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
bb9465295f
TensorRT-LLMs/_modules/tensorrt_llm/models/redrafter/model.html
Kaiyu Xie bb9465295f Fix main page 
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
2025-04-26 05:56:13 +00:00

927 lines
74 KiB
HTML
Raw Blame History

<!DOCTYPE html>
<html lang="en" data-content_root="../../../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>tensorrt_llm.models.redrafter.model &#8212; TensorRT-LLM</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!--
this give us a css class that will be invisible only if js is disabled
-->
<noscript>
<style>
.pst-js-only { display: none !important; }
</style>
</noscript>
<!-- Loaded before other Sphinx assets -->
<link href="../../../../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link href="../../../../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="../../../../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../../../../_static/styles/nvidia-sphinx-theme.css?v=df3ac72c" />
<link rel="stylesheet" type="text/css" href="../../../../_static/copybutton.css?v=76b2166b" />
<link rel="stylesheet" type="text/css" href="../../../../_static/autodoc_pydantic.css" />
<!-- So that users can add custom icons -->
<script src="../../../../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script>
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" />
<link rel="preload" as="script" href="../../../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" />
<script src="../../../../_static/documentation_options.js?v=5929fcd5"></script>
<script src="../../../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../../../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../../../../_static/copybutton.js?v=65e89d2a"></script>
<script>DOCUMENTATION_OPTIONS.pagename = '_modules/tensorrt_llm/models/redrafter/model';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '0.20.0rc0';
DOCUMENTATION_OPTIONS.show_version_warning_banner =
false;
</script>
<link rel="icon" href="../../../../_static/favicon.png"/>
<link rel="index" title="Index" href="../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../search.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="0.20.0rc0" />
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<dialog id="pst-search-dialog">
<form class="bd-search d-flex align-items-center"
action="../../../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form>
</dialog>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
<div class="bd-header__inner bd-page-width">
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
<span class="fa-solid fa-bars"></span>
</button>
<div class="col-lg-3 navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="../../../../index.html">
<img src="../../../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
<img src="../../../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
<p class="title logo__title">TensorRT-LLM</p>
</a></div>
</div>
<div class="col-lg-9 navbar-header-items">
<div class="me-auto navbar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-2"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-2"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-2"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-2">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="navbar-header-items__end">
<div class="navbar-item navbar-persistent--container">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="navbar-persistent--mobile">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
</div>
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<dialog id="pst-primary-sidebar-modal"></dialog>
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
<a class="navbar-brand logo" href="../../../../index.html">
<img src="../../../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
<img src="../../../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
<p class="title logo__title">TensorRT-LLM</p>
</a>
<div class="sidebar-header-items sidebar-primary__section">
<div class="sidebar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-3"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-3"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-3"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-3">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="sidebar-header-items__end">
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<nav class="bd-docs-nav bd-links"
aria-label="Table of Contents">
<p class="bd-links__title" role="heading" aria-level="1">Table of Contents</p>
<div class="bd-toc-item navbar-nav"><p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../../overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../quick-start-guide.html">Quick Start Guide</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../key-features.html">Key Features</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../torch.html">PyTorch Backend</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../release-notes.html">Release Notes</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Installation</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../../installation/linux.html">Installing on Linux</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../installation/grace-hopper.html">Installing on Grace Hopper</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">LLM API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../../llm-api/index.html">API Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../llm-api/reference.html">API Reference</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Examples</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../examples/index.html">LLM Examples Introduction</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_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_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_customize.html">Generate text with customization</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_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_quantization.html">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_eagle_decoding.html">Generate Text Using Eagle Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_inference_kv_events.html">Get KV Cache Events</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_auto_parallel.html">Automatic Parallelism with LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../examples/customization.html">LLM Common Customizations</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../examples/llm_api_examples.html">LLM Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_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_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_customize.html">Generate text with customization</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_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_quantization.html">Generation with Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_eagle_decoding.html">Generate Text Using Eagle Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_inference_kv_events.html">Get KV Cache Events</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_auto_parallel.html">Automatic Parallelism with LLM</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
</ul>
</details></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../examples/trtllm_serve_examples.html">Online Serving Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/curl_chat_client.html">Curl Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/curl_completion_client.html">Curl Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/genai_perf_client.html">Genai Perf Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/openai_chat_client.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/openai_chat_client_for_multimodal.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Model Definition API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../../python-api/tensorrt_llm.layers.html">Layers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../python-api/tensorrt_llm.functional.html">Functionals</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../python-api/tensorrt_llm.models.html">Models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../python-api/tensorrt_llm.plugin.html">Plugin</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../python-api/tensorrt_llm.quantization.html">Quantization</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../python-api/tensorrt_llm.runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">C++ API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../../_cpp_gen/executor.html">Executor</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../_cpp_gen/runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../../commands/trtllm-build.html">trtllm-build</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../commands/trtllm-serve.html">trtllm-serve</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Architecture</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../../architecture/overview.html">TensorRT-LLM Architecture</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../architecture/core-concepts.html">Model Definition</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../architecture/checkpoint.html">TensorRT-LLM Checkpoint</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../architecture/workflow.html">TensorRT-LLM Build Workflow</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../architecture/add-model.html">Adding a Model</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Advanced</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/gpt-attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/gpt-runtime.html">C++ GPT Runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/executor.html">Executor API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/graph-rewriting.html">Graph Rewriting Module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/lora.html">Run gpt-2b + LoRA using Executor / cpp runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/expert-parallelism.html">Expert Parallelism in TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/kv-cache-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>
</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.models.redrafter.model</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<h1>Source code for tensorrt_llm.models.redrafter.model</h1><div class="highlight"><pre>
<span></span><span class="c1"># SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION &amp; AFFILIATES. All rights reserved.</span>
<span class="c1"># SPDX-License-Identifier: Apache-2.0</span>
<span class="c1">#</span>
<span class="c1"># Licensed under the Apache License, Version 2.0 (the &quot;License&quot;);</span>
<span class="c1"># you may not use this file except in compliance with the License.</span>
<span class="c1"># You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">collections</span><span class="w"> </span><span class="kn">import</span> <span class="n">OrderedDict</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">tensorrt_llm._common</span><span class="w"> </span><span class="kn">import</span> <span class="n">default_net</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.bindings</span><span class="w"> </span><span class="kn">import</span> <span class="n">KVCacheType</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.functional</span><span class="w"> </span><span class="kn">import</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">cast</span><span class="p">,</span> <span class="n">categorical_sample</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.models</span><span class="w"> </span><span class="kn">import</span> <span class="n">LLaMAForCausalLM</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.models.generation_mixin</span><span class="w"> </span><span class="kn">import</span> <span class="n">GenerationMixin</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">pad_vocab_size</span><span class="p">,</span> <span class="n">str_dtype_to_trt</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">.drafter</span><span class="w"> </span><span class="kn">import</span> <span class="n">Drafter</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">.redrafter_helper</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span><span class="n">_beam_search_candidates</span><span class="p">,</span> <span class="n">_beams2tree</span><span class="p">,</span>
<span class="n">_process_logits_and_hidden_states</span><span class="p">)</span>
<div class="viewcode-block" id="ReDrafterForCausalLM">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.ReDrafterForCausalLM">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">ReDrafterForCausalLM</span><span class="p">(</span><span class="n">LLaMAForCausalLM</span><span class="p">):</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="n">config</span><span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">config</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dtype</span> <span class="o">=</span> <span class="n">str_dtype_to_trt</span><span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">vocab_size</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">vocab_size</span>
<span class="n">vocab_size_padded</span> <span class="o">=</span> <span class="n">pad_vocab_size</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">,</span>
<span class="n">config</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="bp">self</span><span class="o">.</span><span class="n">drafter</span> <span class="o">=</span> <span class="n">Drafter</span><span class="o">.</span><span class="n">from_config</span><span class="p">(</span><span class="n">config</span><span class="p">,</span> <span class="n">vocab_size_padded</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">num_beams</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">redrafter_num_beams</span>
<span class="bp">self</span><span class="o">.</span><span class="n">beam_candidate_length</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">redrafter_draft_len_per_beam</span>
<span class="bp">self</span><span class="o">.</span><span class="n">beam_length</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">beam_candidate_length</span> <span class="o">+</span> <span class="mi">1</span> <span class="c1"># including true token</span>
<span class="bp">self</span><span class="o">.</span><span class="n">greedy_search</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">redrafter_greedy_search</span>
<span class="bp">self</span><span class="o">.</span><span class="n">is_rnn</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">redrafter_is_rnn</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">dtype</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">drafter</span><span class="o">.</span><span class="n">dtype</span><span class="p">,</span> <span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="si">}</span><span class="s2"> != </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">drafter</span><span class="o">.</span><span class="n">dtype</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="k">def</span><span class="w"> </span><span class="nf">_fwd_helper</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hidden_states</span><span class="p">,</span> <span class="n">lm_logits</span><span class="p">,</span> <span class="n">embedding</span><span class="p">,</span> <span class="n">drafter</span><span class="p">,</span>
<span class="n">kwargs</span><span class="p">:</span> <span class="nb">dict</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> Must enable remove_input_padding:</span>
<span class="sd"> hidden_states [total_tokens, H]</span>
<span class="sd"> lm_logits [total_tokens, V]</span>
<span class="sd"> 1. process_logits: context vs gen</span>
<span class="sd"> a. Context: just return the last hidden states, and logits/probs</span>
<span class="sd"> b. Gen:</span>
<span class="sd"> i. verify: use lm_logits, draft_probs, draft_indices, draft_tokens</span>
<span class="sd"> ii. select hidden state and update probs</span>
<span class="sd"> 3. Sample token based on probs</span>
<span class="sd"> 4. Generate candidates using hidden_states, sampled token</span>
<span class="sd"> 5. Using beams, generate validation buffers, mark them as output</span>
<span class="sd"> 6. Mark all the outputs</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="n">num_beams</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_beams</span>
<span class="n">beam_length</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">beam_length</span>
<span class="c1"># Get the inputs needed</span>
<span class="n">rand_data_sample</span> <span class="o">=</span> <span class="n">kwargs</span><span class="p">[</span><span class="s1">&#39;rand_data_sample&#39;</span><span class="p">]</span>
<span class="n">position_ids_base</span> <span class="o">=</span> <span class="n">kwargs</span><span class="p">[</span><span class="s1">&#39;position_ids_base&#39;</span><span class="p">]</span>
<span class="c1"># Step 1: Process logits and hidden states</span>
<span class="c1"># process the base model output (verify for gen-phase)</span>
<span class="n">probs</span><span class="p">,</span> <span class="n">draft_input</span><span class="p">,</span> <span class="n">num_accepted_tokens</span><span class="p">,</span> \
<span class="n">accepted_beam_index</span> <span class="o">=</span> <span class="n">_process_logits_and_hidden_states</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span> <span class="n">lm_logits</span><span class="p">,</span> <span class="n">hidden_states</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span>
<span class="c1"># NOTE: num_accepted_tokens doesn&#39;t include true token so add 1 here</span>
<span class="n">num_accepted_tokens</span> <span class="o">=</span> <span class="n">num_accepted_tokens</span> <span class="o">+</span> <span class="mi">1</span>
<span class="c1"># At this point:</span>
<span class="c1"># probs : [bs, V]</span>
<span class="c1"># hidden_states : [bs, H]</span>
<span class="c1"># Step 2: Sample token</span>
<span class="n">next_token</span> <span class="o">=</span> <span class="n">categorical_sample</span><span class="p">(</span><span class="n">probs</span><span class="p">,</span> <span class="n">rand_data_sample</span><span class="p">)</span>
<span class="c1"># Step 3: beam search</span>
<span class="n">new_draft_tokens</span><span class="p">,</span> <span class="n">new_draft_logits</span> <span class="o">=</span> <span class="n">_beam_search_candidates</span><span class="p">(</span>
<span class="n">draft_input</span><span class="p">,</span> <span class="n">next_token</span><span class="p">,</span> <span class="n">embedding</span><span class="p">,</span> <span class="n">drafter</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_beams</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">beam_length</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_rnn</span><span class="p">)</span>
<span class="c1"># Step 4: tree processing</span>
<span class="n">active_tokens_flattened</span><span class="p">,</span> <span class="n">new_draft_token_indices</span><span class="p">,</span> <span class="n">new_mask</span><span class="p">,</span> \
<span class="n">new_position_offsets</span><span class="p">,</span> <span class="n">packed_position_ids</span><span class="p">,</span> <span class="n">next_num_gen_tokens</span><span class="p">,</span> <span class="n">max_gen_token</span><span class="p">,</span> \
<span class="n">total_gen_token</span> <span class="o">=</span> <span class="n">_beams2tree</span><span class="p">(</span><span class="n">new_draft_tokens</span><span class="p">,</span> <span class="n">num_beams</span><span class="p">,</span> <span class="n">beam_length</span><span class="p">,</span>
<span class="n">position_ids_base</span> <span class="o">+</span> <span class="n">num_accepted_tokens</span><span class="p">)</span>
<span class="c1"># Step 5: mark all the tensors we need</span>
<span class="n">num_accepted_tokens</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;num_accepted_tokens&#39;</span><span class="p">)</span>
<span class="n">accepted_beam_index</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;accepted_beam_index&#39;</span><span class="p">)</span>
<span class="n">max_gen_token</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;max_gen_token&#39;</span><span class="p">)</span>
<span class="n">total_gen_token</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;total_gen_token&#39;</span><span class="p">)</span>
<span class="n">next_num_gen_tokens</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;next_spec_decoding_generation_lengths&#39;</span><span class="p">)</span>
<span class="n">active_tokens_flattened</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;next_flat_tokens&#39;</span><span class="p">)</span>
<span class="n">new_draft_tokens</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;next_draft_tokens&#39;</span><span class="p">)</span>
<span class="n">new_draft_logits</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;next_draft_probs&#39;</span><span class="p">)</span>
<span class="n">new_draft_token_indices</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;next_draft_indices&#39;</span><span class="p">)</span>
<span class="n">new_mask</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;spec_decoding_mask&#39;</span><span class="p">)</span>
<span class="n">new_position_offsets</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;next_spec_decoding_position_offsets&#39;</span><span class="p">)</span>
<span class="n">packed_position_ids</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;packed_position_ids&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">next_token</span><span class="p">,</span> <span class="n">probs</span><span class="p">,</span> <span class="n">draft_input</span>
<div class="viewcode-block" id="ReDrafterForCausalLM.forward">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.ReDrafterForCausalLM.forward">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> 0. run base model, get logits, hidden_states</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">extra_args</span> <span class="o">=</span> <span class="p">[</span>
<span class="s1">&#39;draft_tokens&#39;</span><span class="p">,</span>
<span class="s1">&#39;draft_indices&#39;</span><span class="p">,</span>
<span class="s1">&#39;draft_probs&#39;</span><span class="p">,</span>
<span class="s1">&#39;device_request_types&#39;</span><span class="p">,</span>
<span class="s1">&#39;redrafter_inverted_temperature&#39;</span><span class="p">,</span>
<span class="s1">&#39;rand_data_validation&#39;</span><span class="p">,</span>
<span class="s1">&#39;rand_data_sample&#39;</span><span class="p">,</span>
<span class="s1">&#39;position_ids_base&#39;</span><span class="p">,</span>
<span class="p">]</span>
<span class="n">use_cache</span> <span class="o">=</span> <span class="kc">True</span>
<span class="n">base_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">v</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> <span class="k">if</span> <span class="n">k</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">extra_args</span><span class="p">}</span>
<span class="k">if</span> <span class="n">use_cache</span> <span class="ow">and</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">paged_kv_cache</span> <span class="ow">is</span> <span class="kc">False</span><span class="p">:</span>
<span class="n">lm_logits</span><span class="p">,</span> <span class="n">presents</span><span class="p">,</span> <span class="n">hidden_states</span> <span class="o">=</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">forward</span><span class="p">(</span>
<span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">base_kwargs</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">lm_logits</span><span class="p">,</span> <span class="n">hidden_states</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">forward</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">base_kwargs</span><span class="p">)</span>
<span class="c1"># lm_logits could be in fp32</span>
<span class="n">lm_logits_cast</span> <span class="o">=</span> <span class="n">cast</span><span class="p">(</span><span class="n">lm_logits</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span> <span class="c1"># no-op if same type</span>
<span class="bp">self</span><span class="o">.</span><span class="n">register_network_output</span><span class="p">(</span><span class="s2">&quot;hidden_states&quot;</span><span class="p">,</span>
<span class="n">hidden_states</span><span class="p">)</span> <span class="c1"># debugging</span>
<span class="n">new_draft_tokens</span><span class="p">,</span> <span class="n">new_draft_logits</span><span class="p">,</span> <span class="n">probs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fwd_helper</span><span class="p">(</span>
<span class="n">hidden_states</span><span class="p">,</span>
<span class="n">lm_logits_cast</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">vocab_embedding</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">drafter</span><span class="p">,</span>
<span class="n">kwargs</span><span class="o">=</span><span class="n">kwargs</span><span class="p">)</span>
<span class="k">return</span> <span class="n">new_draft_tokens</span><span class="p">,</span> <span class="n">new_draft_logits</span><span class="p">,</span> <span class="n">probs</span></div>
<div class="viewcode-block" id="ReDrafterForCausalLM.prepare_inputs">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.ReDrafterForCausalLM.prepare_inputs">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">prepare_inputs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Inputs needed:</span>
<span class="sd"> Assuming, max_gen_tokens = 1 + nb*(bl - 1), counting true token</span>
<span class="sd"> device_request_types: [bs]</span>
<span class="sd"> draft_tokens: [bs, nb, bl]</span>
<span class="sd"> draft_indices: [bs, nb, bl]</span>
<span class="sd"> draft_probs: [bs, nb, bl-1, V]</span>
<span class="sd"> spec_decoding_generation_lengths: [bs]</span>
<span class="sd"> spec_decoding_position_offsets: [bs, max_gen_tokens]</span>
<span class="sd"> spec_decoding_packed_mask: [bs, max_gen_tokens, packed_length] **</span>
<span class="sd"> redrafter_inverted_temperature: [bs]</span>
<span class="sd"> rand_data_sample: [bs]</span>
<span class="sd"> rand_data_validation: [bs, nb, bl-1]</span>
<span class="sd"> ** The mask is tricky since the boolean mask will need to be</span>
<span class="sd"> packed in runtime. So, the last dim will be:</span>
<span class="sd"> packed_length = ceil(max_gen_tokens/32)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">default_range</span> <span class="o">=</span> <span class="n">GenerationMixin</span><span class="o">.</span><span class="n">default_range</span>
<span class="n">remove_input_padding</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">remove_input_padding</span>
<span class="n">use_gpt_attention_plugin</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">(</span>
<span class="p">)</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">gpt_attention_plugin</span>
<span class="n">use_gemm_plugin</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">gemm_plugin</span>
<span class="n">paged_kv_cache</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">paged_kv_cache</span>
<span class="n">max_batch_size</span> <span class="o">=</span> <span class="n">kwargs</span><span class="p">[</span><span class="s1">&#39;max_batch_size&#39;</span><span class="p">]</span>
<span class="k">assert</span> <span class="n">max_batch_size</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
<span class="n">bb_range</span> <span class="o">=</span> <span class="n">default_range</span><span class="p">(</span><span class="n">max_batch_size</span><span class="p">)</span>
<span class="n">bb0_range</span> <span class="o">=</span> <span class="n">default_range</span><span class="p">(</span><span class="n">max_batch_size</span><span class="p">,</span> <span class="n">min_range</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">opt_offset</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">num_beam_tokens</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_beams</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">beam_length</span>
<span class="n">max_draft_tokens</span> <span class="o">=</span> <span class="n">num_beam_tokens</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_beams</span> <span class="c1"># ignore the true token</span>
<span class="n">max_gen_token_len</span> <span class="o">=</span> <span class="mi">1</span> <span class="o">+</span> <span class="n">max_draft_tokens</span> <span class="c1"># for the true token</span>
<span class="n">max_gen_token_len_range</span> <span class="o">=</span> <span class="n">default_range</span><span class="p">(</span><span class="n">max_gen_token_len</span><span class="p">)</span>
<span class="n">bb_max_gen_token_len_range</span> <span class="o">=</span> <span class="n">default_range</span><span class="p">(</span><span class="n">max_gen_token_len</span> <span class="o">*</span>
<span class="n">max_batch_size</span><span class="p">,</span>
<span class="n">min_range</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="n">kwargs</span><span class="p">[</span><span class="s1">&#39;speculative_decoding_draft_tokens_external&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="kc">False</span>
<span class="n">kwargs</span><span class="p">[</span><span class="s1">&#39;max_draft_len&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">max_draft_tokens</span>
<span class="n">kwargs</span><span class="p">[</span><span class="s1">&#39;spec_decoding_is_generation_length_variable&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span>
<span class="n">inputs</span> <span class="o">=</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">prepare_inputs</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">inputs</span><span class="p">[</span><span class="s1">&#39;spec_decoding_params&#39;</span><span class="p">]</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
<span class="n">enable_two_optimization_profiles</span> <span class="o">=</span> <span class="n">GenerationMixin</span><span class="o">.</span><span class="n">has_ctx_gen_opt_profiles</span><span class="p">(</span>
<span class="n">use_gpt_attention_plugin</span><span class="o">=</span><span class="n">use_gpt_attention_plugin</span><span class="p">,</span>
<span class="n">use_gemm_plugin</span><span class="o">=</span><span class="n">use_gemm_plugin</span><span class="p">,</span>
<span class="n">remove_input_padding</span><span class="o">=</span><span class="n">remove_input_padding</span><span class="p">,</span>
<span class="n">kv_cache_type</span><span class="o">=</span><span class="n">KVCacheType</span><span class="o">.</span><span class="n">PAGED</span>
<span class="k">if</span> <span class="n">paged_kv_cache</span> <span class="k">else</span> <span class="n">KVCacheType</span><span class="o">.</span><span class="n">CONTINUOUS</span><span class="p">)</span>
<span class="k">if</span> <span class="n">enable_two_optimization_profiles</span><span class="p">:</span>
<span class="n">bb_range</span> <span class="o">=</span> <span class="p">[</span><span class="n">bb_range</span><span class="p">,</span> <span class="n">bb_range</span><span class="p">]</span>
<span class="n">bb0_range</span> <span class="o">=</span> <span class="p">[</span><span class="n">bb0_range</span><span class="p">,</span> <span class="n">bb0_range</span><span class="p">]</span>
<span class="n">max_gen_token_len_range</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">max_gen_token_len_range</span><span class="p">,</span> <span class="n">max_gen_token_len_range</span>
<span class="p">]</span>
<span class="n">bb_max_gen_token_len_range</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">bb_max_gen_token_len_range</span><span class="p">,</span> <span class="n">bb_max_gen_token_len_range</span>
<span class="p">]</span>
<span class="n">num_beams_range</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">num_beams</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_beams</span><span class="p">]</span>
<span class="n">beam_length_range</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">beam_length</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">beam_length</span><span class="p">]</span>
<span class="n">candidate_length_range</span> <span class="o">=</span> <span class="p">[</span>
<span class="bp">self</span><span class="o">.</span><span class="n">beam_candidate_length</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">beam_candidate_length</span>
<span class="p">]</span>
<span class="n">vocab_size_range</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">bb_range</span> <span class="o">=</span> <span class="p">[</span><span class="n">bb_range</span><span class="p">]</span>
<span class="n">bb0_range</span> <span class="o">=</span> <span class="p">[</span><span class="n">bb0_range</span><span class="p">]</span>
<span class="n">max_gen_token_len_range</span> <span class="o">=</span> <span class="p">[</span><span class="n">max_gen_token_len_range</span><span class="p">]</span>
<span class="n">bb_max_gen_token_len_range</span> <span class="o">=</span> <span class="p">[</span><span class="n">bb_max_gen_token_len_range</span><span class="p">]</span>
<span class="n">num_beams_range</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">num_beams</span><span class="p">]</span>
<span class="n">beam_length_range</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">beam_length</span><span class="p">]</span>
<span class="n">candidate_length_range</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">beam_candidate_length</span><span class="p">]</span>
<span class="n">vocab_size_range</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">]</span>
<span class="n">device_request_types</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">&#39;device_request_types&#39;</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">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</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="p">(</span><span class="s1">&#39;batch_size&#39;</span><span class="p">,</span> <span class="n">bb_range</span><span class="p">),</span>
<span class="p">]))</span>
<span class="n">draft_tokens</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">&#39;draft_tokens&#39;</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">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_beams</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">beam_length</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="p">(</span><span class="s1">&#39;batch_size_wt0&#39;</span><span class="p">,</span> <span class="n">bb0_range</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;num_beams&#39;</span><span class="p">,</span> <span class="n">num_beams_range</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;beam_length&#39;</span><span class="p">,</span> <span class="n">beam_length_range</span><span class="p">),</span>
<span class="p">]))</span>
<span class="n">draft_indices</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">&#39;draft_indices&#39;</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">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_beams</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">beam_length</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="p">(</span><span class="s1">&#39;batch_size_wt0&#39;</span><span class="p">,</span> <span class="n">bb0_range</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;num_beams&#39;</span><span class="p">,</span> <span class="n">num_beams_range</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;beam_length&#39;</span><span class="p">,</span> <span class="n">beam_length_range</span><span class="p">),</span>
<span class="p">]))</span>
<span class="n">draft_probs</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">&#39;draft_probs&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_beams</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">beam_length</span> <span class="o">-</span> <span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">vocab_size</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="p">(</span><span class="s1">&#39;batch_size_wt0&#39;</span><span class="p">,</span> <span class="n">bb0_range</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;num_beams&#39;</span><span class="p">,</span> <span class="n">num_beams_range</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;candidate_length&#39;</span><span class="p">,</span> <span class="n">candidate_length_range</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;vocab_size&#39;</span><span class="p">,</span> <span class="n">vocab_size_range</span><span class="p">),</span>
<span class="p">]))</span>
<span class="n">redrafter_inverted_temperature</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">&#39;redrafter_inverted_temperature&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</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="p">(</span><span class="s2">&quot;batch_size&quot;</span><span class="p">,</span> <span class="n">bb_range</span><span class="p">),</span>
<span class="p">]))</span>
<span class="n">rand_data_validation</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">&#39;rand_data_validation&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_beams</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">beam_length</span> <span class="o">-</span> <span class="mi">1</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="p">(</span><span class="s1">&#39;batch_size_wt0&#39;</span><span class="p">,</span> <span class="n">bb0_range</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;num_beams&#39;</span><span class="p">,</span> <span class="n">num_beams_range</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;candidate_length&#39;</span><span class="p">,</span> <span class="n">candidate_length_range</span><span class="p">),</span>
<span class="p">]))</span>
<span class="n">rand_data_sample</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">&#39;rand_data_sample&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</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="p">(</span><span class="s1">&#39;batch_size&#39;</span><span class="p">,</span> <span class="n">bb_range</span><span class="p">),</span>
<span class="p">]))</span>
<span class="n">position_ids_base</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="s2">&quot;position_ids_base&quot;</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">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</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="p">(</span><span class="s2">&quot;batch_size&quot;</span><span class="p">,</span> <span class="n">bb_range</span><span class="p">),</span>
<span class="p">]),</span>
<span class="p">)</span>
<span class="n">inputs</span><span class="p">[</span>
<span class="s1">&#39;device_request_types&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">device_request_types</span> <span class="c1"># needed by process_logits</span>
<span class="n">inputs</span><span class="p">[</span><span class="s1">&#39;draft_tokens&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">draft_tokens</span>
<span class="n">inputs</span><span class="p">[</span><span class="s1">&#39;draft_indices&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">draft_indices</span>
<span class="n">inputs</span><span class="p">[</span><span class="s1">&#39;draft_probs&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">draft_probs</span>
<span class="n">inputs</span><span class="p">[</span>
<span class="s1">&#39;redrafter_inverted_temperature&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">redrafter_inverted_temperature</span>
<span class="n">inputs</span><span class="p">[</span><span class="s1">&#39;rand_data_validation&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">rand_data_validation</span>
<span class="n">inputs</span><span class="p">[</span><span class="s1">&#39;rand_data_sample&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">rand_data_sample</span>
<span class="n">inputs</span><span class="p">[</span><span class="s1">&#39;position_ids_base&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">position_ids_base</span>
<span class="k">return</span> <span class="n">inputs</span></div>
</div>
</pre></div>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
</div>
</footer>
</div>
<div class="bd-sidebar-secondary"></div>
</div>
<footer class="bd-footer-content">
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script defer src="../../../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf"></script>
<script defer src="../../../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf"></script>
<footer class="bd-footer">
<div class="bd-footer__inner bd-page-width">
<div class="footer-items__start">
<div class="footer-item">
<a class="footer-brand logo" href="https://www.nvidia.com">
<img src="../../../../_static/nvidia-logo-horiz-rgb-1c-blk-for-screen.svg" class="logo__image only-light" alt="NVIDIA"/>
<img src="../../../../_static/nvidia-logo-horiz-rgb-1c-wht-for-screen.svg" class="logo__image only-dark" alt="NVIDIA"/>
</a></div>
<div class="footer-item">
<div class="footer-links">
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/">Privacy Policy</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-center/">Manage My Privacy</a>
|
<a class="external" href="https://www.nvidia.com/en-us/preferences/start/">Do Not Sell or Share My Data</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/terms-of-service/">Terms of Service</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/accessibility/">Accessibility</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/company-policies/">Corporate Policies</a>
|
<a class="external" href="https://www.nvidia.com/en-us/product-security/">Product Security</a>
|
<a class="external" href="https://www.nvidia.com/en-us/contact/">Contact</a>
</div>
</div>
<div class="footer-item">
<p class="copyright">
Copyright © 2025, NVidia.
<br/>
</p>
</div>
</div>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink