n">lamport_buffers_size</span><span class="p">,</span>
|
||
<span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="n">lamport_buffers_2</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span><span class="n">mapping</span><span class="p">,</span> <span class="n">lamport_buffers_size</span><span class="p">,</span>
|
||
<span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="c1"># TODO: it seems we may need to initialize lamport buffers for all tp groups</span>
|
||
<span class="c1"># just like its cpp counterpart (AllReduceBuffers::AllReduceBuffers()) does.</span>
|
||
<span class="k">if</span> <span class="n">is_p2p_supported</span><span class="p">:</span>
|
||
<span class="n">lamport_initialize_all</span><span class="p">(</span>
|
||
<span class="n">lamport_buffers_0</span><span class="o">.</span><span class="n">local_ptr</span><span class="p">,</span>
|
||
<span class="n">lamport_buffers_1</span><span class="o">.</span><span class="n">local_ptr</span><span class="p">,</span>
|
||
<span class="n">lamport_buffers_2</span><span class="o">.</span><span class="n">local_ptr</span><span class="p">,</span>
|
||
<span class="n">lamport_buffers_size</span><span class="p">,</span>
|
||
<span class="p">)</span>
|
||
<span class="n">buffers</span> <span class="o">=</span> <span class="p">[</span>
|
||
<span class="n">ipc_buffers_ping</span><span class="p">,</span>
|
||
<span class="n">ipc_buffers_pong</span><span class="p">,</span>
|
||
<span class="n">ipc_barriers_in</span><span class="p">,</span>
|
||
<span class="n">ipc_barriers_out</span><span class="p">,</span>
|
||
<span class="n">lamport_buffers_0</span><span class="p">,</span>
|
||
<span class="n">lamport_buffers_1</span><span class="p">,</span>
|
||
<span class="n">lamport_buffers_2</span><span class="p">,</span>
|
||
<span class="c1"># Start from 1 since 0 represents released state for barrier at the beginning of the all_reduce.</span>
|
||
<span class="c1"># The last element is the barrier flag counter.</span>
|
||
<span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">int64</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">)</span>
|
||
<span class="p">]</span>
|
||
|
||
<span class="k">return</span> <span class="n">buffers</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">ipc_buffers_ping</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span> <span class="n">ipc_buffers_pong</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span>
|
||
<span class="n">ipc_barriers_in</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span> <span class="n">ipc_barriers_out</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span>
|
||
<span class="n">lamport_buffers_0</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span> <span class="n">lamport_buffers_1</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span>
|
||
<span class="n">lamport_buffers_2</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span> <span class="p">[</span><span class="n">buffers</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">data_ptr</span><span class="p">()]</span> <span class="o">+</span>
|
||
<span class="p">[</span><span class="n">buffers</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">1</span><span class="p">:]</span><span class="o">.</span><span class="n">data_ptr</span><span class="p">()]</span> <span class="o">+</span> <span class="p">[</span><span class="n">buffers</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">2</span><span class="p">:]</span><span class="o">.</span><span class="n">data_ptr</span><span class="p">()],</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">int64</span><span class="p">,</span>
|
||
<span class="n">device</span><span class="o">=</span><span class="s2">"cpu"</span><span class="p">)</span>
|
||
|
||
<span class="nd">@staticmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">allocate_lowprecision_workspace</span><span class="p">(</span>
|
||
<span class="n">mapping</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">,</span>
|
||
<span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">IpcMemory</span><span class="p">],</span> <span class="s2">"torch.tensor"</span><span class="p">]:</span>
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
|
||
|
||
<span class="c1"># Force pull mode and disable lamport when force deterministic is enabled, for reducing device memory usage.</span>
|
||
<span class="n">is_p2p_supported</span> <span class="o">=</span> <span class="n">can_access_peer</span><span class="p">(</span><span class="n">mapping</span><span class="p">)</span>
|
||
<span class="n">ipc_buffers_size</span> <span class="o">=</span> <span class="n">size</span>
|
||
<span class="n">ipc_buffers_ping</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span><span class="n">mapping</span><span class="p">,</span> <span class="n">ipc_buffers_size</span><span class="p">,</span>
|
||
<span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="n">ipc_buffers_pong</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span><span class="n">mapping</span><span class="p">,</span> <span class="n">ipc_buffers_size</span><span class="p">,</span>
|
||
<span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="n">ipc_barriers_in</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span>
|
||
<span class="n">mapping</span><span class="p">,</span> <span class="n">IpcMemory</span><span class="o">.</span><span class="n">IPC_BARRIERS_SIZE_PER_GPU</span> <span class="o">*</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">*</span> <span class="mi">2</span><span class="p">,</span>
|
||
<span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="n">ipc_barriers_out</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span>
|
||
<span class="n">mapping</span><span class="p">,</span> <span class="n">IpcMemory</span><span class="o">.</span><span class="n">IPC_BARRIERS_SIZE_PER_GPU</span> <span class="o">*</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">*</span> <span class="mi">2</span><span class="p">,</span>
|
||
<span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="n">buffers</span> <span class="o">=</span> <span class="p">[</span>
|
||
<span class="n">ipc_buffers_ping</span><span class="p">,</span> <span class="n">ipc_buffers_pong</span><span class="p">,</span> <span class="n">ipc_barriers_in</span><span class="p">,</span>
|
||
<span class="n">ipc_barriers_out</span>
|
||
<span class="p">]</span>
|
||
|
||
<span class="k">return</span> <span class="n">buffers</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">ipc_buffers_ping</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span> <span class="n">ipc_buffers_pong</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span>
|
||
<span class="n">ipc_barriers_in</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span> <span class="n">ipc_barriers_out</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span> <span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span>
|
||
<span class="p">[</span><span class="mi">0</span><span class="p">],</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">int64</span><span class="p">,</span>
|
||
<span class="n">device</span><span class="o">=</span><span class="s2">"cpu"</span><span class="p">)</span>
|
||
|
||
<span class="nd">@staticmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">allocate_allreduce_fusion_workspace</span><span class="p">(</span>
|
||
<span class="n">mapping</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">,</span>
|
||
<span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">IpcMemory</span><span class="p">],</span> <span class="s2">"torch.tensor"</span><span class="p">]:</span>
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
|
||
<span class="n">is_p2p_supported</span> <span class="o">=</span> <span class="n">can_access_peer</span><span class="p">(</span><span class="n">mapping</span><span class="p">)</span>
|
||
<span class="n">ipc_buffers_size</span> <span class="o">=</span> <span class="n">size</span> <span class="o">*</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span>
|
||
<span class="n">ipc_buffers</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span><span class="n">mapping</span><span class="p">,</span> <span class="n">ipc_buffers_size</span><span class="p">,</span> <span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="n">ipc_barriers</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span><span class="n">mapping</span><span class="p">,</span> <span class="mi">256</span> <span class="o">*</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">,</span>
|
||
<span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="n">lamport_buffers_size</span> <span class="o">=</span> <span class="n">size</span> <span class="o">*</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span>
|
||
<span class="n">lamport_buffers</span> <span class="o">=</span> <span class="n">IpcMemory</span><span class="p">(</span><span class="n">mapping</span><span class="p">,</span> <span class="mi">3</span> <span class="o">*</span> <span class="n">lamport_buffers_size</span><span class="p">,</span>
|
||
<span class="n">is_p2p_supported</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">is_p2p_supported</span><span class="p">:</span>
|
||
<span class="n">lamport_initialize</span><span class="p">(</span>
|
||
<span class="n">lamport_buffers</span><span class="o">.</span><span class="n">local_ptr</span><span class="p">,</span>
|
||
<span class="mi">3</span> <span class="o">*</span> <span class="n">lamport_buffers_size</span><span class="p">,</span>
|
||
<span class="p">)</span>
|
||
<span class="n">flag_buffer</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">([</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">lamport_buffers_size</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">int</span><span class="p">,</span>
|
||
<span class="n">device</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">)</span>
|
||
<span class="n">buffers</span> <span class="o">=</span> <span class="p">[</span><span class="n">ipc_buffers</span><span class="p">,</span> <span class="n">ipc_barriers</span><span class="p">,</span> <span class="n">lamport_buffers</span><span class="p">,</span> <span class="n">flag_buffer</span><span class="p">]</span>
|
||
|
||
<span class="k">return</span> <span class="n">buffers</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">ipc_buffers</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span> <span class="n">ipc_barriers</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span>
|
||
<span class="n">lamport_buffers</span><span class="o">.</span><span class="n">serialize</span><span class="p">()</span> <span class="o">+</span> <span class="p">[</span><span class="n">flag_buffer</span><span class="o">.</span><span class="n">data_ptr</span><span class="p">()],</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">int64</span><span class="p">,</span>
|
||
<span class="n">device</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">)</span>
|
||
|
||
|
||
<span class="n">custom_all_reduce_helper</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">init_all_reduce_helper</span><span class="p">():</span>
|
||
<span class="k">global</span> <span class="n">custom_all_reduce_helper</span>
|
||
<span class="n">custom_all_reduce_helper</span> <span class="o">=</span> <span class="n">CustomAllReduceHelper</span><span class="p">()</span>
|
||
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">current_all_reduce_helper</span><span class="p">():</span>
|
||
<span class="k">global</span> <span class="n">custom_all_reduce_helper</span>
|
||
<span class="k">assert</span> <span class="n">custom_all_reduce_helper</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">,</span> <span class="s2">"You must call `init_all_reduce_helper` first"</span>
|
||
<span class="k">return</span> <span class="n">custom_all_reduce_helper</span>
|
||
</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 September 29, 2025.</p>
|
||
|
||
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/560ded5">560ded5</a>.</p>
|
||
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
</footer>
|
||
</body>
|
||
</html> |