kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
a79e2dc7fb
TensorRT-LLMs/_modules/tensorrt_llm/models/bert/model.html
Kaiyu Xie a79e2dc7fb Update GitHub pages in root to v1.2.0rc4
2025-11-25 03:40:39 +00:00

1202 lines
111 KiB
HTML
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!DOCTYPE html>
<html lang="en" data-content_root="../../../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>tensorrt_llm.models.bert.model &#8212; TensorRT LLM</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!--
this give us a css class that will be invisible only if js is disabled
-->
<noscript>
<style>
.pst-js-only { display: none !important; }
</style>
</noscript>
<!-- Loaded before other Sphinx assets -->
<link href="../../../../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link href="../../../../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="../../../../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../../../../_static/styles/nvidia-sphinx-theme.css?v=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/models/bert/model';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '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 &amp; 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 &amp; 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 &amp; 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 &amp; 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 &amp; 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.models.bert.model</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<h1>Source code for tensorrt_llm.models.bert.model</h1><div class="highlight"><pre>
<span></span><span class="c1"># SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION &amp; AFFILIATES. All rights reserved.</span>
<span class="c1"># SPDX-License-Identifier: Apache-2.0</span>
<span class="c1">#</span>
<span class="c1"># Licensed under the Apache License, Version 2.0 (the &quot;License&quot;);</span>
<span class="c1"># you may not use this file except in compliance with the License.</span>
<span class="c1"># You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">OrderedDict</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">tensorrt</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">trt</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">transformers</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.models.modeling_utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">PretrainedModel</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">..._common</span><span class="w"> </span><span class="kn">import</span> <span class="n">default_net</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">...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">concat</span><span class="p">,</span> <span class="n">constant</span><span class="p">,</span> <span class="n">cumsum</span><span class="p">,</span> <span class="n">expand</span><span class="p">,</span>
<span class="n">index_select</span><span class="p">,</span> <span class="n">select</span><span class="p">,</span> <span class="n">shape</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="kn">from</span><span class="w"> </span><span class="nn">...layers</span><span class="w"> </span><span class="kn">import</span> <span class="n">MLP</span><span class="p">,</span> <span class="n">BertAttention</span><span class="p">,</span> <span class="n">Embedding</span><span class="p">,</span> <span class="n">LayerNorm</span><span class="p">,</span> <span class="n">Linear</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="p">,</span> <span class="n">ModuleList</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">..modeling_utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">QuantConfig</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">.config</span><span class="w"> </span><span class="kn">import</span> <span class="n">BERTConfig</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">.convert</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span><span class="n">load_hf_bert_base</span><span class="p">,</span> <span class="n">load_hf_bert_cls</span><span class="p">,</span> <span class="n">load_hf_bert_qa</span><span class="p">,</span>
<span class="n">load_weights_from_hf_model</span><span class="p">)</span>
<span class="k">class</span><span class="w"> </span><span class="nc">BertEmbedding</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">vocab_size</span><span class="p">,</span>
<span class="n">hidden_size</span><span class="p">,</span>
<span class="n">max_position_embeddings</span><span class="p">,</span>
<span class="n">type_vocab_size</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">vocab_embedding</span> <span class="o">=</span> <span class="n">Embedding</span><span class="p">(</span><span class="n">vocab_size</span><span class="p">,</span> <span class="n">hidden_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="bp">self</span><span class="o">.</span><span class="n">position_embedding</span> <span class="o">=</span> <span class="n">Embedding</span><span class="p">(</span><span class="n">max_position_embeddings</span><span class="p">,</span>
<span class="n">hidden_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="bp">self</span><span class="o">.</span><span class="n">token_embedding</span> <span class="o">=</span> <span class="n">Embedding</span><span class="p">(</span><span class="n">type_vocab_size</span><span class="p">,</span>
<span class="n">hidden_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="bp">self</span><span class="o">.</span><span class="n">max_position_embeddings</span> <span class="o">=</span> <span class="n">max_position_embeddings</span>
<span class="bp">self</span><span class="o">.</span><span class="n">embedding_ln</span> <span class="o">=</span> <span class="n">LayerNorm</span><span class="p">(</span><span class="n">normalized_shape</span><span class="o">=</span><span class="n">hidden_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">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">input_ids</span><span class="p">,</span> <span class="n">position_ids</span><span class="p">,</span> <span class="n">token_type_ids</span><span class="p">):</span>
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">vocab_embedding</span><span class="p">(</span><span class="n">input_ids</span><span class="p">)</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">x</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">position_embedding</span><span class="p">(</span><span class="n">position_ids</span><span class="p">)</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">x</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">token_embedding</span><span class="p">(</span><span class="n">token_type_ids</span><span class="p">)</span>
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">embedding_ln</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span>
<span class="k">class</span><span class="w"> </span><span class="nc">BertEncoderLayer</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">hidden_size</span><span class="p">,</span>
<span class="n">num_attention_heads</span><span class="p">,</span>
<span class="n">max_position_embeddings</span><span class="p">,</span>
<span class="n">hidden_act</span><span class="o">=</span><span class="s1">&#39;relu&#39;</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">tp_size</span><span class="o">=</span><span class="mi">1</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">input_layernorm</span> <span class="o">=</span> <span class="n">LayerNorm</span><span class="p">(</span><span class="n">normalized_shape</span><span class="o">=</span><span class="n">hidden_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="bp">self</span><span class="o">.</span><span class="n">attention</span> <span class="o">=</span> <span class="n">BertAttention</span><span class="p">(</span>
<span class="n">hidden_size</span><span class="o">=</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">num_attention_heads</span><span class="o">=</span><span class="n">num_attention_heads</span><span class="p">,</span>
<span class="n">max_position_embeddings</span><span class="o">=</span><span class="n">max_position_embeddings</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="bp">self</span><span class="o">.</span><span class="n">mlp</span> <span class="o">=</span> <span class="n">MLP</span><span class="p">(</span><span class="n">hidden_size</span><span class="o">=</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">ffn_hidden_size</span><span class="o">=</span><span class="n">hidden_size</span> <span class="o">*</span> <span class="mi">4</span><span class="p">,</span>
<span class="n">hidden_act</span><span class="o">=</span><span class="n">hidden_act</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="bp">self</span><span class="o">.</span><span class="n">post_layernorm</span> <span class="o">=</span> <span class="n">LayerNorm</span><span class="p">(</span><span class="n">normalized_shape</span><span class="o">=</span><span class="n">hidden_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">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">hidden_states</span><span class="p">,</span>
<span class="n">attention_mask</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">input_lengths</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">max_input_length</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">residual</span> <span class="o">=</span> <span class="n">hidden_states</span>
<span class="n">attention_output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">attention</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="n">attention_mask</span><span class="o">=</span><span class="n">attention_mask</span><span class="p">,</span>
<span class="n">input_lengths</span><span class="o">=</span><span class="n">input_lengths</span><span class="p">,</span>
<span class="n">max_input_length</span><span class="o">=</span><span class="n">max_input_length</span><span class="p">)</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">residual</span> <span class="o">+</span> <span class="n">attention_output</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">input_layernorm</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">residual</span> <span class="o">=</span> <span class="n">hidden_states</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mlp</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="n">residual</span> <span class="o">+</span> <span class="n">hidden_states</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">post_layernorm</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>
<span class="k">class</span><span class="w"> </span><span class="nc">BertBase</span><span class="p">(</span><span class="n">PretrainedModel</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> Base class that provides from_huggingface() and prepare_inputs() methods</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="n">config_class</span> <span class="o">=</span> <span class="n">BERTConfig</span>
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">config</span><span class="p">:</span> <span class="n">BERTConfig</span><span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">config</span><span class="p">)</span>
<span class="nd">@classmethod</span>
<span class="k">def</span><span class="w"> </span><span class="nf">load_hf_bert</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">model_dir</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">load_model_on_cpu</span><span class="p">:</span> <span class="nb">bool</span><span class="p">,</span>
<span class="n">dtype</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">dtype</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Use as the abstractmethod, load corresponding HF model.</span>
<span class="sd"> Subclass must implement this method!</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">assert</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span> <span class="o">!=</span> <span class="s2">&quot;BertBase&quot;</span><span class="p">,</span> <span class="sa">f</span><span class="s2">&quot;Never call from BertBase class!&quot;</span>
<span class="k">if</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;BertModel&quot;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">load_hf_bert_base</span><span class="p">(</span><span class="n">model_dir</span><span class="p">,</span> <span class="n">load_model_on_cpu</span><span class="p">,</span> <span class="n">dtype</span><span class="p">)</span>
<span class="k">elif</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;BertForQuestionAnswering&quot;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">load_hf_bert_qa</span><span class="p">(</span><span class="n">model_dir</span><span class="p">,</span> <span class="n">load_model_on_cpu</span><span class="p">,</span> <span class="n">dtype</span><span class="p">)</span>
<span class="k">elif</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;BertForSequenceClassification&quot;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">load_hf_bert_cls</span><span class="p">(</span><span class="n">model_dir</span><span class="p">,</span> <span class="n">load_model_on_cpu</span><span class="p">,</span> <span class="n">dtype</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">assert</span> <span class="kc">False</span><span class="p">,</span> <span class="sa">f</span><span class="s2">&quot;Unknown class </span><span class="si">{</span><span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span><span class="si">}</span><span class="s2">!&quot;</span>
<span class="nd">@classmethod</span>
<span class="k">def</span><span class="w"> </span><span class="nf">from_hugging_face</span><span class="p">(</span>
<span class="bp">cls</span><span class="p">,</span>
<span class="n">hf_model_or_dir</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="s1">&#39;transformers.PreTrainedModel&#39;</span><span class="p">],</span>
<span class="n">dtype</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s1">&#39;float16&#39;</span><span class="p">,</span>
<span class="n">mapping</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">quant_config</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">QuantConfig</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Create a BertModel object from give parameters</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">transformers</span>
<span class="k">assert</span> <span class="n">hf_model_or_dir</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
<span class="n">use_preloading</span> <span class="o">=</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">hf_model_or_dir</span><span class="p">,</span>
<span class="n">transformers</span><span class="o">.</span><span class="n">PreTrainedModel</span><span class="p">)</span>
<span class="k">if</span> <span class="n">use_preloading</span><span class="p">:</span>
<span class="n">hf_model</span> <span class="o">=</span> <span class="n">hf_model_or_dir</span>
<span class="n">hf_config_or_dir</span> <span class="o">=</span> <span class="n">hf_model</span><span class="o">.</span><span class="n">config</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">hf_model_dir</span> <span class="o">=</span> <span class="n">hf_model_or_dir</span>
<span class="n">hf_config_or_dir</span> <span class="o">=</span> <span class="n">hf_model_or_dir</span>
<span class="n">load_model_on_cpu</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="s1">&#39;load_model_on_cpu&#39;</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>
<span class="n">tllm_config</span> <span class="o">=</span> <span class="n">BERTConfig</span><span class="o">.</span><span class="n">from_hugging_face</span><span class="p">(</span>
<span class="n">hf_config_or_dir</span><span class="o">=</span><span class="n">hf_config_or_dir</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">mapping</span><span class="o">=</span><span class="n">mapping</span><span class="p">,</span>
<span class="n">quant_config</span><span class="o">=</span><span class="n">quant_config</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="c1">#NOTE: override architecture info</span>
<span class="n">RobertaCls_mapping</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;BertModel&quot;</span><span class="p">:</span> <span class="s2">&quot;RobertaModel&quot;</span><span class="p">,</span>
<span class="s2">&quot;BertForQuestionAnswering&quot;</span><span class="p">:</span> <span class="s2">&quot;RobertaForQuestionAnswering&quot;</span><span class="p">,</span>
<span class="s2">&quot;BertForSequenceClassification&quot;</span><span class="p">:</span> <span class="s2">&quot;RobertaForSequenceClassification&quot;</span><span class="p">,</span>
<span class="p">}</span>
<span class="k">if</span> <span class="n">tllm_config</span><span class="o">.</span><span class="n">is_roberta</span><span class="p">:</span>
<span class="nb">setattr</span><span class="p">(</span><span class="n">tllm_config</span><span class="p">,</span> <span class="s1">&#39;architecture&#39;</span><span class="p">,</span>
<span class="n">RobertaCls_mapping</span><span class="p">[</span><span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span><span class="p">])</span>
<span class="k">else</span><span class="p">:</span>
<span class="nb">setattr</span><span class="p">(</span><span class="n">tllm_config</span><span class="p">,</span> <span class="s1">&#39;architecture&#39;</span><span class="p">,</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span><span class="p">)</span>
<span class="n">torch_dtype</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">float16</span> <span class="k">if</span> <span class="n">dtype</span> <span class="o">==</span> <span class="s1">&#39;float16&#39;</span> <span class="k">else</span> <span class="n">torch</span><span class="o">.</span><span class="n">float32</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">use_preloading</span><span class="p">:</span>
<span class="n">hf_model</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">load_hf_bert</span><span class="p">(</span><span class="n">model_dir</span><span class="o">=</span><span class="n">hf_model_dir</span><span class="p">,</span>
<span class="n">load_model_on_cpu</span><span class="o">=</span><span class="n">load_model_on_cpu</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">torch_dtype</span><span class="p">)</span>
<span class="n">weights</span> <span class="o">=</span> <span class="n">load_weights_from_hf_model</span><span class="p">(</span><span class="n">hf_model</span><span class="o">=</span><span class="n">hf_model</span><span class="p">,</span>
<span class="n">config</span><span class="o">=</span><span class="n">tllm_config</span><span class="p">)</span>
<span class="n">model</span> <span class="o">=</span> <span class="bp">cls</span><span class="p">(</span><span class="n">tllm_config</span><span class="p">)</span>
<span class="n">model</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">weights</span><span class="p">)</span>
<span class="k">return</span> <span class="n">model</span>
<span class="c1"># Override the PretrainedModel&#39;s meothd, can unify in the future.</span>
<span class="k">def</span><span class="w"> </span><span class="nf">prepare_inputs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">max_batch_size</span><span class="p">,</span> <span class="n">max_input_len</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="n">remove_input_padding</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">remove_input_padding</span>
<span class="c1"># opt_shape is set to half of max batch_size and seq_len by default</span>
<span class="c1"># tune this according to real data distribution</span>
<span class="n">bs_range</span> <span class="o">=</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="p">(</span><span class="n">max_batch_size</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">//</span> <span class="mi">2</span><span class="p">,</span> <span class="n">max_batch_size</span><span class="p">]</span>
<span class="n">inlen_range</span> <span class="o">=</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="p">(</span><span class="n">max_input_len</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">//</span> <span class="mi">2</span><span class="p">,</span> <span class="n">max_input_len</span><span class="p">]</span>
<span class="n">num_tokens_range</span> <span class="o">=</span> <span class="p">[</span>
<span class="mi">1</span><span class="p">,</span>
<span class="p">(</span><span class="n">max_input_len</span> <span class="o">*</span> <span class="n">max_batch_size</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">//</span> <span class="mi">2</span><span class="p">,</span>
<span class="n">max_input_len</span> <span class="o">*</span> <span class="n">max_batch_size</span><span class="p">,</span>
<span class="p">]</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">remove_input_padding</span><span class="p">:</span>
<span class="n">input_ids</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;input_ids&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([(</span><span class="s1">&#39;batch_size&#39;</span><span class="p">,</span> <span class="p">[</span><span class="n">bs_range</span><span class="p">]),</span>
<span class="p">(</span><span class="s1">&#39;input_len&#39;</span><span class="p">,</span> <span class="p">[</span><span class="n">inlen_range</span><span class="p">])]),</span>
<span class="p">)</span>
<span class="c1"># also called segment_ids</span>
<span class="n">token_type_ids</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;token_type_ids&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([(</span><span class="s1">&#39;batch_size&#39;</span><span class="p">,</span> <span class="p">[</span><span class="n">bs_range</span><span class="p">]),</span>
<span class="p">(</span><span class="s1">&#39;input_len&#39;</span><span class="p">,</span> <span class="p">[</span><span class="n">inlen_range</span><span class="p">])]),</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">input_ids</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s2">&quot;input_ids&quot;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([(</span><span class="s2">&quot;num_tokens&quot;</span><span class="p">,</span> <span class="p">[</span><span class="n">num_tokens_range</span><span class="p">])]),</span>
<span class="p">)</span>
<span class="n">token_type_ids</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;token_type_ids&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([(</span><span class="s1">&#39;num_tokens&#39;</span><span class="p">,</span> <span class="p">[</span><span class="n">num_tokens_range</span><span class="p">])]),</span>
<span class="p">)</span>
<span class="n">position_ids</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;position_ids&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([(</span><span class="s1">&#39;num_tokens&#39;</span><span class="p">,</span> <span class="p">[</span><span class="n">num_tokens_range</span><span class="p">])]),</span>
<span class="p">)</span>
<span class="n">max_input_length</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s2">&quot;max_input_length&quot;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([(</span><span class="s2">&quot;max_input_length&quot;</span><span class="p">,</span> <span class="p">[</span><span class="n">inlen_range</span><span class="p">])]),</span>
<span class="p">)</span>
<span class="n">input_lengths</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;input_lengths&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([(</span><span class="s1">&#39;batch_size&#39;</span><span class="p">,</span> <span class="p">[</span><span class="n">bs_range</span><span class="p">])</span>
<span class="p">]))</span>
<span class="n">inputs</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;input_ids&#39;</span><span class="p">:</span> <span class="n">input_ids</span><span class="p">,</span>
<span class="s1">&#39;input_lengths&#39;</span><span class="p">:</span> <span class="n">input_lengths</span><span class="p">,</span>
<span class="s1">&#39;token_type_ids&#39;</span><span class="p">:</span> <span class="n">token_type_ids</span><span class="p">,</span>
<span class="p">}</span>
<span class="k">if</span> <span class="n">remove_input_padding</span><span class="p">:</span>
<span class="n">inputs</span><span class="p">[</span><span class="s1">&#39;position_ids&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">position_ids</span>
<span class="n">inputs</span><span class="p">[</span><span class="s1">&#39;max_input_length&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">max_input_length</span>
<span class="k">return</span> <span class="n">inputs</span>
<div class="viewcode-block" id="BertModel">
<a class="viewcode-back" href="../../../../legacy/python-api/tensorrt_llm.models.html#tensorrt_llm.models.BertModel">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">BertModel</span><span class="p">(</span><span class="n">BertBase</span><span class="p">):</span>
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">config</span><span class="p">:</span> <span class="n">BERTConfig</span><span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">config</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">config</span> <span class="o">=</span> <span class="n">config</span>
<span class="bp">self</span><span class="o">.</span><span class="n">max_position_embeddings</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">max_position_embeddings</span>
<span class="bp">self</span><span class="o">.</span><span class="n">padding_idx</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">pad_token_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">is_roberta</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">is_roberta</span>
<span class="bp">self</span><span class="o">.</span><span class="n">embedding</span> <span class="o">=</span> <span class="n">BertEmbedding</span><span class="p">(</span>
<span class="n">vocab_size</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">,</span>
<span class="n">hidden_size</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">max_position_embeddings</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">max_position_embeddings</span><span class="p">,</span>
<span class="n">type_vocab_size</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">type_vocab_size</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">layers</span> <span class="o">=</span> <span class="n">ModuleList</span><span class="p">([</span>
<span class="n">BertEncoderLayer</span><span class="p">(</span>
<span class="n">hidden_size</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">num_attention_heads</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">num_attention_heads</span><span class="p">,</span>
<span class="n">max_position_embeddings</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">max_position_embeddings</span><span class="p">,</span>
<span class="n">hidden_act</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_act</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">config</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">tp_size</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">num_hidden_layers</span><span class="p">)</span>
<span class="p">])</span>
<div class="viewcode-block" id="BertModel.forward">
<a class="viewcode-back" href="../../../../legacy/python-api/tensorrt_llm.models.html#tensorrt_llm.models.BertModel.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">input_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">input_lengths</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">position_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">token_type_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">hidden_states</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">max_input_length</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="c1"># remove_input_padding requires these fields as explicit input</span>
<span class="n">mask</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">remove_input_padding</span><span class="p">:</span>
<span class="n">seq_len_2d</span> <span class="o">=</span> <span class="n">concat</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="n">shape</span><span class="p">(</span><span class="n">input_ids</span><span class="p">,</span> <span class="mi">1</span><span class="p">)])</span>
<span class="c1"># create position ids</span>
<span class="n">position_ids_buffer</span> <span class="o">=</span> <span class="n">constant</span><span class="p">(</span>
<span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span><span class="p">(</span>
<span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">max_position_embeddings</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">int32</span><span class="p">),</span>
<span class="mi">0</span><span class="p">))</span>
<span class="n">tmp_position_ids</span> <span class="o">=</span> <span class="nb">slice</span><span class="p">(</span><span class="n">position_ids_buffer</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="mi">0</span><span class="p">],</span>
<span class="n">sizes</span><span class="o">=</span><span class="n">seq_len_2d</span><span class="p">)</span>
<span class="n">tmp_position_ids</span> <span class="o">=</span> <span class="n">expand</span><span class="p">(</span><span class="n">tmp_position_ids</span><span class="p">,</span> <span class="n">shape</span><span class="p">(</span><span class="n">input_ids</span><span class="p">))</span> <span class="c1">#BxL</span>
<span class="n">tmp_input_lengths</span> <span class="o">=</span> <span class="n">unsqueeze</span><span class="p">(</span><span class="n">input_lengths</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> <span class="c1">#Bx1</span>
<span class="n">tmp_input_lengths</span> <span class="o">=</span> <span class="n">expand</span><span class="p">(</span><span class="n">tmp_input_lengths</span><span class="p">,</span>
<span class="n">shape</span><span class="p">(</span><span class="n">input_ids</span><span class="p">))</span> <span class="c1">#BxL</span>
<span class="n">mask</span> <span class="o">=</span> <span class="n">tmp_position_ids</span> <span class="o">&lt;</span> <span class="n">tmp_input_lengths</span> <span class="c1"># BxL</span>
<span class="n">mask</span> <span class="o">=</span> <span class="n">mask</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="s1">&#39;int32&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">position_ids</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_roberta</span><span class="p">:</span>
<span class="c1"># see create_position_ids_from_input_ids() in https://github.com/huggingface/transformers/blob/main/src/transformers/models/roberta/modeling_roberta.py</span>
<span class="n">position_ids</span> <span class="o">=</span> <span class="p">(</span><span class="n">tmp_position_ids</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="n">mask</span>
<span class="n">position_ids</span> <span class="o">=</span> <span class="n">position_ids</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">padding_idx</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">position_ids</span> <span class="o">=</span> <span class="nb">slice</span><span class="p">(</span><span class="n">position_ids_buffer</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="mi">0</span><span class="p">],</span>
<span class="n">sizes</span><span class="o">=</span><span class="n">seq_len_2d</span><span class="p">)</span>
<span class="n">position_ids</span> <span class="o">=</span> <span class="n">expand</span><span class="p">(</span><span class="n">position_ids</span><span class="p">,</span> <span class="n">shape</span><span class="p">(</span><span class="n">input_ids</span><span class="p">))</span>
<span class="c1"># create token_type_ids</span>
<span class="k">if</span> <span class="n">token_type_ids</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">token_type_ids_buffer</span> <span class="o">=</span> <span class="n">constant</span><span class="p">(</span>
<span class="n">np</span><span class="o">.</span><span class="n">expand_dims</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="bp">self</span><span class="o">.</span><span class="n">max_position_embeddings</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">int32</span><span class="p">),</span>
<span class="mi">0</span><span class="p">))</span>
<span class="n">token_type_ids</span> <span class="o">=</span> <span class="nb">slice</span><span class="p">(</span><span class="n">token_type_ids_buffer</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="mi">0</span><span class="p">],</span>
<span class="n">sizes</span><span class="o">=</span><span class="n">seq_len_2d</span><span class="p">)</span>
<span class="n">token_type_ids</span> <span class="o">=</span> <span class="n">expand</span><span class="p">(</span><span class="n">token_type_ids</span><span class="p">,</span> <span class="n">shape</span><span class="p">(</span><span class="n">input_ids</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">embedding</span><span class="p">(</span><span class="n">input_ids</span><span class="p">,</span> <span class="n">position_ids</span><span class="p">,</span> <span class="n">token_type_ids</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">register_network_output</span><span class="p">(</span><span class="s1">&#39;embedding_output&#39;</span><span class="p">,</span> <span class="n">hidden_states</span><span class="p">)</span>
<span class="k">for</span> <span class="n">idx</span><span class="p">,</span> <span class="n">layer</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">layers</span><span class="p">):</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">layer</span><span class="p">(</span><span class="n">hidden_states</span><span class="o">=</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="n">input_lengths</span><span class="o">=</span><span class="n">input_lengths</span><span class="p">,</span>
<span class="n">attention_mask</span><span class="o">=</span><span class="n">mask</span><span class="p">,</span>
<span class="n">max_input_length</span><span class="o">=</span><span class="n">max_input_length</span><span class="p">)</span>
<span class="c1"># keep the last layer output name as hidden_states</span>
<span class="k">if</span> <span class="p">((</span><span class="n">idx</span> <span class="o">==</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">num_hidden_layers</span> <span class="o">-</span> <span class="mi">1</span><span class="p">))</span> <span class="ow">and</span>
<span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">architecture</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">&quot;BertModel&quot;</span><span class="p">,</span> <span class="s2">&quot;RobertaModel&quot;</span><span class="p">])):</span>
<span class="n">hidden_states</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;hidden_states&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</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">register_network_output</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;layer_</span><span class="si">{</span><span class="n">idx</span><span class="si">}</span><span class="s2">_output&quot;</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>
<span class="n">RobertaModel</span> <span class="o">=</span> <span class="n">BertModel</span>
<div class="viewcode-block" id="BertForQuestionAnswering">
<a class="viewcode-back" href="../../../../legacy/python-api/tensorrt_llm.models.html#tensorrt_llm.models.BertForQuestionAnswering">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">BertForQuestionAnswering</span><span class="p">(</span><span class="n">BertBase</span><span class="p">):</span>
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">config</span><span class="p">:</span> <span class="n">BERTConfig</span><span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">config</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bert</span> <span class="o">=</span> <span class="n">BertModel</span><span class="p">(</span><span class="n">config</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">num_labels</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">num_labels</span>
<span class="bp">self</span><span class="o">.</span><span class="n">qa_outputs</span> <span class="o">=</span> <span class="n">Linear</span><span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">config</span><span class="o">.</span><span class="n">num_labels</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<div class="viewcode-block" id="BertForQuestionAnswering.forward">
<a class="viewcode-back" href="../../../../legacy/python-api/tensorrt_llm.models.html#tensorrt_llm.models.BertForQuestionAnswering.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">input_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">input_lengths</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">token_type_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">position_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">hidden_states</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">max_input_length</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">remove_input_padding</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">remove_input_padding</span>
<span class="k">if</span> <span class="n">remove_input_padding</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">token_type_ids</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> \
<span class="n">position_ids</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> \
<span class="n">max_input_length</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">,</span> \
<span class="s2">&quot;token_type_ids, position_ids, max_input_length is required &quot;</span> \
<span class="s2">&quot;in remove_input_padding mode&quot;</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">bert</span><span class="o">.</span><span class="n">forward</span><span class="p">(</span><span class="n">input_ids</span><span class="o">=</span><span class="n">input_ids</span><span class="p">,</span>
<span class="n">input_lengths</span><span class="o">=</span><span class="n">input_lengths</span><span class="p">,</span>
<span class="n">token_type_ids</span><span class="o">=</span><span class="n">token_type_ids</span><span class="p">,</span>
<span class="n">position_ids</span><span class="o">=</span><span class="n">position_ids</span><span class="p">,</span>
<span class="n">hidden_states</span><span class="o">=</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="n">max_input_length</span><span class="o">=</span><span class="n">max_input_length</span><span class="p">)</span>
<span class="n">logits</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">qa_outputs</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">logits</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;logits&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">logits_dtype</span><span class="p">)</span>
<span class="k">return</span> <span class="n">logits</span></div>
</div>
<span class="n">RobertaForQuestionAnswering</span> <span class="o">=</span> <span class="n">BertForQuestionAnswering</span>
<span class="k">class</span><span class="w"> </span><span class="nc">BertPooler</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">hidden_size</span><span class="p">,</span> <span class="n">dtype</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">dense</span> <span class="o">=</span> <span class="n">Linear</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span> <span class="n">hidden_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="bp">self</span><span class="o">.</span><span class="n">activation</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="s1">&#39;tanh&#39;</span><span class="p">]</span>
<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">hidden_states</span><span class="p">,</span> <span class="n">input_lengths</span><span class="p">,</span> <span class="n">remove_input_padding</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">remove_input_padding</span><span class="p">:</span>
<span class="c1"># We &quot;pool&quot; the model by simply taking the hidden state corresponding</span>
<span class="c1"># to the first token.</span>
<span class="n">first_token_tensor</span> <span class="o">=</span> <span class="n">select</span><span class="p">(</span><span class="n">hidden_states</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="k">else</span><span class="p">:</span>
<span class="c1"># when remove_input_padding is enabled, the shape of hidden_states is [num_tokens, hidden_size]</span>
<span class="c1"># We can take the first token of each sequence according to input_lengths,</span>
<span class="c1"># and then do pooling similar to padding mode.</span>
<span class="c1"># For example, if input_lengths is [8, 5, 6], then the indices of first tokens</span>
<span class="c1"># should be [0, 8, 13]</span>
<span class="n">first_token_indices</span> <span class="o">=</span> <span class="n">cumsum</span><span class="p">(</span>
<span class="n">concat</span><span class="p">([</span>
<span class="mi">0</span><span class="p">,</span>
<span class="nb">slice</span><span class="p">(</span><span class="n">input_lengths</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">sizes</span><span class="o">=</span><span class="p">(</span><span class="n">shape</span><span class="p">(</span><span class="n">input_lengths</span><span class="p">)</span> <span class="o">-</span>
<span class="n">constant</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mi">1</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">int32</span><span class="p">))))</span>
<span class="p">]),</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">first_token_tensor</span> <span class="o">=</span> <span class="n">index_select</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span>
<span class="n">first_token_indices</span><span class="p">)</span>
<span class="n">pooled_output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dense</span><span class="p">(</span><span class="n">first_token_tensor</span><span class="p">)</span>
<span class="n">pooled_output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span><span class="p">(</span><span class="n">pooled_output</span><span class="p">)</span>
<span class="k">return</span> <span class="n">pooled_output</span>
<span class="k">class</span><span class="w"> </span><span class="nc">RobertaClassificationHead</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Head for sentence-level classification tasks.&quot;&quot;&quot;</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">hidden_size</span><span class="p">,</span> <span class="n">dtype</span><span class="p">,</span> <span class="n">num_labels</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">dense</span> <span class="o">=</span> <span class="n">Linear</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span> <span class="n">hidden_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="bp">self</span><span class="o">.</span><span class="n">out_proj</span> <span class="o">=</span> <span class="n">Linear</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span> <span class="n">num_labels</span><span class="p">)</span>
<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">hidden_states</span><span class="p">,</span> <span class="n">input_lengths</span><span class="p">,</span> <span class="n">remove_input_padding</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">remove_input_padding</span><span class="p">:</span>
<span class="c1"># We &quot;pool&quot; the model by simply taking the hidden state corresponding</span>
<span class="c1"># to the first token.</span>
<span class="n">first_token_tensor</span> <span class="o">=</span> <span class="n">select</span><span class="p">(</span><span class="n">hidden_states</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="k">else</span><span class="p">:</span>
<span class="c1"># when remove_input_padding is enabled, the shape of hidden_states is [num_tokens, hidden_size]</span>
<span class="c1"># We can take the first token of each sequence according to input_lengths,</span>
<span class="c1"># and then do pooling similar to padding mode.</span>
<span class="c1"># For example, if input_lengths is [8, 5, 6], then the indices of first tokens</span>
<span class="c1"># should be [0, 8, 13]</span>
<span class="n">first_token_indices</span> <span class="o">=</span> <span class="n">cumsum</span><span class="p">(</span>
<span class="n">concat</span><span class="p">([</span>
<span class="mi">0</span><span class="p">,</span>
<span class="nb">slice</span><span class="p">(</span><span class="n">input_lengths</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">sizes</span><span class="o">=</span><span class="p">(</span><span class="n">shape</span><span class="p">(</span><span class="n">input_lengths</span><span class="p">)</span> <span class="o">-</span>
<span class="n">constant</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mi">1</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">int32</span><span class="p">))))</span>
<span class="p">]),</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">first_token_tensor</span> <span class="o">=</span> <span class="n">index_select</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span>
<span class="n">first_token_indices</span><span class="p">)</span>
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dense</span><span class="p">(</span><span class="n">first_token_tensor</span><span class="p">)</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="s1">&#39;tanh&#39;</span><span class="p">](</span><span class="n">x</span><span class="p">)</span>
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">out_proj</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span>
<div class="viewcode-block" id="BertForSequenceClassification">
<a class="viewcode-back" href="../../../../legacy/python-api/tensorrt_llm.models.html#tensorrt_llm.models.BertForSequenceClassification">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">BertForSequenceClassification</span><span class="p">(</span><span class="n">BertBase</span><span class="p">):</span>
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">config</span><span class="p">:</span> <span class="n">BERTConfig</span><span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">config</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">config</span> <span class="o">=</span> <span class="n">config</span>
<span class="bp">self</span><span class="o">.</span><span class="n">is_roberta</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">is_roberta</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bert</span> <span class="o">=</span> <span class="n">BertModel</span><span class="p">(</span><span class="n">config</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">num_labels</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">num_labels</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">config</span><span class="o">.</span><span class="n">is_roberta</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">pooler</span> <span class="o">=</span> <span class="n">BertPooler</span><span class="p">(</span><span class="n">hidden_size</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">classifier</span> <span class="o">=</span> <span class="n">Linear</span><span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">config</span><span class="o">.</span><span class="n">num_labels</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</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">classifier</span> <span class="o">=</span> <span class="n">RobertaClassificationHead</span><span class="p">(</span>
<span class="n">hidden_size</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">num_labels</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">num_labels</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<div class="viewcode-block" id="BertForSequenceClassification.forward">
<a class="viewcode-back" href="../../../../legacy/python-api/tensorrt_llm.models.html#tensorrt_llm.models.BertForSequenceClassification.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">input_ids</span><span class="p">,</span>
<span class="n">input_lengths</span><span class="p">,</span>
<span class="n">token_type_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">position_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">hidden_states</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">max_input_length</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">remove_input_padding</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">remove_input_padding</span>
<span class="c1"># required as explicit input in remove_input_padding mode</span>
<span class="c1"># see examples/models/core/bert/run_remove_input_padding.py for how to create them from input_ids and input_lengths</span>
<span class="k">if</span> <span class="n">remove_input_padding</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">token_type_ids</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> \
<span class="n">position_ids</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> \
<span class="n">max_input_length</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">,</span> \
<span class="s2">&quot;token_type_ids, position_ids, max_input_length is required &quot;</span> \
<span class="s2">&quot;in remove_input_padding mode&quot;</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">bert</span><span class="o">.</span><span class="n">forward</span><span class="p">(</span><span class="n">input_ids</span><span class="o">=</span><span class="n">input_ids</span><span class="p">,</span>
<span class="n">input_lengths</span><span class="o">=</span><span class="n">input_lengths</span><span class="p">,</span>
<span class="n">token_type_ids</span><span class="o">=</span><span class="n">token_type_ids</span><span class="p">,</span>
<span class="n">position_ids</span><span class="o">=</span><span class="n">position_ids</span><span class="p">,</span>
<span class="n">hidden_states</span><span class="o">=</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="n">max_input_length</span><span class="o">=</span><span class="n">max_input_length</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_roberta</span><span class="p">:</span>
<span class="n">pooled_output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pooler</span><span class="p">(</span>
<span class="n">hidden_states</span><span class="o">=</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="n">input_lengths</span><span class="o">=</span><span class="n">input_lengths</span><span class="p">,</span>
<span class="n">remove_input_padding</span><span class="o">=</span><span class="n">remove_input_padding</span><span class="p">)</span>
<span class="n">logits</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">classifier</span><span class="p">(</span><span class="n">pooled_output</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">logits</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">classifier</span><span class="p">(</span><span class="n">hidden_states</span><span class="o">=</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="n">input_lengths</span><span class="o">=</span><span class="n">input_lengths</span><span class="p">,</span>
<span class="n">remove_input_padding</span><span class="o">=</span><span class="n">remove_input_padding</span><span class="p">)</span>
<span class="n">logits</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;logits&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">logits_dtype</span><span class="p">)</span>
<span class="k">return</span> <span class="n">logits</span></div>
</div>
<span class="n">RobertaForSequenceClassification</span> <span class="o">=</span> <span class="n">BertForSequenceClassification</span>
</pre></div>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
</div>
</footer>
</div>
<div class="bd-sidebar-secondary"></div>
</div>
<footer class="bd-footer-content">
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script defer src="../../../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf"></script>
<script defer src="../../../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf"></script>
<footer class="bd-footer">
<div class="bd-footer__inner bd-page-width">
<div class="footer-items__start">
<div class="footer-item">
<a class="footer-brand logo" href="https://www.nvidia.com">
<img src="../../../../_static/nvidia-logo-horiz-rgb-1c-blk-for-screen.svg" class="logo__image only-light" alt="NVIDIA"/>
<img src="../../../../_static/nvidia-logo-horiz-rgb-1c-wht-for-screen.svg" class="logo__image only-dark" alt="NVIDIA"/>
</a></div>
<div class="footer-item">
<div class="footer-links">
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/">Privacy Policy</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-center/">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>
Reference in New Issue View Git Blame Copy Permalink