mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
1387 lines
134 KiB
HTML
1387 lines
134 KiB
HTML
|
||
|
||
<!DOCTYPE html>
|
||
|
||
|
||
<html lang="en" data-content_root="../../../" >
|
||
|
||
<head>
|
||
<meta charset="utf-8" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||
<title>tensorrt_llm.layers.embedding — 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=933278ad" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css?v=76b2166b" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/autodoc_pydantic.css" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/togglebutton.css?v=13237357" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/custom.css?v=19d20f17" />
|
||
|
||
<!-- So that users can add custom icons -->
|
||
<script src="../../../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script>
|
||
<!-- Pre-loaded scripts that we'll load fully later -->
|
||
<link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" />
|
||
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" />
|
||
|
||
|
||
|
||
<script src="../../../_static/documentation_options.js?v=5929fcd5"></script>
|
||
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
|
||
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||
<script src="../../../_static/clipboard.min.js?v=a7894cd8"></script>
|
||
<script src="../../../_static/copybutton.js?v=65e89d2a"></script>
|
||
<script>let toggleHintShow = 'Click to show';</script>
|
||
<script>let toggleHintHide = 'Click to hide';</script>
|
||
<script>let toggleOpenOnPrint = 'true';</script>
|
||
<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
|
||
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
|
||
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
|
||
<script>DOCUMENTATION_OPTIONS.pagename = '_modules/tensorrt_llm/layers/embedding';</script>
|
||
<script>
|
||
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.2.0rc4';
|
||
DOCUMENTATION_OPTIONS.show_version_warning_banner =
|
||
false;
|
||
</script>
|
||
|
||
<link rel="icon" href="../../../_static/favicon.png"/>
|
||
|
||
<link rel="index" title="Index" href="../../../genindex.html" />
|
||
<link rel="search" title="Search" href="../../../search.html" />
|
||
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
||
<meta name="docsearch:language" content="en"/>
|
||
<meta name="docsearch:version" content="1.2.0rc4" />
|
||
|
||
|
||
</head>
|
||
|
||
|
||
|
||
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
|
||
|
||
|
||
|
||
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
|
||
|
||
|
||
|
||
<div id="pst-scroll-pixel-helper"></div>
|
||
|
||
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
|
||
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
|
||
|
||
|
||
<dialog id="pst-search-dialog">
|
||
|
||
<form class="bd-search d-flex align-items-center"
|
||
action="../../../search.html"
|
||
method="get">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<input type="search"
|
||
class="form-control"
|
||
name="q"
|
||
placeholder="Search the docs ..."
|
||
aria-label="Search the docs ..."
|
||
autocomplete="off"
|
||
autocorrect="off"
|
||
autocapitalize="off"
|
||
spellcheck="false"/>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
|
||
</form>
|
||
</dialog>
|
||
|
||
<div class="pst-async-banner-revealer d-none">
|
||
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
|
||
</div>
|
||
|
||
|
||
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
|
||
<div class="bd-header__inner bd-page-width">
|
||
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
|
||
<span class="fa-solid fa-bars"></span>
|
||
</button>
|
||
|
||
|
||
<div class="col-lg-3 navbar-header-items__start">
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
|
||
|
||
|
||
<a class="navbar-brand logo" href="../../../index.html">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<img src="../../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT LLM - Home"/>
|
||
<img src="../../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT LLM - Home"/>
|
||
|
||
|
||
<p class="title logo__title">TensorRT LLM</p>
|
||
|
||
</a></div>
|
||
|
||
</div>
|
||
|
||
<div class="col-lg-9 navbar-header-items">
|
||
|
||
<div class="me-auto navbar-header-items__center">
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
<div class="version-switcher__container dropdown pst-js-only">
|
||
<button id="pst-version-switcher-button-2"
|
||
type="button"
|
||
class="version-switcher__button btn btn-sm dropdown-toggle"
|
||
data-bs-toggle="dropdown"
|
||
aria-haspopup="listbox"
|
||
aria-controls="pst-version-switcher-list-2"
|
||
aria-label="Version switcher list"
|
||
>
|
||
Choose version <!-- this text may get changed later by javascript -->
|
||
<span class="caret"></span>
|
||
</button>
|
||
<div id="pst-version-switcher-list-2"
|
||
class="version-switcher__menu dropdown-menu list-group-flush py-0"
|
||
role="listbox" aria-labelledby="pst-version-switcher-button-2">
|
||
<!-- dropdown will be populated by javascript on page load -->
|
||
</div>
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="navbar-header-items__end">
|
||
|
||
<div class="navbar-item navbar-persistent--container">
|
||
|
||
|
||
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
</div>
|
||
|
||
|
||
<div class="navbar-item">
|
||
|
||
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
||
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
||
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
||
</button></div>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="navbar-persistent--mobile">
|
||
|
||
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
</header>
|
||
|
||
|
||
<div class="bd-container">
|
||
<div class="bd-container__inner bd-page-width">
|
||
|
||
|
||
|
||
<dialog id="pst-primary-sidebar-modal"></dialog>
|
||
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<a class="navbar-brand logo" href="../../../index.html">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<img src="../../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT LLM - Home"/>
|
||
<img src="../../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT LLM - Home"/>
|
||
|
||
|
||
<p class="title logo__title">TensorRT LLM</p>
|
||
|
||
</a>
|
||
|
||
|
||
|
||
<div class="sidebar-header-items sidebar-primary__section">
|
||
|
||
|
||
<div class="sidebar-header-items__center">
|
||
|
||
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
<div class="version-switcher__container dropdown pst-js-only">
|
||
<button id="pst-version-switcher-button-3"
|
||
type="button"
|
||
class="version-switcher__button btn btn-sm dropdown-toggle"
|
||
data-bs-toggle="dropdown"
|
||
aria-haspopup="listbox"
|
||
aria-controls="pst-version-switcher-list-3"
|
||
aria-label="Version switcher list"
|
||
>
|
||
Choose version <!-- this text may get changed later by javascript -->
|
||
<span class="caret"></span>
|
||
</button>
|
||
<div id="pst-version-switcher-list-3"
|
||
class="version-switcher__menu dropdown-menu list-group-flush py-0"
|
||
role="listbox" aria-labelledby="pst-version-switcher-button-3">
|
||
<!-- dropdown will be populated by javascript on page load -->
|
||
</div>
|
||
</div></div>
|
||
|
||
|
||
</div>
|
||
|
||
|
||
|
||
<div class="sidebar-header-items__end">
|
||
|
||
<div class="navbar-item">
|
||
|
||
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
||
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
||
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
||
</button></div>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
|
||
<div class="sidebar-primary-items__start sidebar-primary__section">
|
||
<div class="sidebar-primary-item">
|
||
|
||
|
||
|
||
<nav class="bd-docs-nav bd-links"
|
||
aria-label="Table of Contents">
|
||
<p class="bd-links__title" role="heading" aria-level="1">Table of Contents</p>
|
||
<div class="bd-toc-item navbar-nav"><p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../overview.html">Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../quick-start-guide.html">Quick Start Guide</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../installation/index.html">Installation</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../installation/containers.html">Pre-built release container images on NGC</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../installation/linux.html">Installing on Linux via <code class="docutils literal notranslate"><span class="pre">pip</span></code></a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Deployment Guide</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../examples/llm_api_examples.html">LLM Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference.html">Generate text</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_async.html">Generate text asynchronously</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_async_streaming.html">Generate text in streaming</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_logits_processor.html">Control generated text using logits processor</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_sparse_attention.html">Sparse Attention</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_speculative_decoding.html">Speculative Decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_kv_cache_connector.html">KV Cache Connector</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_kv_cache_offloading.html">KV Cache Offloading</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_runtime.html">Runtime Configuration Examples</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_sampling.html">Sampling Techniques Showcase</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_llm_distributed.html">Run LLM-API with pytorch backend on Slurm</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_trtllm_bench.html">Run trtllm-bench with pytorch backend on Slurm</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_trtllm_serve.html">Run trtllm-serve with pytorch backend on Slurm</a></li>
|
||
</ul>
|
||
</details></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../examples/trtllm_serve_examples.html">Online Serving Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/curl_chat_client.html">Curl Chat Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/curl_completion_client.html">Curl Completion Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/genai_perf_client.html">Genai Perf Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/genai_perf_client_for_multimodal.html">Genai Perf Client For Multimodal</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_chat_client.html">OpenAI Chat Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_chat_client_for_multimodal.html">OpenAI Chat Client for Multimodal</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client_for_lora.html">Openai Completion Client For Lora</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client_json_schema.html">OpenAI Completion Client with JSON Schema</a></li>
|
||
</ul>
|
||
</details></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../examples/dynamo_k8s_example.html">Dynamo K8s Example</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../deployment-guide/index.html">Model Recipes</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/deployment-guide-for-deepseek-r1-on-trtllm.html">Deployment Guide for DeepSeek R1 on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/deployment-guide-for-llama3.3-70b-on-trtllm.html">Deployment Guide for Llama3.3 70B on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/deployment-guide-for-llama4-scout-on-trtllm.html">Deployment Guide for Llama4 Scout 17B on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/deployment-guide-for-gpt-oss-on-trtllm.html">Deployment Guide for GPT-OSS on TensorRT-LLM - Blackwell Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/deployment-guide-for-qwen3-next-on-trtllm.html">Deployment Guide for Qwen3 Next on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Models</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../models/supported-models.html">Supported Models</a></li>
|
||
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../models/adding-new-model.html">Adding a New Model</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">CLI Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-bench.html">trtllm-bench</a></li>
|
||
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-eval.html">trtllm-eval</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../commands/trtllm-serve/index.html">trtllm-serve</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../commands/trtllm-serve/trtllm-serve.html">trtllm-serve</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../commands/trtllm-serve/run-benchmark-with-trtllm-serve.html">Run benchmarking with <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code></a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">API Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api/index.html">LLM API Introduction</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api/reference.html">API Reference</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Features</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/feature-combination-matrix.html">Feature Combination Matrix</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/disagg-serving.html">Disaggregated Serving</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/kvcache.html">KV Cache System</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/long-sequence.html">Long Sequences</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/lora.html">LoRA (Low-Rank Adaptation)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/multi-modality.html">Multimodal Support in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/overlap-scheduler.html">Overlap Scheduler</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/paged-attention-ifb-scheduler.html">Paged Attention, IFB, and Request Scheduling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/parallel-strategy.html">Parallelism in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/quantization.html">Quantization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/sampling.html">Sampling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/additional-outputs.html">Additional Outputs</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/speculative-decoding.html">Speculative Decoding</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/checkpoint-loading.html">Checkpoint Loading</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/auto_deploy/auto-deploy.html">AutoDeploy (Prototype)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/ray-orchestrator.html">Ray Orchestrator (Prototype)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/torch_compile_and_piecewise_cuda_graph.html">Torch Compile & Piecewise CUDA Graph</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Developer Guide</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/overview.html">Architecture Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/perf-analysis.html">Performance Analysis</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/perf-benchmarking.html">TensorRT LLM Benchmarking</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/ci-overview.html">Continuous Integration Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/dev-containers.html">Using Dev Containers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/api-change.html">LLM API Change Guide</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/kv-transfer.html">Introduction to KV Cache Transmission</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog10_ADP_Balance_Strategy.html">ADP Balance Strategy</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog11_GPT_OSS_Eagle3.html">Running GPT-OSS-120B with Eagle3 Speculative Decoding on GB200/B200 (TensorRT LLM)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.html">Combining Guided Decoding and Speculative Decoding: Making CPU and GPU Cooperate Seamlessly</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog13_Inference_Time_Compute_Implementation_in_TensorRT-LLM.html">Inference Time Compute Implementation in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog14_Scaling_Expert_Parallelism_in_TensorRT-LLM_part3.html">Scaling Expert Parallelism in TensorRT LLM (Part 3: Pushing the Performance Boundary)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html">Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html">DeepSeek R1 MTP Implementation and Optimization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html">Optimizing DeepSeek R1 Throughput on NVIDIA Blackwell GPUs: A Deep Dive for Developers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html">Scaling Expert Parallelism in TensorRT LLM (Part 1: Design and Implementation of Large-scale EP)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html">Disaggregated Serving in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html">How to launch Llama4 Maverick + Eagle3 TensorRT LLM server</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html">N-Gram Speculative Decoding in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html">Scaling Expert Parallelism in TensorRT LLM (Part 2: Performance Status and Optimization)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html">Running a High Performance GPT-OSS-120B Inference Server with TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.html">How to get best performance on DeepSeek-R1 in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Quick Links</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/releases">Releases</a></li>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM">Github Code</a></li>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/issues?q=is%3Aissue%20state%3Aopen%20label%3Aroadmap">Roadmap</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Use TensorRT Engine</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../legacy/tensorrt_quickstart.html">LLM API with TensorRT Engine</a></li>
|
||
</ul>
|
||
</div>
|
||
</nav></div>
|
||
</div>
|
||
|
||
|
||
<div class="sidebar-primary-items__end sidebar-primary__section">
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
<main id="main-content" class="bd-main" role="main">
|
||
|
||
|
||
<div class="bd-content">
|
||
<div class="bd-article-container">
|
||
|
||
<div class="bd-header-article d-print-none">
|
||
<div class="header-article-items header-article__inner">
|
||
|
||
<div class="header-article-items__start">
|
||
|
||
<div class="header-article-item">
|
||
|
||
<nav aria-label="Breadcrumb" class="d-print-none">
|
||
<ul class="bd-breadcrumbs">
|
||
|
||
<li class="breadcrumb-item breadcrumb-home">
|
||
<a href="../../../index.html" class="nav-link" aria-label="Home">
|
||
<i class="fa-solid fa-home"></i>
|
||
</a>
|
||
</li>
|
||
|
||
<li class="breadcrumb-item"><a href="../../index.html" class="nav-link">Module code</a></li>
|
||
|
||
<li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">tensorrt_llm.layers.embedding</span></li>
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<div id="searchbox"></div>
|
||
<article class="bd-article">
|
||
|
||
<h1>Source code for tensorrt_llm.layers.embedding</h1><div class="highlight"><pre>
|
||
<span></span><span class="c1"># SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.</span>
|
||
<span class="c1"># SPDX-License-Identifier: Apache-2.0</span>
|
||
<span class="c1">#</span>
|
||
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
||
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
||
<span class="c1"># You may obtain a copy of the License at</span>
|
||
<span class="c1">#</span>
|
||
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
||
<span class="c1">#</span>
|
||
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
||
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
||
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
||
<span class="c1"># See the License for the specific language governing permissions and</span>
|
||
<span class="c1"># limitations under the License.</span>
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">math</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Sequence</span><span class="p">,</span> <span class="n">Union</span>
|
||
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">numpy</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">np</span>
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</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">set_obj_attrs</span><span class="p">,</span> <span class="n">str_dtype_to_torch</span><span class="p">,</span> <span class="n">trt_dtype_to_np</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">..functional</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span><span class="n">ACT2FN</span><span class="p">,</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">arange</span><span class="p">,</span> <span class="n">concat</span><span class="p">,</span> <span class="n">constant</span><span class="p">,</span> <span class="n">cos</span><span class="p">,</span> <span class="n">div</span><span class="p">,</span>
|
||
<span class="n">embedding</span><span class="p">,</span> <span class="n">exp</span><span class="p">,</span> <span class="n">expand</span><span class="p">,</span> <span class="n">identity</span><span class="p">,</span> <span class="n">meshgrid2d</span><span class="p">,</span> <span class="n">outer</span><span class="p">,</span>
|
||
<span class="n">pad</span><span class="p">,</span> <span class="n">shape</span><span class="p">,</span> <span class="n">sin</span><span class="p">,</span> <span class="nb">slice</span><span class="p">,</span> <span class="n">unsqueeze</span><span class="p">,</span> <span class="n">where</span><span class="p">)</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">..mapping</span><span class="w"> </span><span class="kn">import</span> <span class="n">Mapping</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">..module</span><span class="w"> </span><span class="kn">import</span> <span class="n">Module</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">..parameter</span><span class="w"> </span><span class="kn">import</span> <span class="n">Parameter</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">.linear</span><span class="w"> </span><span class="kn">import</span> <span class="n">ColumnLinear</span><span class="p">,</span> <span class="n">Linear</span><span class="p">,</span> <span class="n">RowLinear</span>
|
||
|
||
|
||
<div class="viewcode-block" id="Embedding">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.Embedding">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">Embedding</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""</span>
|
||
<span class="sd"> The embedding layer takes input indices (x) and the embedding lookup table (weight) as input.</span>
|
||
<span class="sd"> And output the corresponding embeddings according to input indices.</span>
|
||
<span class="sd"> The size of weight is [num_embeddings, embedding_dim]</span>
|
||
|
||
<span class="sd"> Four parameters (tp_size, tp_group, sharding_dim, tp_rank) are involved in tensor parallelism.</span>
|
||
<span class="sd"> Only when "tp_size > 1 and tp_group is not None", tensor parallelism is enabled.</span>
|
||
<span class="sd"> When "sharding_dim == 0", the weight is shared in the vocabulary dimension.</span>
|
||
<span class="sd"> tp_rank must be set when sharding_dim == 0.</span>
|
||
<span class="sd"> When "sharding_dim == 1", the weight is shard in the hidden dimension.</span>
|
||
<span class="sd"> """</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">num_embeddings</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||
<span class="n">embedding_dim</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">tp_size</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
|
||
<span class="n">tp_group</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">list</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">sharding_dim</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span>
|
||
<span class="n">tp_rank</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
|
||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
||
<span class="c1"># num_embeddings records the total vocab size no matter using TP or not</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">num_embeddings</span> <span class="o">=</span> <span class="n">num_embeddings</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">embedding_dim</span> <span class="o">=</span> <span class="n">embedding_dim</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">=</span> <span class="n">tp_size</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">tp_group</span> <span class="o">=</span> <span class="n">tp_group</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">sharding_dim</span> <span class="o">=</span> <span class="n">sharding_dim</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">tp_rank</span> <span class="o">=</span> <span class="n">tp_rank</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">dtype</span> <span class="o">=</span> <span class="n">dtype</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">tp_dim</span> <span class="o">=</span> <span class="n">sharding_dim</span>
|
||
|
||
<span class="k">if</span> <span class="n">sharding_dim</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
|
||
<span class="n">shape</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_embeddings</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">embedding_dim</span> <span class="o">//</span> <span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">sharding_dim</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
||
<span class="n">shape</span> <span class="o">=</span> <span class="p">(</span><span class="n">math</span><span class="o">.</span><span class="n">ceil</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_embeddings</span> <span class="o">/</span> <span class="bp">self</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">embedding_dim</span><span class="p">)</span>
|
||
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">weight</span> <span class="o">=</span> <span class="n">Parameter</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="n">shape</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span>
|
||
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">weight_padding_size</span> <span class="o">=</span> <span class="p">((</span><span class="mi">8</span> <span class="o">-</span> <span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">%</span> <span class="mi">8</span><span class="p">)</span> <span class="o">%</span> <span class="mi">8</span><span class="p">,</span> <span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
|
||
|
||
<span class="n">set_obj_attrs</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">weight</span><span class="p">,</span> <span class="p">{</span>
|
||
<span class="s2">"weight_loader"</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight_loader</span><span class="p">,</span>
|
||
<span class="p">})</span>
|
||
|
||
<div class="viewcode-block" id="Embedding.forward">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.Embedding.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="n">x</span><span class="p">):</span>
|
||
<span class="c1"># The embedding weight is padded to the multiple of 8.</span>
|
||
<span class="c1"># The reason is that when lm_head and vocab_embedding are using the same embedding weight,</span>
|
||
<span class="c1"># previously weights can't be depulicated in the engine because gemm will pad the weight to the multiple of 8.</span>
|
||
<span class="c1"># If we also pad the embedding weight to the multiple of 8, the weights can be successfully deduplicated.</span>
|
||
<span class="c1"># This will not affect the input and output of the gather op and perf impact is negligible.</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight_padding_size</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
|
||
<span class="n">padding_values</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">weight_padding_size</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">trt_dtype_to_np</span><span class="p">(</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">value</span><span class="o">.</span><span class="n">dtype</span><span class="p">))</span>
|
||
<span class="n">padding</span> <span class="o">=</span> <span class="n">constant</span><span class="p">(</span><span class="n">padding_values</span><span class="p">)</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">padding</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
||
<span class="k">return</span> <span class="n">embedding</span><span class="p">(</span><span class="n">x</span><span class="p">,</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">value</span><span class="p">,</span>
|
||
<span class="n">tp_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span><span class="p">,</span>
|
||
<span class="n">tp_group</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">tp_group</span><span class="p">,</span>
|
||
<span class="n">sharding_dim</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">sharding_dim</span><span class="p">,</span>
|
||
<span class="n">tp_rank</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">tp_rank</span><span class="p">,</span>
|
||
<span class="n">padding</span><span class="o">=</span><span class="n">padding</span><span class="p">)</span></div>
|
||
|
||
|
||
<div class="viewcode-block" id="Embedding.weight_loader">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.Embedding.weight_loader">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">weight_loader</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">mapping</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">,</span> <span class="n">param</span><span class="p">:</span> <span class="n">Parameter</span><span class="p">,</span>
|
||
<span class="n">loaded_weight</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span>
|
||
<span class="c1"># use_parallel_embedding</span>
|
||
<span class="n">tp_rank</span> <span class="o">=</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_rank</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">></span> <span class="mi">1</span><span class="p">:</span>
|
||
<span class="n">sharding_dim</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">sharding_dim</span>
|
||
<span class="n">shard_size</span> <span class="o">=</span> <span class="n">param</span><span class="o">.</span><span class="n">_shape</span><span class="p">[</span><span class="n">sharding_dim</span><span class="p">]</span>
|
||
<span class="n">start_idx</span> <span class="o">=</span> <span class="n">tp_rank</span> <span class="o">*</span> <span class="n">shard_size</span>
|
||
<span class="n">loaded_weight</span> <span class="o">=</span> <span class="n">loaded_weight</span><span class="o">.</span><span class="n">narrow</span><span class="p">(</span><span class="n">sharding_dim</span><span class="p">,</span> <span class="n">start_idx</span><span class="p">,</span>
|
||
<span class="n">shard_size</span><span class="p">)</span>
|
||
<span class="n">param</span><span class="o">.</span><span class="n">value</span> <span class="o">=</span> <span class="n">loaded_weight</span></div>
|
||
|
||
|
||
<div class="viewcode-block" id="Embedding.postprocess">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.Embedding.postprocess">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">postprocess</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tllm_key</span><span class="p">,</span> <span class="n">weights</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
||
<span class="k">if</span> <span class="n">weights</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="p">{}</span>
|
||
<span class="n">weights</span> <span class="o">=</span> <span class="n">weights</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">str_dtype_to_torch</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="k">return</span> <span class="p">{</span><span class="n">tllm_key</span><span class="p">:</span> <span class="n">weights</span><span class="p">}</span></div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="PromptTuningEmbedding">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.PromptTuningEmbedding">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">PromptTuningEmbedding</span><span class="p">(</span><span class="n">Embedding</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""</span>
|
||
<span class="sd"> PromptTuningEmbedding handles fine-tuned prompts with virtual tokens. At runtime,</span>
|
||
<span class="sd"> a supplementary embedding dictionary is passed. Tokens whose ids are >= vocab_size are embedded</span>
|
||
<span class="sd"> with that additional dictionary.</span>
|
||
<span class="sd"> The prompt tuning dictionary holds multiple tasks, and each sequence is assigned a given task.</span>
|
||
<span class="sd"> Prompt-tuned tokens from a given sequence use the adequate task dictionary, as defined by the `tasks` input.</span>
|
||
<span class="sd"> """</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">num_embeddings</span><span class="p">,</span>
|
||
<span class="n">embedding_dim</span><span class="p">,</span>
|
||
<span class="n">vocab_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">tp_size</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
|
||
<span class="n">tp_group</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">sharding_dim</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
|
||
<span class="n">tp_rank</span><span class="o">=</span><span class="mi">0</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">num_embeddings</span><span class="p">,</span> <span class="n">embedding_dim</span><span class="p">,</span> <span class="n">dtype</span><span class="p">,</span> <span class="n">tp_size</span><span class="p">,</span>
|
||
<span class="n">tp_group</span><span class="p">,</span> <span class="n">sharding_dim</span><span class="p">,</span> <span class="n">tp_rank</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">vocab_size</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="n">vocab_size</span> <span class="o">=</span> <span class="n">num_embeddings</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">vocab_size</span> <span class="o">=</span> <span class="n">vocab_size</span>
|
||
|
||
<div class="viewcode-block" id="PromptTuningEmbedding.forward">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.PromptTuningEmbedding.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="n">tokens</span><span class="p">,</span> <span class="n">prompt_embedding_table</span><span class="p">,</span> <span class="n">tasks</span><span class="p">,</span> <span class="n">task_vocab_size</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""</span>
|
||
<span class="sd"> Pass all tokens through both normal and prompt embedding tables.</span>
|
||
<span class="sd"> Tokens are masked so that "normal" embedding only see "normal" tokens. Same logic for "prompt" embedding.</span>
|
||
<span class="sd"> After those two embedding, combine results based on whether the token was "normal" or "prompt-tuned".</span>
|
||
|
||
<span class="sd"> Parameters:</span>
|
||
<span class="sd"> tokens : Tensor</span>
|
||
<span class="sd"> the ids to embed, size [batch_size, seq_len]</span>
|
||
|
||
<span class="sd"> prompt_embedding_table : Tensor</span>
|
||
<span class="sd"> the additional embedding table for prompt-tuned tokens, size [num_tasks * num_tokens_per_task, hidden_size]</span>
|
||
|
||
<span class="sd"> tasks: Tensor</span>
|
||
<span class="sd"> the task required by each token, size [batch_size, seq_len]</span>
|
||
|
||
<span class="sd"> task_vocab_size: Tensor</span>
|
||
<span class="sd"> the number of tokens used for each task, should be equal to prompt_embedding_table's num_tokens_per_task, size [1]</span>
|
||
|
||
<span class="sd"> Returns:</span>
|
||
<span class="sd"> Tokens' embedding</span>
|
||
<span class="sd"> """</span>
|
||
<span class="c1"># do not use ">=" because internally the layer works with floating points</span>
|
||
<span class="n">prompt_tokens_mask</span> <span class="o">=</span> <span class="n">tokens</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="o">-</span> <span class="mi">1</span><span class="p">)</span>
|
||
|
||
<span class="c1"># clip tokens in the [0, vocab_size) range</span>
|
||
<span class="n">normal_tokens</span> <span class="o">=</span> <span class="n">where</span><span class="p">(</span><span class="n">prompt_tokens_mask</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="mi">1</span><span class="p">,</span> <span class="n">tokens</span><span class="p">)</span>
|
||
<span class="n">normal_embeddings</span> <span class="o">=</span> <span class="n">embedding</span><span class="p">(</span><span class="n">normal_tokens</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">value</span><span class="p">,</span>
|
||
<span class="bp">self</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">tp_group</span><span class="p">,</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">sharding_dim</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">tp_rank</span><span class="p">)</span>
|
||
|
||
<span class="c1"># put virtual tokens in the [0, max_prompt_vocab_size) range</span>
|
||
<span class="n">prompt_tokens</span> <span class="o">=</span> <span class="n">where</span><span class="p">(</span><span class="n">prompt_tokens_mask</span><span class="p">,</span> <span class="n">tokens</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
|
||
<span class="c1"># add offsets to match the concatenated embedding tables</span>
|
||
<span class="n">tasks</span> <span class="o">=</span> <span class="n">tasks</span> <span class="o">*</span> <span class="n">task_vocab_size</span>
|
||
|
||
<span class="c1"># tasks: [batch_size, seq_len]</span>
|
||
<span class="c1"># prompt_tokens: [batch_size, seq_len]</span>
|
||
<span class="c1"># if speculative decoding is enabled the shape of prompt_tokens is [batch_size, seq_len + max_draft_len],</span>
|
||
<span class="c1"># so we need to expand tasks to [batch_size, seq_len + max_draft_len]</span>
|
||
<span class="n">tasks</span> <span class="o">=</span> <span class="n">expand</span><span class="p">(</span><span class="n">tasks</span><span class="p">,</span> <span class="n">shape</span><span class="p">(</span><span class="n">prompt_tokens</span><span class="p">))</span>
|
||
<span class="n">prompt_tokens</span> <span class="o">=</span> <span class="n">prompt_tokens</span> <span class="o">+</span> <span class="n">tasks</span>
|
||
<span class="n">prompt_embeddings</span> <span class="o">=</span> <span class="n">embedding</span><span class="p">(</span><span class="n">prompt_tokens</span><span class="p">,</span> <span class="n">prompt_embedding_table</span><span class="p">)</span>
|
||
|
||
<span class="c1"># prompt_tokens_mask: [batch_size, seq_len] -> [batch_size, seq_len, 1]</span>
|
||
<span class="c1"># combine the correct sources of embedding: normal/prompt</span>
|
||
<span class="k">return</span> <span class="n">where</span><span class="p">(</span><span class="n">unsqueeze</span><span class="p">(</span><span class="n">prompt_tokens_mask</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">),</span> <span class="n">prompt_embeddings</span><span class="p">,</span>
|
||
<span class="n">normal_embeddings</span><span class="p">)</span></div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="LabelEmbedding">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.LabelEmbedding">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">LabelEmbedding</span><span class="p">(</span><span class="n">Module</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">num_classes</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||
<span class="n">hidden_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||
<span class="n">dropout_prob</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
|
||
<span class="n">mapping</span><span class="o">=</span><span class="n">Mapping</span><span class="p">(),</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</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">use_cfg_embedding</span> <span class="o">=</span> <span class="n">dropout_prob</span> <span class="o">></span> <span class="mi">0</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">embedding_table</span> <span class="o">=</span> <span class="n">Embedding</span><span class="p">(</span><span class="n">num_classes</span> <span class="o">+</span> <span class="n">use_cfg_embedding</span><span class="p">,</span>
|
||
<span class="n">hidden_size</span><span class="p">,</span>
|
||
<span class="n">tp_size</span><span class="o">=</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">,</span>
|
||
<span class="n">tp_group</span><span class="o">=</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_group</span><span class="p">,</span>
|
||
<span class="n">dtype</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">num_classes</span> <span class="o">=</span> <span class="n">num_classes</span>
|
||
|
||
<div class="viewcode-block" id="LabelEmbedding.token_drop">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.LabelEmbedding.token_drop">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">token_drop</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">labels</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">force_drop_ids</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">):</span>
|
||
<span class="n">labels</span> <span class="o">=</span> <span class="n">where</span><span class="p">(</span><span class="n">force_drop_ids</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_classes</span><span class="p">,</span> <span class="n">labels</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">labels</span></div>
|
||
|
||
|
||
<div class="viewcode-block" id="LabelEmbedding.forward">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.LabelEmbedding.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="n">labels</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">force_drop_ids</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Tensor</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
|
||
<span class="k">if</span> <span class="n">force_drop_ids</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="n">labels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">token_drop</span><span class="p">(</span><span class="n">labels</span><span class="p">,</span> <span class="n">force_drop_ids</span><span class="p">)</span>
|
||
<span class="n">embeddings</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">embedding_table</span><span class="p">(</span><span class="n">labels</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">embeddings</span></div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="get_1d_sincos_pos_embed_from_grid">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.get_1d_sincos_pos_embed_from_grid">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">get_1d_sincos_pos_embed_from_grid</span><span class="p">(</span><span class="n">embed_dim</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">pos</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">):</span>
|
||
<span class="k">if</span> <span class="n">embed_dim</span> <span class="o">%</span> <span class="mi">2</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
|
||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"embed_dim must be divisible by 2"</span><span class="p">)</span>
|
||
|
||
<span class="n">omega</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="n">embed_dim</span> <span class="o">//</span> <span class="mi">2</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span>
|
||
<span class="n">omega</span> <span class="o">/=</span> <span class="n">embed_dim</span> <span class="o">/</span> <span class="mf">2.0</span>
|
||
<span class="n">omega</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">/</span> <span class="mi">10000</span><span class="o">**</span><span class="n">omega</span> <span class="c1"># (D/2,)</span>
|
||
<span class="n">omega</span> <span class="o">=</span> <span class="n">constant</span><span class="p">(</span><span class="n">omega</span><span class="o">.</span><span class="n">numpy</span><span class="p">()</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">))</span>
|
||
|
||
<span class="n">pos</span> <span class="o">=</span> <span class="n">pos</span><span class="o">.</span><span class="n">view</span><span class="p">([</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span> <span class="c1"># (M,)</span>
|
||
<span class="n">out</span> <span class="o">=</span> <span class="n">outer</span><span class="p">(</span><span class="n">pos</span><span class="p">,</span> <span class="n">omega</span><span class="p">)</span> <span class="c1"># (M, D/2), outer product</span>
|
||
|
||
<span class="n">emb_sin</span> <span class="o">=</span> <span class="n">sin</span><span class="p">(</span><span class="n">out</span><span class="p">)</span> <span class="c1"># (M, D/2)</span>
|
||
<span class="n">emb_cos</span> <span class="o">=</span> <span class="n">cos</span><span class="p">(</span><span class="n">out</span><span class="p">)</span> <span class="c1"># (M, D/2)</span>
|
||
|
||
<span class="n">emb</span> <span class="o">=</span> <span class="n">concat</span><span class="p">([</span><span class="n">emb_sin</span><span class="p">,</span> <span class="n">emb_cos</span><span class="p">],</span> <span class="n">dim</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> <span class="c1"># (M, D)</span>
|
||
<span class="k">return</span> <span class="n">emb</span></div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="get_2d_sincos_pos_embed_from_grid">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.get_2d_sincos_pos_embed_from_grid">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">get_2d_sincos_pos_embed_from_grid</span><span class="p">(</span><span class="n">embed_dim</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">grid</span><span class="p">:</span> <span class="n">Sequence</span><span class="p">[</span><span class="n">Tensor</span><span class="p">]):</span>
|
||
<span class="k">if</span> <span class="n">embed_dim</span> <span class="o">%</span> <span class="mi">2</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
|
||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"embed_dim must be divisible by 2"</span><span class="p">)</span>
|
||
|
||
<span class="c1"># use half of dimensions to encode grid_h</span>
|
||
<span class="n">emb_h</span> <span class="o">=</span> <span class="n">get_1d_sincos_pos_embed_from_grid</span><span class="p">(</span><span class="n">embed_dim</span> <span class="o">//</span> <span class="mi">2</span><span class="p">,</span>
|
||
<span class="n">grid</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="c1"># (H*W, D/2)</span>
|
||
<span class="n">emb_w</span> <span class="o">=</span> <span class="n">get_1d_sincos_pos_embed_from_grid</span><span class="p">(</span><span class="n">embed_dim</span> <span class="o">//</span> <span class="mi">2</span><span class="p">,</span>
|
||
<span class="n">grid</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> <span class="c1"># (H*W, D/2)</span>
|
||
|
||
<span class="n">emb</span> <span class="o">=</span> <span class="n">concat</span><span class="p">([</span><span class="n">emb_h</span><span class="p">,</span> <span class="n">emb_w</span><span class="p">],</span> <span class="n">dim</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> <span class="c1"># (H*W, D)</span>
|
||
<span class="k">return</span> <span class="n">emb</span></div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="get_2d_sincos_pos_embed">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.get_2d_sincos_pos_embed">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">get_2d_sincos_pos_embed</span><span class="p">(</span>
|
||
<span class="n">embed_dim</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||
<span class="n">grid_size</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="n">Sequence</span><span class="p">[</span><span class="nb">int</span><span class="p">]],</span>
|
||
<span class="n">cls_token</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">extra_tokens</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span>
|
||
<span class="n">interpolation_scale</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span>
|
||
<span class="n">base_size</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">16</span><span class="p">,</span>
|
||
<span class="p">):</span>
|
||
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">grid_size</span><span class="p">,</span> <span class="nb">int</span><span class="p">):</span>
|
||
<span class="n">grid_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">grid_size</span><span class="p">,</span> <span class="n">grid_size</span><span class="p">)</span>
|
||
|
||
<span class="n">grid_h</span> <span class="o">=</span> <span class="n">div</span><span class="p">(</span>
|
||
<span class="n">div</span><span class="p">(</span><span class="n">arange</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">grid_size</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="s1">'float32'</span><span class="p">),</span>
|
||
<span class="nb">float</span><span class="p">(</span><span class="n">grid_size</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">/</span> <span class="n">base_size</span><span class="p">)),</span> <span class="n">interpolation_scale</span><span class="p">)</span>
|
||
<span class="n">grid_w</span> <span class="o">=</span> <span class="n">div</span><span class="p">(</span>
|
||
<span class="n">div</span><span class="p">(</span><span class="n">arange</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">grid_size</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="s1">'float32'</span><span class="p">),</span>
|
||
<span class="nb">float</span><span class="p">(</span><span class="n">grid_size</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">/</span> <span class="n">base_size</span><span class="p">)),</span> <span class="n">interpolation_scale</span><span class="p">)</span>
|
||
<span class="n">grid_h</span><span class="p">,</span> <span class="n">grid_w</span> <span class="o">=</span> <span class="n">meshgrid2d</span><span class="p">(</span><span class="n">grid_w</span><span class="p">,</span> <span class="n">grid_h</span><span class="p">)</span> <span class="c1"># here w goes first</span>
|
||
<span class="n">pos_embed</span> <span class="o">=</span> <span class="n">get_2d_sincos_pos_embed_from_grid</span><span class="p">(</span><span class="n">embed_dim</span><span class="p">,</span> <span class="p">[</span>
|
||
<span class="n">grid_h</span><span class="o">.</span><span class="n">view</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="n">grid_size</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">grid_size</span><span class="p">[</span><span class="mi">0</span><span class="p">]]),</span>
|
||
<span class="n">grid_w</span><span class="o">.</span><span class="n">view</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="n">grid_size</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">grid_size</span><span class="p">[</span><span class="mi">0</span><span class="p">]])</span>
|
||
<span class="p">])</span>
|
||
<span class="k">if</span> <span class="n">cls_token</span> <span class="ow">and</span> <span class="n">extra_tokens</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
|
||
<span class="n">pos_embed</span> <span class="o">=</span> <span class="n">concat</span><span class="p">([</span>
|
||
<span class="n">constant</span><span class="p">(</span>
|
||
<span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">extra_tokens</span><span class="p">,</span> <span class="n">embed_dim</span><span class="p">),</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">trt_dtype_to_np</span><span class="p">(</span><span class="n">pos_embed</span><span class="o">.</span><span class="n">dtype</span><span class="p">))),</span> <span class="n">pos_embed</span>
|
||
<span class="p">],</span>
|
||
<span class="n">dim</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">pos_embed</span></div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="SD3PatchEmbed">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.SD3PatchEmbed">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">SD3PatchEmbed</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""</span>
|
||
<span class="sd"> 2D Image to Patch Embedding with support for SD3 cropping.</span>
|
||
<span class="sd"> """</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">height</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">224</span><span class="p">,</span>
|
||
<span class="n">width</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">224</span><span class="p">,</span>
|
||
<span class="n">patch_size</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">16</span><span class="p">,</span>
|
||
<span class="n">in_channels</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">3</span><span class="p">,</span>
|
||
<span class="n">embed_dim</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">768</span><span class="p">,</span>
|
||
<span class="n">layer_norm</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">flatten</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">bias</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">interpolation_scale</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
|
||
<span class="n">pos_embed_type</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"sincos"</span><span class="p">,</span>
|
||
<span class="n">pos_embed_max_size</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="c1"># For SD3 cropping</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">diffusers.models.embeddings</span><span class="w"> </span><span class="kn">import</span> \
|
||
<span class="n">get_2d_sincos_pos_embed</span> <span class="k">as</span> <span class="n">get_2d_sincos_pos_embed_torch</span>
|
||
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">.conv</span><span class="w"> </span><span class="kn">import</span> <span class="n">Conv2d</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">.normalization</span><span class="w"> </span><span class="kn">import</span> <span class="n">LayerNorm</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">num_patches</span> <span class="o">=</span> <span class="p">(</span><span class="n">height</span> <span class="o">//</span> <span class="n">patch_size</span><span class="p">)</span> <span class="o">*</span> <span class="p">(</span><span class="n">width</span> <span class="o">//</span> <span class="n">patch_size</span><span class="p">)</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">flatten</span> <span class="o">=</span> <span class="n">flatten</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">layer_norm</span> <span class="o">=</span> <span class="n">layer_norm</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_max_size</span> <span class="o">=</span> <span class="n">pos_embed_max_size</span>
|
||
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">proj</span> <span class="o">=</span> <span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,</span>
|
||
<span class="n">embed_dim</span><span class="p">,</span>
|
||
<span class="n">kernel_size</span><span class="o">=</span><span class="p">(</span><span class="n">patch_size</span><span class="p">,</span> <span class="n">patch_size</span><span class="p">),</span>
|
||
<span class="n">stride</span><span class="o">=</span><span class="p">(</span><span class="n">patch_size</span><span class="p">,</span> <span class="n">patch_size</span><span class="p">),</span>
|
||
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">layer_norm</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">norm</span> <span class="o">=</span> <span class="n">LayerNorm</span><span class="p">(</span><span class="n">embed_dim</span><span class="p">,</span>
|
||
<span class="n">elementwise_affine</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">eps</span><span class="o">=</span><span class="mf">1e-6</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">norm</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">patch_size</span> <span class="o">=</span> <span class="n">patch_size</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">height</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">width</span> <span class="o">=</span> <span class="n">height</span> <span class="o">//</span> <span class="n">patch_size</span><span class="p">,</span> <span class="n">width</span> <span class="o">//</span> <span class="n">patch_size</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">base_size</span> <span class="o">=</span> <span class="n">height</span> <span class="o">//</span> <span class="n">patch_size</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">interpolation_scale</span> <span class="o">=</span> <span class="n">interpolation_scale</span>
|
||
|
||
<span class="c1"># Calculate positional embeddings based on max size or default</span>
|
||
<span class="k">if</span> <span class="n">pos_embed_max_size</span><span class="p">:</span>
|
||
<span class="n">grid_size</span> <span class="o">=</span> <span class="n">pos_embed_max_size</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">grid_size</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">num_patches</span><span class="o">**</span><span class="mf">0.5</span><span class="p">)</span>
|
||
|
||
<span class="k">if</span> <span class="n">pos_embed_type</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">pos_embed</span> <span class="o">=</span> <span class="kc">None</span>
|
||
<span class="k">elif</span> <span class="n">pos_embed_type</span> <span class="o">==</span> <span class="s2">"sincos"</span><span class="p">:</span>
|
||
<span class="n">pos_embed</span> <span class="o">=</span> <span class="n">get_2d_sincos_pos_embed_torch</span><span class="p">(</span>
|
||
<span class="n">embed_dim</span><span class="p">,</span>
|
||
<span class="n">grid_size</span><span class="p">,</span>
|
||
<span class="n">base_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">base_size</span><span class="p">,</span>
|
||
<span class="n">interpolation_scale</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">interpolation_scale</span><span class="p">,</span>
|
||
<span class="n">output_type</span><span class="o">=</span><span class="s2">"pt"</span><span class="p">,</span>
|
||
<span class="p">)</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">pos_embed</span> <span class="o">=</span> <span class="n">Parameter</span><span class="p">(</span>
|
||
<span class="n">pos_embed</span><span class="o">.</span><span class="n">detach</span><span class="p">()</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span><span class="o">.</span><span class="n">float</span><span class="p">()</span><span class="o">.</span><span class="n">unsqueeze</span><span class="p">(</span><span class="mi">0</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
|
||
<span class="sa">f</span><span class="s2">"Unsupported pos_embed_type: </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_type</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
||
|
||
<div class="viewcode-block" id="SD3PatchEmbed.cropped_pos_embed">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.SD3PatchEmbed.cropped_pos_embed">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">cropped_pos_embed</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""Crops positional embeddings for SD3 compatibility."""</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_max_size</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"`pos_embed_max_size` must be set for cropping."</span><span class="p">)</span>
|
||
|
||
<span class="n">height</span> <span class="o">=</span> <span class="n">height</span> <span class="o">//</span> <span class="bp">self</span><span class="o">.</span><span class="n">patch_size</span>
|
||
<span class="n">width</span> <span class="o">=</span> <span class="n">width</span> <span class="o">//</span> <span class="bp">self</span><span class="o">.</span><span class="n">patch_size</span>
|
||
<span class="k">if</span> <span class="n">height</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_max_size</span><span class="p">:</span>
|
||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
|
||
<span class="sa">f</span><span class="s2">"Height (</span><span class="si">{</span><span class="n">height</span><span class="si">}</span><span class="s2">) cannot be greater than `pos_embed_max_size`: </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_max_size</span><span class="si">}</span><span class="s2">."</span>
|
||
<span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">width</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_max_size</span><span class="p">:</span>
|
||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
|
||
<span class="sa">f</span><span class="s2">"Width (</span><span class="si">{</span><span class="n">width</span><span class="si">}</span><span class="s2">) cannot be greater than `pos_embed_max_size`: </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_max_size</span><span class="si">}</span><span class="s2">."</span>
|
||
<span class="p">)</span>
|
||
|
||
<span class="n">top</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_max_size</span> <span class="o">-</span> <span class="n">height</span><span class="p">)</span> <span class="o">//</span> <span class="mi">2</span>
|
||
<span class="n">left</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_max_size</span> <span class="o">-</span> <span class="n">width</span><span class="p">)</span> <span class="o">//</span> <span class="mi">2</span>
|
||
<span class="n">spatial_pos_embed</span> <span class="o">=</span> <span class="n">identity</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">pos_embed</span><span class="o">.</span><span class="n">value</span><span class="p">)</span><span class="o">.</span><span class="n">view</span><span class="p">(</span>
|
||
<span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_max_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_max_size</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">])</span>
|
||
<span class="n">spatial_pos_embed</span> <span class="o">=</span> <span class="nb">slice</span><span class="p">(</span><span class="n">spatial_pos_embed</span><span class="p">,</span>
|
||
<span class="n">starts</span><span class="o">=</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="n">top</span><span class="p">,</span> <span class="n">left</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span>
|
||
<span class="n">sizes</span><span class="o">=</span><span class="n">concat</span><span class="p">([</span>
|
||
<span class="n">shape</span><span class="p">(</span><span class="n">spatial_pos_embed</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span> <span class="n">height</span><span class="p">,</span>
|
||
<span class="n">width</span><span class="p">,</span>
|
||
<span class="n">shape</span><span class="p">(</span><span class="n">spatial_pos_embed</span><span class="p">,</span> <span class="mi">3</span><span class="p">)</span>
|
||
<span class="p">]))</span>
|
||
<span class="n">spatial_pos_embed</span> <span class="o">=</span> <span class="n">spatial_pos_embed</span><span class="o">.</span><span class="n">view</span><span class="p">(</span>
|
||
<span class="n">concat</span><span class="p">(</span>
|
||
<span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span>
|
||
<span class="n">shape</span><span class="p">(</span><span class="n">spatial_pos_embed</span><span class="p">,</span>
|
||
<span class="n">spatial_pos_embed</span><span class="o">.</span><span class="n">ndim</span><span class="p">()</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)]))</span>
|
||
<span class="k">return</span> <span class="n">spatial_pos_embed</span></div>
|
||
|
||
|
||
<div class="viewcode-block" id="SD3PatchEmbed.forward">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.SD3PatchEmbed.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="n">latent</span><span class="p">):</span>
|
||
<span class="c1"># [TODO] to support height and width for runtime</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_max_size</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="n">height</span><span class="p">,</span> <span class="n">width</span> <span class="o">=</span> <span class="n">latent</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="o">-</span><span class="mi">2</span><span class="p">:]</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">height</span><span class="p">,</span> <span class="n">width</span> <span class="o">=</span> <span class="n">latent</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="o">-</span><span class="mi">2</span><span class="p">]</span> <span class="o">//</span> <span class="bp">self</span><span class="o">.</span><span class="n">patch_size</span><span class="p">,</span> <span class="n">latent</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span>
|
||
<span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">//</span> <span class="bp">self</span><span class="o">.</span><span class="n">patch_size</span>
|
||
<span class="n">latent</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">proj</span><span class="p">(</span><span class="n">latent</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">flatten</span><span class="p">:</span>
|
||
<span class="n">latent</span> <span class="o">=</span> <span class="n">latent</span><span class="o">.</span><span class="n">flatten</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span><span class="o">.</span><span class="n">transpose</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span> <span class="c1"># BCHW -> BNC</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_norm</span><span class="p">:</span>
|
||
<span class="n">latent</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">norm</span><span class="p">(</span><span class="n">latent</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">pos_embed</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="n">latent</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">latent</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
|
||
<span class="c1"># Interpolate or crop positional embeddings as needed</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">pos_embed_max_size</span><span class="p">:</span>
|
||
<span class="n">pos_embed</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cropped_pos_embed</span><span class="p">(</span><span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">)</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">height</span> <span class="o">!=</span> <span class="n">height</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">width</span> <span class="o">!=</span> <span class="n">width</span><span class="p">:</span>
|
||
<span class="n">pos_embed</span> <span class="o">=</span> <span class="n">get_2d_sincos_pos_embed</span><span class="p">(</span>
|
||
<span class="n">embed_dim</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">pos_embed</span><span class="o">.</span><span class="n">value</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span>
|
||
<span class="n">grid_size</span><span class="o">=</span><span class="p">(</span><span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">),</span>
|
||
<span class="n">base_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">base_size</span><span class="p">,</span>
|
||
<span class="n">interpolation_scale</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">interpolation_scale</span><span class="p">,</span>
|
||
<span class="p">)</span>
|
||
<span class="n">pos_embed</span> <span class="o">=</span> <span class="n">unsqueeze</span><span class="p">(</span><span class="n">pos_embed</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="s1">'float32'</span><span class="p">),</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">pos_embed</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pos_embed</span><span class="o">.</span><span class="n">value</span>
|
||
|
||
<span class="n">pos_embed</span> <span class="o">=</span> <span class="n">pos_embed</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">latent</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
|
||
<span class="n">output</span> <span class="o">=</span> <span class="p">(</span><span class="n">latent</span> <span class="o">+</span> <span class="n">pos_embed</span><span class="p">)</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">latent</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">output</span></div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="get_timestep_embedding">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.get_timestep_embedding">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">get_timestep_embedding</span><span class="p">(</span>
|
||
<span class="n">timesteps</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span>
|
||
<span class="n">embedding_dim</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||
<span class="n">flip_sin_to_cos</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">downscale_freq_shift</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
|
||
<span class="n">scale</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
|
||
<span class="n">max_period</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10000</span><span class="p">,</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="n">Tensor</span><span class="p">:</span>
|
||
<span class="w"> </span><span class="sd">"""</span>
|
||
<span class="sd"> This matches the implementation in Denoising Diffusion Probabilistic Models: Create sinusoidal timestep embeddings.</span>
|
||
|
||
<span class="sd"> Args</span>
|
||
<span class="sd"> timesteps (Tensor):</span>
|
||
<span class="sd"> a 1-D Tensor of N indices, one per batch element. These may be fractional.</span>
|
||
<span class="sd"> embedding_dim (int):</span>
|
||
<span class="sd"> the dimension of the output.</span>
|
||
<span class="sd"> flip_sin_to_cos (bool):</span>
|
||
<span class="sd"> Whether the embedding order should be `cos, sin` (if True) or `sin, cos` (if False)</span>
|
||
<span class="sd"> downscale_freq_shift (float):</span>
|
||
<span class="sd"> Controls the delta between frequencies between dimensions</span>
|
||
<span class="sd"> scale (float):</span>
|
||
<span class="sd"> Scaling factor applied to the embeddings.</span>
|
||
<span class="sd"> max_period (int):</span>
|
||
<span class="sd"> Controls the maximum frequency of the embeddings</span>
|
||
<span class="sd"> Returns</span>
|
||
<span class="sd"> Tensor: an [N x dim] Tensor of positional embeddings.</span>
|
||
<span class="sd"> """</span>
|
||
<span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">timesteps</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">"Timesteps should be a 1d-array"</span>
|
||
|
||
<span class="n">half_dim</span> <span class="o">=</span> <span class="n">embedding_dim</span> <span class="o">//</span> <span class="mi">2</span>
|
||
<span class="n">exponent</span> <span class="o">=</span> <span class="o">-</span><span class="n">math</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="n">max_period</span><span class="p">)</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span>
|
||
<span class="n">start</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">stop</span><span class="o">=</span><span class="n">half_dim</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
|
||
<span class="n">exponent</span> <span class="o">=</span> <span class="n">exponent</span> <span class="o">/</span> <span class="p">(</span><span class="n">half_dim</span> <span class="o">-</span> <span class="n">downscale_freq_shift</span><span class="p">)</span>
|
||
<span class="n">exponent</span> <span class="o">=</span> <span class="n">constant</span><span class="p">(</span><span class="n">exponent</span><span class="p">)</span>
|
||
|
||
<span class="n">emb</span> <span class="o">=</span> <span class="n">exp</span><span class="p">(</span><span class="n">exponent</span><span class="p">)</span>
|
||
<span class="n">emb</span> <span class="o">=</span> <span class="n">unsqueeze</span><span class="p">(</span><span class="n">timesteps</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="s1">'float32'</span><span class="p">)</span> <span class="o">*</span> <span class="n">unsqueeze</span><span class="p">(</span><span class="n">emb</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
|
||
|
||
<span class="c1"># scale embeddings</span>
|
||
<span class="n">emb</span> <span class="o">=</span> <span class="n">scale</span> <span class="o">*</span> <span class="n">emb</span>
|
||
|
||
<span class="c1"># flip sine and cosine embeddings</span>
|
||
<span class="k">if</span> <span class="n">flip_sin_to_cos</span><span class="p">:</span>
|
||
<span class="n">emb</span> <span class="o">=</span> <span class="n">concat</span><span class="p">([</span><span class="n">cos</span><span class="p">(</span><span class="n">emb</span><span class="p">),</span> <span class="n">sin</span><span class="p">(</span><span class="n">emb</span><span class="p">)],</span> <span class="n">dim</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">emb</span> <span class="o">=</span> <span class="n">concat</span><span class="p">([</span><span class="n">sin</span><span class="p">(</span><span class="n">emb</span><span class="p">),</span> <span class="n">cos</span><span class="p">(</span><span class="n">emb</span><span class="p">)],</span> <span class="n">dim</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span>
|
||
|
||
<span class="c1"># zero pad</span>
|
||
<span class="k">if</span> <span class="n">embedding_dim</span> <span class="o">%</span> <span class="mi">2</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
|
||
<span class="n">emb</span> <span class="o">=</span> <span class="n">pad</span><span class="p">(</span><span class="n">emb</span><span class="p">,</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">))</span>
|
||
<span class="k">return</span> <span class="n">emb</span></div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="TimestepEmbedding">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.TimestepEmbedding">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">TimestepEmbedding</span><span class="p">(</span><span class="n">Module</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">in_channels</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||
<span class="n">time_embed_dim</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||
<span class="n">act_fn</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"silu"</span><span class="p">,</span>
|
||
<span class="n">out_dim</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">post_act_fn</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">cond_proj_dim</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">sample_proj_bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">mapping</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</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">tp_group</span> <span class="o">=</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_group</span>
|
||
<span class="n">tp_size</span> <span class="o">=</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">linear_1</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,</span>
|
||
<span class="n">time_embed_dim</span><span class="p">,</span>
|
||
<span class="n">sample_proj_bias</span><span class="p">,</span>
|
||
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
|
||
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
|
||
<span class="n">gather_output</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||
|
||
<span class="k">if</span> <span class="n">cond_proj_dim</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">cond_proj</span> <span class="o">=</span> <span class="n">Linear</span><span class="p">(</span><span class="n">cond_proj_dim</span><span class="p">,</span>
|
||
<span class="n">in_channels</span><span class="p">,</span>
|
||
<span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">cond_proj</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="n">act_fn</span><span class="p">]</span>
|
||
|
||
<span class="k">if</span> <span class="n">out_dim</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="n">time_embed_dim_out</span> <span class="o">=</span> <span class="n">out_dim</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">time_embed_dim_out</span> <span class="o">=</span> <span class="n">time_embed_dim</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">linear_2</span> <span class="o">=</span> <span class="n">RowLinear</span><span class="p">(</span><span class="n">time_embed_dim</span><span class="p">,</span>
|
||
<span class="n">time_embed_dim_out</span><span class="p">,</span>
|
||
<span class="n">sample_proj_bias</span><span class="p">,</span>
|
||
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
|
||
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span>
|
||
|
||
<span class="k">if</span> <span class="n">post_act_fn</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">post_act</span> <span class="o">=</span> <span class="kc">None</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">post_act</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="n">post_act_fn</span><span class="p">]</span>
|
||
|
||
<div class="viewcode-block" id="TimestepEmbedding.forward">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.TimestepEmbedding.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="n">sample</span><span class="p">,</span> <span class="n">condition</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
||
<span class="k">if</span> <span class="n">condition</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="n">sample</span> <span class="o">=</span> <span class="n">sample</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">cond_proj</span><span class="p">(</span><span class="n">condition</span><span class="p">)</span>
|
||
<span class="n">sample</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">linear_1</span><span class="p">(</span><span class="n">sample</span><span class="p">)</span>
|
||
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="n">sample</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span><span class="p">(</span><span class="n">sample</span><span class="p">)</span>
|
||
|
||
<span class="n">sample</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">linear_2</span><span class="p">(</span><span class="n">sample</span><span class="p">)</span>
|
||
|
||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">post_act</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="n">sample</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">post_act</span><span class="p">(</span><span class="n">sample</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">sample</span></div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="Timesteps">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.Timesteps">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">Timesteps</span><span class="p">(</span><span class="n">Module</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">num_channels</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||
<span class="n">flip_sin_to_cos</span><span class="p">:</span> <span class="nb">bool</span><span class="p">,</span>
|
||
<span class="n">downscale_freq_shift</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span>
|
||
<span class="n">scale</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</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="bp">self</span><span class="o">.</span><span class="n">num_channels</span> <span class="o">=</span> <span class="n">num_channels</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">flip_sin_to_cos</span> <span class="o">=</span> <span class="n">flip_sin_to_cos</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">downscale_freq_shift</span> <span class="o">=</span> <span class="n">downscale_freq_shift</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">scale</span> <span class="o">=</span> <span class="n">scale</span>
|
||
|
||
<div class="viewcode-block" id="Timesteps.forward">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.Timesteps.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="n">timesteps</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tensor</span><span class="p">:</span>
|
||
<span class="n">t_emb</span> <span class="o">=</span> <span class="n">get_timestep_embedding</span><span class="p">(</span>
|
||
<span class="n">timesteps</span><span class="p">,</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">num_channels</span><span class="p">,</span>
|
||
<span class="n">flip_sin_to_cos</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">flip_sin_to_cos</span><span class="p">,</span>
|
||
<span class="n">downscale_freq_shift</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">downscale_freq_shift</span><span class="p">,</span>
|
||
<span class="n">scale</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">scale</span><span class="p">,</span>
|
||
<span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">t_emb</span></div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="PixArtAlphaTextProjection">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.PixArtAlphaTextProjection">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">PixArtAlphaTextProjection</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""</span>
|
||
<span class="sd"> Projects caption embeddings. Also handles dropout for classifier-free guidance.</span>
|
||
|
||
<span class="sd"> Adapted from https://github.com/PixArt-alpha/PixArt-alpha/blob/master/diffusion/model/nets/PixArt_blocks.py</span>
|
||
<span class="sd"> """</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">in_features</span><span class="p">,</span>
|
||
<span class="n">hidden_size</span><span class="p">,</span>
|
||
<span class="n">out_features</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">act_fn</span><span class="o">=</span><span class="s2">"gelu_tanh"</span><span class="p">,</span>
|
||
<span class="n">mapping</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</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="k">if</span> <span class="n">out_features</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="n">out_features</span> <span class="o">=</span> <span class="n">hidden_size</span>
|
||
<span class="n">tp_group</span> <span class="o">=</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_group</span>
|
||
<span class="n">tp_size</span> <span class="o">=</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">linear_1</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span><span class="n">in_features</span><span class="o">=</span><span class="n">in_features</span><span class="p">,</span>
|
||
<span class="n">out_features</span><span class="o">=</span><span class="n">hidden_size</span><span class="p">,</span>
|
||
<span class="n">bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
|
||
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
|
||
<span class="n">gather_output</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">act_1</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="n">act_fn</span><span class="p">]</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">linear_2</span> <span class="o">=</span> <span class="n">RowLinear</span><span class="p">(</span><span class="n">in_features</span><span class="o">=</span><span class="n">hidden_size</span><span class="p">,</span>
|
||
<span class="n">out_features</span><span class="o">=</span><span class="n">out_features</span><span class="p">,</span>
|
||
<span class="n">bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
|
||
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span>
|
||
|
||
<div class="viewcode-block" id="PixArtAlphaTextProjection.forward">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.PixArtAlphaTextProjection.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="n">caption</span><span class="p">):</span>
|
||
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">linear_1</span><span class="p">(</span><span class="n">caption</span><span class="p">)</span>
|
||
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">act_1</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
|
||
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">linear_2</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">hidden_states</span></div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="CombinedTimestepTextProjEmbeddings">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.CombinedTimestepTextProjEmbeddings">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">CombinedTimestepTextProjEmbeddings</span><span class="p">(</span><span class="n">Module</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">embedding_dim</span><span class="p">,</span>
|
||
<span class="n">pooled_projection_dim</span><span class="p">,</span>
|
||
<span class="n">mapping</span><span class="o">=</span><span class="n">Mapping</span><span class="p">(),</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</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="bp">self</span><span class="o">.</span><span class="n">time_proj</span> <span class="o">=</span> <span class="n">Timesteps</span><span class="p">(</span><span class="n">num_channels</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
|
||
<span class="n">flip_sin_to_cos</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">downscale_freq_shift</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">timestep_embedder</span> <span class="o">=</span> <span class="n">TimestepEmbedding</span><span class="p">(</span><span class="n">in_channels</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
|
||
<span class="n">time_embed_dim</span><span class="o">=</span><span class="n">embedding_dim</span><span class="p">,</span>
|
||
<span class="n">mapping</span><span class="o">=</span><span class="n">mapping</span><span class="p">,</span>
|
||
<span class="n">dtype</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">text_embedder</span> <span class="o">=</span> <span class="n">PixArtAlphaTextProjection</span><span class="p">(</span><span class="n">pooled_projection_dim</span><span class="p">,</span>
|
||
<span class="n">embedding_dim</span><span class="p">,</span>
|
||
<span class="n">act_fn</span><span class="o">=</span><span class="s2">"silu"</span><span class="p">,</span>
|
||
<span class="n">mapping</span><span class="o">=</span><span class="n">mapping</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span>
|
||
|
||
<div class="viewcode-block" id="CombinedTimestepTextProjEmbeddings.forward">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.CombinedTimestepTextProjEmbeddings.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="n">timestep</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">pooled_projection</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">):</span>
|
||
<span class="n">timesteps_proj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">time_proj</span><span class="p">(</span><span class="n">timestep</span><span class="p">)</span>
|
||
<span class="n">timesteps_emb</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">timestep_embedder</span><span class="p">(</span>
|
||
<span class="n">timesteps_proj</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">dtype</span><span class="o">=</span><span class="n">pooled_projection</span><span class="o">.</span><span class="n">dtype</span><span class="p">))</span> <span class="c1"># (N, D)</span>
|
||
|
||
<span class="n">pooled_projections</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">text_embedder</span><span class="p">(</span><span class="n">pooled_projection</span><span class="p">)</span>
|
||
|
||
<span class="n">conditioning</span> <span class="o">=</span> <span class="n">timesteps_emb</span> <span class="o">+</span> <span class="n">pooled_projections</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">register_network_output</span><span class="p">(</span><span class="s1">'output'</span><span class="p">,</span> <span class="n">conditioning</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">conditioning</span></div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="CombinedTimestepLabelEmbeddings">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.CombinedTimestepLabelEmbeddings">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">CombinedTimestepLabelEmbeddings</span><span class="p">(</span><span class="n">Module</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">num_classes</span><span class="p">,</span>
|
||
<span class="n">embedding_dim</span><span class="p">,</span>
|
||
<span class="n">class_dropout_prob</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
|
||
<span class="n">mapping</span><span class="o">=</span><span class="n">Mapping</span><span class="p">(),</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</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="bp">self</span><span class="o">.</span><span class="n">time_proj</span> <span class="o">=</span> <span class="n">Timesteps</span><span class="p">(</span><span class="n">num_channels</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
|
||
<span class="n">flip_sin_to_cos</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">downscale_freq_shift</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">timestep_embedder</span> <span class="o">=</span> <span class="n">TimestepEmbedding</span><span class="p">(</span><span class="n">in_channels</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span>
|
||
<span class="n">time_embed_dim</span><span class="o">=</span><span class="n">embedding_dim</span><span class="p">,</span>
|
||
<span class="n">mapping</span><span class="o">=</span><span class="n">mapping</span><span class="p">,</span>
|
||
<span class="n">dtype</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">class_embedder</span> <span class="o">=</span> <span class="n">LabelEmbedding</span><span class="p">(</span><span class="n">num_classes</span><span class="p">,</span>
|
||
<span class="n">embedding_dim</span><span class="p">,</span>
|
||
<span class="n">class_dropout_prob</span><span class="p">,</span>
|
||
<span class="n">mapping</span><span class="o">=</span><span class="n">mapping</span><span class="p">,</span>
|
||
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span>
|
||
|
||
<div class="viewcode-block" id="CombinedTimestepLabelEmbeddings.forward">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.CombinedTimestepLabelEmbeddings.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="n">timestep</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span>
|
||
<span class="n">class_labels</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span>
|
||
<span class="n">hidden_dtype</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'float32'</span><span class="p">):</span>
|
||
<span class="n">timesteps_proj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">time_proj</span><span class="p">(</span><span class="n">timestep</span><span class="p">)</span>
|
||
<span class="n">timesteps_emb</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">timestep_embedder</span><span class="p">(</span>
|
||
<span class="n">timesteps_proj</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">dtype</span><span class="o">=</span><span class="n">hidden_dtype</span><span class="p">))</span> <span class="c1"># (N, D)</span>
|
||
<span class="n">class_labels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">class_embedder</span><span class="p">(</span><span class="n">class_labels</span><span class="p">)</span> <span class="c1"># (N, D)</span>
|
||
<span class="n">conditioning</span> <span class="o">=</span> <span class="n">timesteps_emb</span> <span class="o">+</span> <span class="n">class_labels</span> <span class="c1"># (N, D)</span>
|
||
<span class="k">return</span> <span class="n">conditioning</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/">Your Privacy Choices</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/terms-of-service/">Terms of Service</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/accessibility/">Accessibility</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/company-policies/">Corporate Policies</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/product-security/">Product Security</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/contact/">Contact</a>
|
||
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
<div class="footer-item">
|
||
|
||
|
||
|
||
|
||
<p class="copyright">
|
||
|
||
Copyright © 2025, NVidia.
|
||
<br/>
|
||
|
||
</p>
|
||
</div>
|
||
|
||
<div class="footer-item">
|
||
<div class="extra_footer">
|
||
|
||
<p>Last updated on November 23, 2025.</p>
|
||
|
||
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/a761585">a761585</a>.</p>
|
||
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
</footer>
|
||
</body>
|
||
</html> |