kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
a79e2dc7fb
TensorRT-LLMs/0.20.0rc3/examples/llm_quantization.html
Kaiyu Xie e2085332db Update GitHub pages to v0.20.0rc3
2025-05-20 09:23:49 +00:00

729 lines
42 KiB
HTML
Raw Blame History

<!DOCTYPE html>
<html lang="en" data-content_root="../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Generation with Quantization &#8212; TensorRT-LLM</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!--
this give us a css class that will be invisible only if js is disabled
-->
<noscript>
<style>
.pst-js-only { display: none !important; }
</style>
</noscript>
<!-- Loaded before other Sphinx assets -->
<link href="../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link href="../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../_static/styles/nvidia-sphinx-theme.css?v=df3ac72c" />
<link rel="stylesheet" type="text/css" href="../_static/copybutton.css?v=76b2166b" />
<link rel="stylesheet" type="text/css" href="../_static/autodoc_pydantic.css" />
<!-- So that users can add custom icons -->
<script src="../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script>
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" />
<link rel="preload" as="script" href="../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" />
<script src="../_static/documentation_options.js?v=5929fcd5"></script>
<script src="../_static/doctools.js?v=9a2dae69"></script>
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../_static/copybutton.js?v=65e89d2a"></script>
<script>DOCUMENTATION_OPTIONS.pagename = 'examples/llm_quantization';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '0.20.0rc3';
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" />
<link rel="next" title="Generate Text in Streaming" href="llm_inference_async_streaming.html" />
<link rel="prev" title="Generate Text Using Lookahead Decoding" href="llm_lookahead_decoding.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="0.20.0rc3" />
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<dialog id="pst-search-dialog">
<form class="bd-search d-flex align-items-center"
action="../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form>
</dialog>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
<div class="bd-header__inner bd-page-width">
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
<span class="fa-solid fa-bars"></span>
</button>
<div class="col-lg-3 navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="../index.html">
<img src="../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
<img src="../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
<p class="title logo__title">TensorRT-LLM</p>
</a></div>
</div>
<div class="col-lg-9 navbar-header-items">
<div class="me-auto navbar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-2"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-2"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-2"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-2">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="navbar-header-items__end">
<div class="navbar-item navbar-persistent--container">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="navbar-persistent--mobile">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
</div>
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<dialog id="pst-primary-sidebar-modal"></dialog>
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
<a class="navbar-brand logo" href="../index.html">
<img src="../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
<img src="../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
<p class="title logo__title">TensorRT-LLM</p>
</a>
<div class="sidebar-header-items sidebar-primary__section">
<div class="sidebar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-3"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-3"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-3"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-3">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="sidebar-header-items__end">
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<nav class="bd-docs-nav bd-links"
aria-label="Table of Contents">
<p class="bd-links__title" role="heading" aria-level="1">Table of Contents</p>
<div class="bd-toc-item navbar-nav"><p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../quick-start-guide.html">Quick Start Guide</a></li>
<li class="toctree-l1"><a class="reference internal" href="../key-features.html">Key Features</a></li>
<li class="toctree-l1"><a class="reference internal" href="../torch.html">PyTorch Backend</a></li>
<li class="toctree-l1"><a class="reference internal" href="../release-notes.html">Release Notes</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Installation</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../installation/linux.html">Installing on Linux</a></li>
<li class="toctree-l1"><a class="reference internal" href="../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
<li class="toctree-l1"><a class="reference internal" href="../installation/grace-hopper.html">Installing on Grace Hopper</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">LLM API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../llm-api/index.html">API Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="../llm-api/reference.html">API Reference</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Examples</span></p>
<ul class="current nav bd-sidenav">
<li class="toctree-l1 current active has-children"><a class="reference internal" href="index.html">LLM Examples Introduction</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="llm_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_eagle_decoding.html">Generate Text Using Eagle Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_async.html">Generate Text Asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_logits_processor.html">Control generated text using logits processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_kv_events.html">Get KV Cache Events</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2 current active"><a class="current reference internal" href="#">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_async_streaming.html">Generate Text in Streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_customize.html">Generate text with customization</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="customization.html">LLM Common Customizations</a></li>
<li class="toctree-l1 current active has-children"><a class="reference internal" href="llm_api_examples.html">LLM Examples</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="llm_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_eagle_decoding.html">Generate Text Using Eagle Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_async.html">Generate Text Asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_logits_processor.html">Control generated text using logits processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_kv_events.html">Get KV Cache Events</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2 current active"><a class="current reference internal" href="#">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_async_streaming.html">Generate Text in Streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_inference_customize.html">Generate text with customization</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
<li class="toctree-l2"><a class="reference internal" href="llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
</ul>
</details></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="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="curl_chat_client.html">Curl Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="curl_completion_client.html">Curl Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
<li class="toctree-l2"><a class="reference internal" href="genai_perf_client.html">Genai Perf Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="genai_perf_client_for_multimodal.html">Genai Perf Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="openai_chat_client.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="openai_chat_client_for_multimodal.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="openai_completion_client.html">OpenAI Completion Client</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Model Definition API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.layers.html">Layers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.functional.html">Functionals</a></li>
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.models.html">Models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.plugin.html">Plugin</a></li>
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.quantization.html">Quantization</a></li>
<li class="toctree-l1"><a class="reference internal" href="../python-api/tensorrt_llm.runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">C++ API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../_cpp_gen/executor.html">Executor</a></li>
<li class="toctree-l1"><a class="reference internal" href="../_cpp_gen/runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-build.html">trtllm-build</a></li>
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-serve.html">trtllm-serve</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Architecture</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../architecture/overview.html">TensorRT-LLM Architecture</a></li>
<li class="toctree-l1"><a class="reference internal" href="../architecture/core-concepts.html">Model Definition</a></li>
<li class="toctree-l1"><a class="reference internal" href="../architecture/checkpoint.html">TensorRT-LLM Checkpoint</a></li>
<li class="toctree-l1"><a class="reference internal" href="../architecture/workflow.html">TensorRT-LLM Build Workflow</a></li>
<li class="toctree-l1"><a class="reference internal" href="../architecture/add-model.html">Adding a Model</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Advanced</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../advanced/gpt-attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/gpt-runtime.html">C++ GPT Runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/executor.html">Executor API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/graph-rewriting.html">Graph Rewriting Module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/lora.html">Run gpt-2b + LoRA using Executor / cpp runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/expert-parallelism.html">Expert Parallelism in TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/kv-cache-reuse.html">KV cache reuse</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/speculative-decoding.html">Speculative Sampling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../advanced/disaggregated-service.html">Disaggregated-Service (experimental)</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Performance</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../performance/perf-overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../performance/perf-benchmarking.html">Benchmarking</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../performance/performance-tuning-guide/index.html">Performance Tuning Guide</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/benchmarking-default-performance.html">Benchmarking Default Performance</a></li>
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/useful-build-time-flags.html">Useful Build-Time Flags</a></li>
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.html">Tuning Max Batch Size and Max Num Tokens</a></li>
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/deciding-model-sharding-strategy.html">Deciding Model Sharding Strategy</a></li>
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/fp8-quantization.html">FP8 Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../performance/performance-tuning-guide/useful-runtime-flags.html">Useful Runtime Options</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../performance/perf-analysis.html">Performance Analysis</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../reference/troubleshooting.html">Troubleshooting</a></li>
<li class="toctree-l1"><a class="reference internal" href="../reference/support-matrix.html">Support Matrix</a></li>
<li class="toctree-l1"><a class="reference internal" href="../reference/precision.html">Numerical Precision</a></li>
<li class="toctree-l1"><a class="reference internal" href="../reference/memory.html">Memory Usage of TensorRT-LLM</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../blogs/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/Falcon180B-H200.html">Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/quantization-in-TRT-LLM.html">Speed up inference with SOTA quantization techniques in TRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
<li class="toctree-l1"><a class="reference internal" href="../blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html">Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs</a></li>
</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">LLM Examples Introduction</a></li>
<li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">Generation with Quantization</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="generation-with-quantization">
<h1>Generation with Quantization<a class="headerlink" href="#generation-with-quantization" title="Link to this heading">#</a></h1>
<p>Source <a class="github reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/llm-api/llm_quantization.py">NVIDIA/TensorRT-LLM</a>.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="c1">### Generation with Quantization</span>
<span class="linenos"> 2</span><span class="kn">import</span><span class="w"> </span><span class="nn">logging</span>
<span class="linenos"> 3</span>
<span class="linenos"> 4</span><span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
<span class="linenos"> 5</span>
<span class="linenos"> 6</span><span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm</span><span class="w"> </span><span class="kn">import</span> <span class="n">LLM</span><span class="p">,</span> <span class="n">SamplingParams</span>
<span class="linenos"> 7</span><span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.llmapi</span><span class="w"> </span><span class="kn">import</span> <span class="n">CalibConfig</span><span class="p">,</span> <span class="n">QuantAlgo</span><span class="p">,</span> <span class="n">QuantConfig</span>
<span class="linenos"> 8</span>
<span class="linenos"> 9</span><span class="n">major</span><span class="p">,</span> <span class="n">minor</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">get_device_capability</span><span class="p">()</span>
<span class="linenos">10</span><span class="n">enable_fp8</span> <span class="o">=</span> <span class="n">major</span> <span class="o">&gt;</span> <span class="mi">8</span> <span class="ow">or</span> <span class="p">(</span><span class="n">major</span> <span class="o">==</span> <span class="mi">8</span> <span class="ow">and</span> <span class="n">minor</span> <span class="o">&gt;=</span> <span class="mi">9</span><span class="p">)</span>
<span class="linenos">11</span><span class="n">enable_nvfp4</span> <span class="o">=</span> <span class="n">major</span> <span class="o">&gt;=</span> <span class="mi">10</span>
<span class="linenos">12</span>
<span class="linenos">13</span><span class="n">quant_and_calib_configs</span> <span class="o">=</span> <span class="p">[]</span>
<span class="linenos">14</span>
<span class="linenos">15</span><span class="k">if</span> <span class="ow">not</span> <span class="n">enable_nvfp4</span><span class="p">:</span>
<span class="linenos">16</span> <span class="c1"># Example 1: Specify int4 AWQ quantization to QuantConfig.</span>
<span class="linenos">17</span> <span class="c1"># We can skip specifying CalibConfig or leave a None as the default value.</span>
<span class="linenos">18</span> <span class="n">quant_and_calib_configs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
<span class="linenos">19</span> <span class="p">(</span><span class="n">QuantConfig</span><span class="p">(</span><span class="n">quant_algo</span><span class="o">=</span><span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A16_AWQ</span><span class="p">),</span> <span class="kc">None</span><span class="p">))</span>
<span class="linenos">20</span>
<span class="linenos">21</span><span class="k">if</span> <span class="n">enable_fp8</span><span class="p">:</span>
<span class="linenos">22</span> <span class="c1"># Example 2: Specify FP8 quantization to QuantConfig.</span>
<span class="linenos">23</span> <span class="c1"># We can create a CalibConfig to specify the calibration dataset and other details.</span>
<span class="linenos">24</span> <span class="c1"># Note that the calibration dataset could be either HF dataset name or a path to local HF dataset.</span>
<span class="linenos">25</span> <span class="n">quant_and_calib_configs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
<span class="linenos">26</span> <span class="p">(</span><span class="n">QuantConfig</span><span class="p">(</span><span class="n">quant_algo</span><span class="o">=</span><span class="n">QuantAlgo</span><span class="o">.</span><span class="n">FP8</span><span class="p">,</span>
<span class="linenos">27</span> <span class="n">kv_cache_quant_algo</span><span class="o">=</span><span class="n">QuantAlgo</span><span class="o">.</span><span class="n">FP8</span><span class="p">),</span>
<span class="linenos">28</span> <span class="n">CalibConfig</span><span class="p">(</span><span class="n">calib_dataset</span><span class="o">=</span><span class="s1">&#39;cnn_dailymail&#39;</span><span class="p">,</span>
<span class="linenos">29</span> <span class="n">calib_batches</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
<span class="linenos">30</span> <span class="n">calib_max_seq_length</span><span class="o">=</span><span class="mi">256</span><span class="p">)))</span>
<span class="linenos">31</span><span class="k">else</span><span class="p">:</span>
<span class="linenos">32</span> <span class="n">logging</span><span class="o">.</span><span class="n">error</span><span class="p">(</span>
<span class="linenos">33</span> <span class="s2">&quot;FP8 quantization only works on post-ada GPUs. Skipped in the example.&quot;</span><span class="p">)</span>
<span class="linenos">34</span>
<span class="linenos">35</span><span class="k">if</span> <span class="n">enable_nvfp4</span><span class="p">:</span>
<span class="linenos">36</span> <span class="c1"># Example 3: Specify NVFP4 quantization to QuantConfig.</span>
<span class="linenos">37</span> <span class="n">quant_and_calib_configs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
<span class="linenos">38</span> <span class="p">(</span><span class="n">QuantConfig</span><span class="p">(</span><span class="n">quant_algo</span><span class="o">=</span><span class="n">QuantAlgo</span><span class="o">.</span><span class="n">NVFP4</span><span class="p">,</span>
<span class="linenos">39</span> <span class="n">kv_cache_quant_algo</span><span class="o">=</span><span class="n">QuantAlgo</span><span class="o">.</span><span class="n">FP8</span><span class="p">),</span>
<span class="linenos">40</span> <span class="n">CalibConfig</span><span class="p">(</span><span class="n">calib_dataset</span><span class="o">=</span><span class="s1">&#39;cnn_dailymail&#39;</span><span class="p">,</span>
<span class="linenos">41</span> <span class="n">calib_batches</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
<span class="linenos">42</span> <span class="n">calib_max_seq_length</span><span class="o">=</span><span class="mi">256</span><span class="p">)))</span>
<span class="linenos">43</span><span class="k">else</span><span class="p">:</span>
<span class="linenos">44</span> <span class="n">logging</span><span class="o">.</span><span class="n">error</span><span class="p">(</span>
<span class="linenos">45</span> <span class="s2">&quot;NVFP4 quantization only works on Blackwell. Skipped in the example.&quot;</span><span class="p">)</span>
<span class="linenos">46</span>
<span class="linenos">47</span>
<span class="linenos">48</span><span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
<span class="linenos">49</span>
<span class="linenos">50</span> <span class="k">for</span> <span class="n">quant_config</span><span class="p">,</span> <span class="n">calib_config</span> <span class="ow">in</span> <span class="n">quant_and_calib_configs</span><span class="p">:</span>
<span class="linenos">51</span> <span class="c1"># The built-in end-to-end quantization is triggered according to the passed quant_config.</span>
<span class="linenos">52</span> <span class="n">llm</span> <span class="o">=</span> <span class="n">LLM</span><span class="p">(</span><span class="n">model</span><span class="o">=</span><span class="s2">&quot;TinyLlama/TinyLlama-1.1B-Chat-v1.0&quot;</span><span class="p">,</span>
<span class="linenos">53</span> <span class="n">quant_config</span><span class="o">=</span><span class="n">quant_config</span><span class="p">,</span>
<span class="linenos">54</span> <span class="n">calib_config</span><span class="o">=</span><span class="n">calib_config</span><span class="p">)</span>
<span class="linenos">55</span>
<span class="linenos">56</span> <span class="c1"># Sample prompts.</span>
<span class="linenos">57</span> <span class="n">prompts</span> <span class="o">=</span> <span class="p">[</span>
<span class="linenos">58</span> <span class="s2">&quot;Hello, my name is&quot;</span><span class="p">,</span>
<span class="linenos">59</span> <span class="s2">&quot;The president of the United States is&quot;</span><span class="p">,</span>
<span class="linenos">60</span> <span class="s2">&quot;The capital of France is&quot;</span><span class="p">,</span>
<span class="linenos">61</span> <span class="s2">&quot;The future of AI is&quot;</span><span class="p">,</span>
<span class="linenos">62</span> <span class="p">]</span>
<span class="linenos">63</span>
<span class="linenos">64</span> <span class="c1"># Create a sampling params.</span>
<span class="linenos">65</span> <span class="n">sampling_params</span> <span class="o">=</span> <span class="n">SamplingParams</span><span class="p">(</span><span class="n">temperature</span><span class="o">=</span><span class="mf">0.8</span><span class="p">,</span> <span class="n">top_p</span><span class="o">=</span><span class="mf">0.95</span><span class="p">)</span>
<span class="linenos">66</span>
<span class="linenos">67</span> <span class="k">for</span> <span class="n">output</span> <span class="ow">in</span> <span class="n">llm</span><span class="o">.</span><span class="n">generate</span><span class="p">(</span><span class="n">prompts</span><span class="p">,</span> <span class="n">sampling_params</span><span class="p">):</span>
<span class="linenos">68</span> <span class="nb">print</span><span class="p">(</span>
<span class="linenos">69</span> <span class="sa">f</span><span class="s2">&quot;Prompt: </span><span class="si">{</span><span class="n">output</span><span class="o">.</span><span class="n">prompt</span><span class="si">!r}</span><span class="s2">, Generated text: </span><span class="si">{</span><span class="n">output</span><span class="o">.</span><span class="n">outputs</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">text</span><span class="si">!r}</span><span class="s2">&quot;</span>
<span class="linenos">70</span> <span class="p">)</span>
<span class="linenos">71</span> <span class="n">llm</span><span class="o">.</span><span class="n">shutdown</span><span class="p">()</span>
<span class="linenos">72</span>
<span class="linenos">73</span> <span class="c1"># Got output like</span>
<span class="linenos">74</span> <span class="c1"># Prompt: &#39;Hello, my name is&#39;, Generated text: &#39;Jane Smith. I am a resident of the city. Can you tell me more about the public services provided in the area?&#39;</span>
<span class="linenos">75</span> <span class="c1"># Prompt: &#39;The president of the United States is&#39;, Generated text: &#39;considered the head of state, and the vice president of the United States is considered the head of state. President and Vice President of the United States (US)&#39;</span>
<span class="linenos">76</span> <span class="c1"># Prompt: &#39;The capital of France is&#39;, Generated text: &#39;located in Paris, France. The population of Paris, France, is estimated to be 2 million. France is home to many famous artists, including Picasso&#39;</span>
<span class="linenos">77</span> <span class="c1"># Prompt: &#39;The future of AI is&#39;, Generated text: &#39;an open and collaborative project. The project is an ongoing effort, and we invite participation from members of the community.\n\nOur community is&#39;</span>
<span class="linenos">78</span>
<span class="linenos">79</span>
<span class="linenos">80</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">&#39;__main__&#39;</span><span class="p">:</span>
<span class="linenos">81</span> <span class="n">main</span><span class="p">()</span>
</pre></div>
</div>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="llm_lookahead_decoding.html"
title="previous page">
<i class="fa-solid fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">Generate Text Using Lookahead Decoding</p>
</div>
</a>
<a class="right-next"
href="llm_inference_async_streaming.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Generate Text in Streaming</p>
</div>
<i class="fa-solid fa-angle-right"></i>
</a>
</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>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink