mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
970 lines
86 KiB
HTML
970 lines
86 KiB
HTML
|
|
|
|
<!DOCTYPE html>
|
|
|
|
|
|
<html lang="en" data-content_root="../../../../" >
|
|
|
|
<head>
|
|
<meta charset="utf-8" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
<title>tensorrt_llm.models.gpt.config — TensorRT-LLM</title>
|
|
|
|
|
|
|
|
<script data-cfasync="false">
|
|
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
|
|
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
|
|
</script>
|
|
<!--
|
|
this give us a css class that will be invisible only if js is disabled
|
|
-->
|
|
<noscript>
|
|
<style>
|
|
.pst-js-only { display: none !important; }
|
|
|
|
</style>
|
|
</noscript>
|
|
|
|
<!-- Loaded before other Sphinx assets -->
|
|
<link href="../../../../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
|
|
<link href="../../../../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
|
|
|
|
<link rel="stylesheet" type="text/css" href="../../../../_static/pygments.css?v=8f2a1f02" />
|
|
<link rel="stylesheet" type="text/css" href="../../../../_static/styles/nvidia-sphinx-theme.css?v=df3ac72c" />
|
|
<link rel="stylesheet" type="text/css" href="../../../../_static/copybutton.css?v=76b2166b" />
|
|
<link rel="stylesheet" type="text/css" href="../../../../_static/autodoc_pydantic.css" />
|
|
|
|
<!-- So that users can add custom icons -->
|
|
<script src="../../../../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script>
|
|
<!-- Pre-loaded scripts that we'll load fully later -->
|
|
<link rel="preload" as="script" href="../../../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" />
|
|
<link rel="preload" as="script" href="../../../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" />
|
|
|
|
<script src="../../../../_static/documentation_options.js?v=5929fcd5"></script>
|
|
<script src="../../../../_static/doctools.js?v=9a2dae69"></script>
|
|
<script src="../../../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
|
<script src="../../../../_static/clipboard.min.js?v=a7894cd8"></script>
|
|
<script src="../../../../_static/copybutton.js?v=65e89d2a"></script>
|
|
<script>DOCUMENTATION_OPTIONS.pagename = '_modules/tensorrt_llm/models/gpt/config';</script>
|
|
<script>
|
|
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
|
|
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
|
|
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '0.21.0rc0';
|
|
DOCUMENTATION_OPTIONS.show_version_warning_banner =
|
|
false;
|
|
</script>
|
|
<link rel="icon" href="../../../../_static/favicon.png"/>
|
|
<link rel="index" title="Index" href="../../../../genindex.html" />
|
|
<link rel="search" title="Search" href="../../../../search.html" />
|
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
|
<meta name="docsearch:language" content="en"/>
|
|
<meta name="docsearch:version" content="0.21.0rc0" />
|
|
|
|
|
|
</head>
|
|
|
|
|
|
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
|
|
|
|
|
|
|
|
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
|
|
|
|
<div id="pst-scroll-pixel-helper"></div>
|
|
|
|
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
|
|
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
|
|
|
|
|
|
<dialog id="pst-search-dialog">
|
|
|
|
<form class="bd-search d-flex align-items-center"
|
|
action="../../../../search.html"
|
|
method="get">
|
|
<i class="fa-solid fa-magnifying-glass"></i>
|
|
<input type="search"
|
|
class="form-control"
|
|
name="q"
|
|
placeholder="Search the docs ..."
|
|
aria-label="Search the docs ..."
|
|
autocomplete="off"
|
|
autocorrect="off"
|
|
autocapitalize="off"
|
|
spellcheck="false"/>
|
|
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
|
|
</form>
|
|
</dialog>
|
|
|
|
<div class="pst-async-banner-revealer d-none">
|
|
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
|
|
</div>
|
|
|
|
|
|
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
|
|
<div class="bd-header__inner bd-page-width">
|
|
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
|
|
<span class="fa-solid fa-bars"></span>
|
|
</button>
|
|
|
|
|
|
<div class="col-lg-3 navbar-header-items__start">
|
|
|
|
<div class="navbar-item">
|
|
|
|
|
|
|
|
|
|
|
|
<a class="navbar-brand logo" href="../../../../index.html">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<img src="../../../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
|
|
<img src="../../../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
|
|
|
|
|
|
<p class="title logo__title">TensorRT-LLM</p>
|
|
|
|
</a></div>
|
|
|
|
</div>
|
|
|
|
<div class="col-lg-9 navbar-header-items">
|
|
|
|
<div class="me-auto navbar-header-items__center">
|
|
|
|
<div class="navbar-item">
|
|
|
|
|
|
<div class="version-switcher__container dropdown pst-js-only">
|
|
<button id="pst-version-switcher-button-2"
|
|
type="button"
|
|
class="version-switcher__button btn btn-sm dropdown-toggle"
|
|
data-bs-toggle="dropdown"
|
|
aria-haspopup="listbox"
|
|
aria-controls="pst-version-switcher-list-2"
|
|
aria-label="Version switcher list"
|
|
>
|
|
Choose version <!-- this text may get changed later by javascript -->
|
|
<span class="caret"></span>
|
|
</button>
|
|
<div id="pst-version-switcher-list-2"
|
|
class="version-switcher__menu dropdown-menu list-group-flush py-0"
|
|
role="listbox" aria-labelledby="pst-version-switcher-button-2">
|
|
<!-- dropdown will be populated by javascript on page load -->
|
|
</div>
|
|
</div></div>
|
|
|
|
</div>
|
|
|
|
|
|
<div class="navbar-header-items__end">
|
|
|
|
<div class="navbar-item navbar-persistent--container">
|
|
|
|
|
|
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<i class="fa-solid fa-magnifying-glass"></i>
|
|
<span class="search-button__default-text">Search</span>
|
|
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
|
</button>
|
|
</div>
|
|
|
|
|
|
<div class="navbar-item">
|
|
|
|
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
|
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
|
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
|
</button></div>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
|
|
<div class="navbar-persistent--mobile">
|
|
|
|
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<i class="fa-solid fa-magnifying-glass"></i>
|
|
<span class="search-button__default-text">Search</span>
|
|
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
|
</button>
|
|
</div>
|
|
|
|
|
|
|
|
</div>
|
|
|
|
</header>
|
|
|
|
|
|
<div class="bd-container">
|
|
<div class="bd-container__inner bd-page-width">
|
|
|
|
|
|
|
|
<dialog id="pst-primary-sidebar-modal"></dialog>
|
|
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<a class="navbar-brand logo" href="../../../../index.html">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<img src="../../../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
|
|
<img src="../../../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
|
|
|
|
|
|
<p class="title logo__title">TensorRT-LLM</p>
|
|
|
|
</a>
|
|
|
|
|
|
|
|
<div class="sidebar-header-items sidebar-primary__section">
|
|
|
|
|
|
<div class="sidebar-header-items__center">
|
|
|
|
|
|
|
|
<div class="navbar-item">
|
|
|
|
|
|
<div class="version-switcher__container dropdown pst-js-only">
|
|
<button id="pst-version-switcher-button-3"
|
|
type="button"
|
|
class="version-switcher__button btn btn-sm dropdown-toggle"
|
|
data-bs-toggle="dropdown"
|
|
aria-haspopup="listbox"
|
|
aria-controls="pst-version-switcher-list-3"
|
|
aria-label="Version switcher list"
|
|
>
|
|
Choose version <!-- this text may get changed later by javascript -->
|
|
<span class="caret"></span>
|
|
</button>
|
|
<div id="pst-version-switcher-list-3"
|
|
class="version-switcher__menu dropdown-menu list-group-flush py-0"
|
|
role="listbox" aria-labelledby="pst-version-switcher-button-3">
|
|
<!-- dropdown will be populated by javascript on page load -->
|
|
</div>
|
|
</div></div>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<div class="sidebar-header-items__end">
|
|
|
|
<div class="navbar-item">
|
|
|
|
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
|
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
|
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
|
</button></div>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<div class="sidebar-primary-items__start sidebar-primary__section">
|
|
<div class="sidebar-primary-item">
|
|
|
|
|
|
|
|
<nav class="bd-docs-nav bd-links"
|
|
aria-label="Table of Contents">
|
|
<p class="bd-links__title" role="heading" aria-level="1">Table of Contents</p>
|
|
<div class="bd-toc-item navbar-nav"><p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../overview.html">Overview</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../quick-start-guide.html">Quick Start Guide</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../key-features.html">Key Features</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../torch.html">PyTorch Backend</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../release-notes.html">Release Notes</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Installation</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../installation/linux.html">Installing on Linux</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../installation/grace-hopper.html">Installing on Grace Hopper</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">LLM API</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../llm-api/index.html">API Introduction</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../llm-api/reference.html">API Reference</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Examples</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../examples/index.html">LLM Examples Introduction</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_medusa_decoding.html">Generate Text Using Medusa Decoding</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_eagle_decoding.html">Generate Text Using Eagle Decoding</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_distributed.html">Distributed LLM Generation</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_eagle2_decoding.html">Generate Text Using Eagle2 Decoding</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_inference_kv_events.html">Get KV Cache Events</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_quantization.html">Generation with Quantization</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_inference_async_streaming.html">Generate Text in Streaming</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_inference.html">Generate text</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_inference_customize.html">Generate text with customization</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
|
|
</ul>
|
|
</details></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../examples/customization.html">LLM Common Customizations</a></li>
|
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../examples/llm_api_examples.html">LLM Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_medusa_decoding.html">Generate Text Using Medusa Decoding</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_eagle_decoding.html">Generate Text Using Eagle Decoding</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_distributed.html">Distributed LLM Generation</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_eagle2_decoding.html">Generate Text Using Eagle2 Decoding</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_inference_kv_events.html">Get KV Cache Events</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_quantization.html">Generation with Quantization</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_inference_async_streaming.html">Generate Text in Streaming</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_inference.html">Generate text</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_inference_customize.html">Generate text with customization</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_mgmn_llm_distributed.html">Llm Mgmn Llm Distributed</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_mgmn_trtllm_bench.html">Llm Mgmn Trtllm Bench</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/llm_mgmn_trtllm_serve.html">Llm Mgmn Trtllm Serve</a></li>
|
|
</ul>
|
|
</details></li>
|
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../examples/trtllm_serve_examples.html">Online Serving Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/curl_chat_client.html">Curl Chat Client</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/curl_completion_client.html">Curl Completion Client</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/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</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
|
|
</ul>
|
|
</details></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Model Definition API</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../python-api/tensorrt_llm.layers.html">Layers</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../python-api/tensorrt_llm.functional.html">Functionals</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../python-api/tensorrt_llm.models.html">Models</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../python-api/tensorrt_llm.plugin.html">Plugin</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../python-api/tensorrt_llm.quantization.html">Quantization</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../python-api/tensorrt_llm.runtime.html">Runtime</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">C++ API</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../_cpp_gen/executor.html">Executor</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../_cpp_gen/runtime.html">Runtime</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../commands/trtllm-build.html">trtllm-build</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../commands/trtllm-serve.html">trtllm-serve</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Architecture</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../architecture/overview.html">TensorRT-LLM Architecture</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../architecture/core-concepts.html">Model Definition</a></li>
|
|
|
|
|
|
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../architecture/checkpoint.html">TensorRT-LLM Checkpoint</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../architecture/workflow.html">TensorRT-LLM Build Workflow</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../architecture/add-model.html">Adding a Model</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Advanced</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/gpt-attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/gpt-runtime.html">C++ GPT Runtime</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/executor.html">Executor API</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/graph-rewriting.html">Graph Rewriting Module</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/lora.html">Run gpt-2b + LoRA using Executor / cpp runtime</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/expert-parallelism.html">Expert Parallelism in TensorRT-LLM</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/kv-cache-management.html">KV Cache Management: Pools, Blocks, and Events</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/kv-cache-reuse.html">KV cache reuse</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/speculative-decoding.html">Speculative Sampling</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/disaggregated-service.html">Disaggregated-Service (experimental)</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Performance</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../performance/perf-overview.html">Overview</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../performance/perf-benchmarking.html">Benchmarking</a></li>
|
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../../performance/performance-tuning-guide/index.html">Performance Tuning Guide</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../performance/performance-tuning-guide/benchmarking-default-performance.html">Benchmarking Default Performance</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../performance/performance-tuning-guide/useful-build-time-flags.html">Useful Build-Time Flags</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.html">Tuning Max Batch Size and Max Num Tokens</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../performance/performance-tuning-guide/deciding-model-sharding-strategy.html">Deciding Model Sharding Strategy</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../performance/performance-tuning-guide/fp8-quantization.html">FP8 Quantization</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../../../../performance/performance-tuning-guide/useful-runtime-flags.html">Useful Runtime Options</a></li>
|
|
</ul>
|
|
</details></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../performance/perf-analysis.html">Performance Analysis</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Reference</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../reference/troubleshooting.html">Troubleshooting</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../reference/support-matrix.html">Support Matrix</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../reference/precision.html">Numerical Precision</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../reference/memory.html">Memory Usage of TensorRT-LLM</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../blogs/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../blogs/H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../blogs/Falcon180B-H200.html">Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../blogs/quantization-in-TRT-LLM.html">Speed up inference with SOTA quantization techniques in TRT-LLM</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../blogs/XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../../blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html">Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs</a></li>
|
|
<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>
|
|
</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.gpt.config</span></li>
|
|
</ul>
|
|
</nav>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<div id="searchbox"></div>
|
|
<article class="bd-article">
|
|
|
|
<h1>Source code for tensorrt_llm.models.gpt.config</h1><div class="highlight"><pre>
|
|
<span></span><span class="c1"># SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.</span>
|
|
<span class="c1"># SPDX-License-Identifier: Apache-2.0</span>
|
|
<span class="c1">#</span>
|
|
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
|
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
|
<span class="c1"># You may obtain a copy of the License at</span>
|
|
<span class="c1">#</span>
|
|
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
|
<span class="c1">#</span>
|
|
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
|
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
|
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
|
<span class="c1"># See the License for the specific language governing permissions and</span>
|
|
<span class="c1"># limitations under the License.</span>
|
|
|
|
<span class="kn">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">Union</span>
|
|
|
|
<span class="kn">import</span><span class="w"> </span><span class="nn">torch</span>
|
|
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">...layers</span><span class="w"> </span><span class="kn">import</span> <span class="n">MoeConfig</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">...logger</span><span class="w"> </span><span class="kn">import</span> <span class="n">logger</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">...mapping</span><span class="w"> </span><span class="kn">import</span> <span class="n">Mapping</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">..convert_utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">infer_dtype</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">PretrainedConfig</span><span class="p">,</span> <span class="n">QuantConfig</span>
|
|
|
|
|
|
<div class="viewcode-block" id="GPTConfig">
|
|
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.GPTConfig">[docs]</a>
|
|
<span class="k">class</span><span class="w"> </span><span class="nc">GPTConfig</span><span class="p">(</span><span class="n">PretrainedConfig</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="o">*</span><span class="p">,</span>
|
|
<span class="n">gpt_variant</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s1">'gpt2'</span><span class="p">,</span>
|
|
<span class="n">bias</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
|
|
<span class="n">q_scaling</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span>
|
|
<span class="n">embedding_scale</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
|
<span class="n">apply_query_key_layer_scaling</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
|
|
<span class="n">rotary_pct</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span>
|
|
<span class="n">rotary_base</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">10000.0</span><span class="p">,</span>
|
|
<span class="n">rotary_scaling</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">dict</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
|
<span class="n">inner_layernorm</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
|
|
<span class="n">norm_before_bmm1</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
|
|
<span class="n">moe</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Union</span><span class="p">[</span><span class="n">MoeConfig</span><span class="p">,</span> <span class="nb">dict</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="bp">self</span><span class="o">.</span><span class="n">gpt_variant</span> <span class="o">=</span> <span class="n">gpt_variant</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="n">bias</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">q_scaling</span> <span class="o">=</span> <span class="n">q_scaling</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">embedding_scale</span> <span class="o">=</span> <span class="n">embedding_scale</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">apply_query_key_layer_scaling</span> <span class="o">=</span> <span class="n">apply_query_key_layer_scaling</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">rotary_pct</span> <span class="o">=</span> <span class="n">rotary_pct</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">rotary_base</span> <span class="o">=</span> <span class="n">rotary_base</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">rotary_scaling</span> <span class="o">=</span> <span class="n">rotary_scaling</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span> <span class="o">=</span> <span class="n">inner_layernorm</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">norm_before_bmm1</span> <span class="o">=</span> <span class="n">norm_before_bmm1</span>
|
|
<span class="k">if</span> <span class="n">moe</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="c1"># Legacy MOE config fields</span>
|
|
<span class="n">moe</span> <span class="o">=</span> <span class="n">MoeConfig</span><span class="p">(</span>
|
|
<span class="n">num_experts</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">'moe_num_experts'</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span>
|
|
<span class="n">top_k</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">'moe_top_k'</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span>
|
|
<span class="n">normalization_mode</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">'moe_normalization_mode'</span><span class="p">,</span>
|
|
<span class="n">MoeConfig</span><span class="o">.</span><span class="n">ExpertScaleNormalizationMode</span><span class="o">.</span><span class="n">RENORMALIZE</span><span class="p">))</span>
|
|
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">moe</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span>
|
|
<span class="n">moe</span> <span class="o">=</span> <span class="n">MoeConfig</span><span class="o">.</span><span class="n">from_dict</span><span class="p">(</span><span class="n">moe</span><span class="p">)</span>
|
|
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">moe</span><span class="p">,</span> <span class="n">MoeConfig</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">moe</span> <span class="o">=</span> <span class="n">moe</span><span class="o">.</span><span class="n">validate</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="o">**</span><span class="n">kwargs</span><span class="p">)</span>
|
|
|
|
<div class="viewcode-block" id="GPTConfig.to_dict">
|
|
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.GPTConfig.to_dict">[docs]</a>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">to_dict</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="n">output</span> <span class="o">=</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">to_dict</span><span class="p">()</span>
|
|
<span class="c1"># Serialize the fields added in GPTConfig</span>
|
|
<span class="n">output</span><span class="p">[</span><span class="s1">'gpt_variant'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">gpt_variant</span>
|
|
<span class="n">output</span><span class="p">[</span><span class="s1">'bias'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">bias</span>
|
|
<span class="n">output</span><span class="p">[</span><span class="s1">'q_scaling'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">q_scaling</span>
|
|
<span class="n">output</span><span class="p">[</span><span class="s1">'embedding_scale'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">embedding_scale</span>
|
|
<span class="n">output</span><span class="p">[</span>
|
|
<span class="s1">'apply_query_key_layer_scaling'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">apply_query_key_layer_scaling</span>
|
|
<span class="n">output</span><span class="p">[</span><span class="s1">'rotary_pct'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">rotary_pct</span>
|
|
<span class="n">output</span><span class="p">[</span><span class="s1">'rotary_base'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">rotary_base</span>
|
|
<span class="n">output</span><span class="p">[</span><span class="s1">'rotary_scaling'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">rotary_scaling</span>
|
|
<span class="n">output</span><span class="p">[</span><span class="s1">'inner_layernorm'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span>
|
|
<span class="n">output</span><span class="p">[</span><span class="s1">'norm_before_bmm1'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">norm_before_bmm1</span>
|
|
<span class="n">output</span><span class="p">[</span><span class="s1">'moe'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">moe</span><span class="o">.</span><span class="n">to_dict</span><span class="p">()</span>
|
|
<span class="k">return</span> <span class="n">output</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="GPTConfig.from_hugging_face">
|
|
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.GPTConfig.from_hugging_face">[docs]</a>
|
|
<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_config_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">'transformers.PretrainedConfig'</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">'auto'</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="kn">import</span><span class="w"> </span><span class="nn">transformers</span>
|
|
<span class="n">trust_remote_code</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">'trust_remote_code'</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</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="n">get_needed_padding</span>
|
|
|
|
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">hf_config_or_dir</span><span class="p">,</span> <span class="n">transformers</span><span class="o">.</span><span class="n">PretrainedConfig</span><span class="p">):</span>
|
|
<span class="n">hf_config</span> <span class="o">=</span> <span class="n">hf_config_or_dir</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">hf_config</span> <span class="o">=</span> <span class="n">transformers</span><span class="o">.</span><span class="n">AutoConfig</span><span class="o">.</span><span class="n">from_pretrained</span><span class="p">(</span>
|
|
<span class="n">hf_config_or_dir</span><span class="p">,</span> <span class="n">trust_remote_code</span><span class="o">=</span><span class="n">trust_remote_code</span><span class="p">)</span>
|
|
|
|
<span class="n">gpt_variant</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">'gpt_variant'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">gpt_variant</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Inferring gpt variant from path..."</span><span class="p">)</span>
|
|
<span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="p">[</span>
|
|
<span class="s1">'starcoder2'</span><span class="p">,</span> <span class="s1">'starcoder'</span><span class="p">,</span> <span class="s1">'santacoder'</span><span class="p">,</span> <span class="s1">'gpt2'</span><span class="p">,</span>
|
|
<span class="s1">'persimmon'</span><span class="p">,</span> <span class="s1">'fuyu'</span><span class="p">,</span> <span class="s1">'kosmos-2'</span><span class="p">,</span> <span class="s1">'jais'</span><span class="p">,</span> <span class="s1">'nemotron'</span>
|
|
<span class="p">]:</span>
|
|
<span class="k">if</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">_name_or_path</span> <span class="ow">or</span> <span class="n">v</span> <span class="o">==</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">model_type</span><span class="p">:</span>
|
|
<span class="n">gpt_variant</span> <span class="o">=</span> <span class="n">v</span>
|
|
<span class="k">break</span>
|
|
<span class="k">if</span> <span class="n">gpt_variant</span> <span class="o">==</span> <span class="s1">'fuyu'</span><span class="p">:</span>
|
|
<span class="n">gpt_variant</span> <span class="o">=</span> <span class="s1">'persimmon'</span>
|
|
|
|
<span class="k">assert</span> <span class="n">gpt_variant</span> <span class="ow">in</span> <span class="p">[</span>
|
|
<span class="s1">'gpt2'</span><span class="p">,</span> <span class="s1">'santacoder'</span><span class="p">,</span> <span class="s1">'starcoder'</span><span class="p">,</span> <span class="s1">'starcoder2'</span><span class="p">,</span> <span class="s1">'persimmon'</span><span class="p">,</span>
|
|
<span class="s1">'kosmos-2'</span><span class="p">,</span> <span class="s1">'jais'</span><span class="p">,</span> <span class="s1">'nemotron'</span>
|
|
<span class="p">]</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Gpt variant: </span><span class="si">{</span><span class="n">gpt_variant</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
|
|
|
<span class="k">if</span> <span class="n">gpt_variant</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'starcoder2'</span><span class="p">,</span> <span class="s1">'nemotron'</span><span class="p">,</span> <span class="s1">'persimmon'</span><span class="p">]:</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_embd</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">hidden_size</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_inner</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">intermediate_size</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_head</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">num_attention_heads</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_kv_head</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">num_key_value_heads</span> <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span>
|
|
<span class="n">hf_config</span><span class="p">,</span> <span class="s1">'num_key_value_heads'</span><span class="p">)</span> <span class="k">else</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">n_head</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_layer</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">num_hidden_layers</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_positions</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">max_position_embeddings</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">activation_function</span> <span class="o">=</span> <span class="s1">'gelu'</span> <span class="k">if</span> <span class="n">gpt_variant</span> <span class="o">==</span> <span class="s1">'starcoder2'</span> <span class="k">else</span> <span class="s1">'squared-relu'</span>
|
|
<span class="k">if</span> <span class="n">gpt_variant</span> <span class="o">==</span> <span class="s2">"nemotron"</span><span class="p">:</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">layer_norm_eps</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">norm_eps</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">layer_norm_epsilon</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">norm_epsilon</span> <span class="k">if</span> <span class="n">gpt_variant</span> <span class="o">==</span> <span class="s1">'starcoder2'</span> <span class="k">else</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">layer_norm_eps</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">use_bias</span> <span class="k">if</span> <span class="n">gpt_variant</span> <span class="o">==</span> <span class="s1">'starcoder2'</span> <span class="k">else</span> <span class="n">gpt_variant</span> <span class="o">!=</span> <span class="s1">'nemotron'</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">position_embedding_type</span> <span class="o">=</span> <span class="s1">'rope_gpt_neox'</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">rotary_base</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">rope_theta</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">rotary_pct</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span>
|
|
<span class="n">hf_config</span><span class="p">,</span> <span class="s1">'partial_rotary_factor'</span><span class="p">,</span>
|
|
<span class="nb">getattr</span><span class="p">(</span><span class="n">hf_config</span><span class="p">,</span> <span class="s1">'rope_percent'</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">))</span>
|
|
<span class="k">try</span><span class="p">:</span>
|
|
<span class="c1"># only for persimmon, not starcoder2</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">vocab_size</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">text_config</span><span class="o">.</span><span class="n">vocab_size</span>
|
|
<span class="k">except</span> <span class="ne">AttributeError</span><span class="p">:</span>
|
|
<span class="k">pass</span>
|
|
<span class="k">elif</span> <span class="n">gpt_variant</span> <span class="o">==</span> <span class="s2">"kosmos-2"</span><span class="p">:</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_embd</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">text_config</span><span class="o">.</span><span class="n">embed_dim</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_inner</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">text_config</span><span class="o">.</span><span class="n">ffn_dim</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_head</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">text_config</span><span class="o">.</span><span class="n">attention_heads</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_kv_head</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">n_head</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_layer</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">text_config</span><span class="o">.</span><span class="n">layers</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_positions</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">text_config</span><span class="o">.</span><span class="n">max_position_embeddings</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">activation_function</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">text_config</span><span class="o">.</span><span class="n">activation_function</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">layer_norm_epsilon</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">text_config</span><span class="o">.</span><span class="n">layer_norm_eps</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">vocab_size</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">text_config</span><span class="o">.</span><span class="n">vocab_size</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="k">if</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">n_inner</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_inner</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">n_embd</span> <span class="o">*</span> <span class="mi">4</span>
|
|
<span class="k">if</span> <span class="n">gpt_variant</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'santacoder'</span><span class="p">,</span> <span class="s1">'starcoder'</span><span class="p">]:</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_kv_head</span> <span class="o">=</span> <span class="mi">1</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_kv_head</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">n_head</span>
|
|
|
|
<span class="k">if</span> <span class="n">gpt_variant</span> <span class="o">==</span> <span class="s1">'jais'</span><span class="p">:</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">q_scaling</span> <span class="o">=</span> <span class="p">(</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_embd</span> <span class="o">//</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">n_head</span><span class="p">)</span><span class="o">**</span><span class="mf">0.5</span>
|
|
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">hf_config</span><span class="p">,</span> <span class="s1">'width_scale'</span><span class="p">):</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">logits_scale</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">width_scale</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">logits_scale</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">mup_output_alpha</span> <span class="o">*</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">mup_width_scale</span>
|
|
|
|
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">hf_config</span><span class="p">,</span> <span class="s1">'mup_embeddings_scale'</span><span class="p">):</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">embeddings_scale</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">mup_embeddings_scale</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="k">assert</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">hf_config</span><span class="p">,</span> <span class="s1">'embeddings_scale'</span><span class="p">)</span>
|
|
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_inner</span> <span class="o">+=</span> <span class="n">get_needed_padding</span><span class="p">(</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_inner</span><span class="p">,</span>
|
|
<span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">)</span>
|
|
|
|
<span class="k">if</span> <span class="n">gpt_variant</span> <span class="o">==</span> <span class="s1">'kosmos-2'</span><span class="p">:</span>
|
|
<span class="k">if</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">text_config</span><span class="o">.</span><span class="n">scale_embedding</span><span class="p">:</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">embeddings_scale</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">n_embd</span><span class="o">**</span><span class="mf">0.5</span>
|
|
|
|
<span class="n">dtype</span> <span class="o">=</span> <span class="n">infer_dtype</span><span class="p">(</span><span class="n">dtype</span><span class="p">,</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">hf_config</span><span class="p">,</span> <span class="s1">'torch_dtype'</span><span class="p">,</span> <span class="kc">None</span><span class="p">))</span>
|
|
|
|
<span class="k">return</span> <span class="bp">cls</span><span class="p">(</span><span class="n">architecture</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">architectures</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
|
|
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
|
|
<span class="n">num_hidden_layers</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_layer</span><span class="p">,</span>
|
|
<span class="n">num_attention_heads</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_head</span><span class="p">,</span>
|
|
<span class="n">num_key_value_heads</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_kv_head</span><span class="p">,</span>
|
|
<span class="n">hidden_size</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_embd</span><span class="p">,</span>
|
|
<span class="n">intermediate_size</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_inner</span><span class="p">,</span>
|
|
<span class="n">norm_epsilon</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">layer_norm_epsilon</span><span class="p">,</span>
|
|
<span class="n">vocab_size</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">,</span>
|
|
<span class="n">position_embedding_type</span><span class="o">=</span><span class="nb">getattr</span><span class="p">(</span><span class="n">hf_config</span><span class="p">,</span>
|
|
<span class="s1">'position_embedding_type'</span><span class="p">,</span>
|
|
<span class="s1">'learned_absolute'</span><span class="p">),</span>
|
|
<span class="n">max_position_embeddings</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_positions</span><span class="p">,</span>
|
|
<span class="n">hidden_act</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">activation_function</span><span class="p">,</span>
|
|
<span class="n">gpt_variant</span><span class="o">=</span><span class="n">gpt_variant</span><span class="p">,</span>
|
|
<span class="n">bias</span><span class="o">=</span><span class="nb">getattr</span><span class="p">(</span><span class="n">hf_config</span><span class="p">,</span> <span class="s1">'bias'</span><span class="p">,</span> <span class="kc">True</span><span class="p">),</span>
|
|
<span class="n">apply_query_key_layer_scaling</span><span class="o">=</span><span class="nb">getattr</span><span class="p">(</span>
|
|
<span class="n">hf_config</span><span class="p">,</span> <span class="s1">'apply_query_key_layer_scaling'</span><span class="p">,</span> <span class="kc">False</span><span class="p">),</span>
|
|
<span class="n">rotary_pct</span><span class="o">=</span><span class="nb">getattr</span><span class="p">(</span><span class="n">hf_config</span><span class="p">,</span> <span class="s1">'rotary_pct'</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span>
|
|
<span class="n">rotary_base</span><span class="o">=</span><span class="nb">getattr</span><span class="p">(</span><span class="n">hf_config</span><span class="p">,</span> <span class="s1">'rotary_base'</span><span class="p">,</span> <span class="mf">10000.0</span><span class="p">),</span>
|
|
<span class="n">rotary_scaling</span><span class="o">=</span><span class="nb">getattr</span><span class="p">(</span><span class="n">hf_config</span><span class="p">,</span> <span class="s1">'rotary_scaling'</span><span class="p">,</span> <span class="kc">None</span><span class="p">),</span>
|
|
<span class="n">qk_layernorm</span><span class="o">=</span><span class="n">gpt_variant</span> <span class="o">==</span> <span class="s1">'persimmon'</span><span class="p">,</span>
|
|
<span class="n">inner_layernorm</span><span class="o">=</span><span class="n">gpt_variant</span> <span class="o">==</span> <span class="s1">'kosmos-2'</span><span class="p">,</span>
|
|
<span class="n">norm_before_bmm1</span><span class="o">=</span><span class="n">gpt_variant</span> <span class="o">==</span> <span class="s1">'kosmos-2'</span><span class="p">,</span>
|
|
<span class="n">q_scaling</span><span class="o">=</span><span class="nb">getattr</span><span class="p">(</span><span class="n">hf_config</span><span class="p">,</span> <span class="s1">'q_scaling'</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span>
|
|
<span class="n">embedding_scale</span><span class="o">=</span><span class="nb">getattr</span><span class="p">(</span><span class="n">hf_config</span><span class="p">,</span> <span class="s1">'embeddings_scale'</span><span class="p">,</span> <span class="kc">None</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">quantization</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></div>
|
|
|
|
|
|
<div class="viewcode-block" id="GPTConfig.from_nemo">
|
|
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.GPTConfig.from_nemo">[docs]</a>
|
|
<span class="nd">@classmethod</span>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">from_nemo</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span>
|
|
<span class="n">nemo_ckpt_dir</span><span class="p">:</span> <span class="nb">str</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">'auto'</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="kn">import</span><span class="w"> </span><span class="nn">transformers</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">UnpackedNemoCheckpointDir</span><span class="p">,</span> <span class="n">cpu_map_location</span><span class="p">,</span>
|
|
<span class="n">gpu_map_location</span><span class="p">,</span> <span class="n">rename_keys</span><span class="p">)</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">'load_model_on_cpu'</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>
|
|
<span class="n">nemo_rename_key</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">'nemo_rename_key'</span><span class="p">,</span> <span class="p">[])</span>
|
|
<span class="n">layer_rename_config</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="n">pattern</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">':'</span><span class="p">)[</span><span class="mi">0</span><span class="p">]:</span> <span class="n">pattern</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">':'</span><span class="p">)[</span><span class="mi">1</span><span class="p">]</span>
|
|
<span class="k">for</span> <span class="n">pattern</span> <span class="ow">in</span> <span class="n">nemo_rename_key</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="n">unpacked_checkpoints_dir</span> <span class="o">=</span> <span class="n">UnpackedNemoCheckpointDir</span><span class="p">(</span>
|
|
<span class="n">nemo_ckpt_dir</span><span class="p">,</span> <span class="n">load_checkpoints_to_cpu</span><span class="o">=</span><span class="n">load_model_on_cpu</span><span class="p">)</span>
|
|
<span class="n">nemo_model_config</span> <span class="o">=</span> <span class="n">unpacked_checkpoints_dir</span><span class="o">.</span><span class="n">model_config</span>
|
|
|
|
<span class="n">training_tp_size</span> <span class="o">=</span> <span class="n">nemo_model_config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"tensor_model_parallel_size"</span><span class="p">,</span>
|
|
<span class="mi">1</span><span class="p">)</span>
|
|
<span class="n">training_pp_size</span> <span class="o">=</span> <span class="n">nemo_model_config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"pipeline_model_parallel_size"</span><span class="p">,</span>
|
|
<span class="mi">1</span><span class="p">)</span>
|
|
|
|
<span class="n">checkpoints_paths</span> <span class="o">=</span> <span class="n">unpacked_checkpoints_dir</span><span class="o">.</span><span class="n">get_checkpoints_paths</span><span class="p">(</span>
|
|
<span class="n">training_tp_size</span><span class="p">,</span>
|
|
<span class="n">training_pp_size</span><span class="p">,</span>
|
|
<span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">unpacked_checkpoints_dir</span><span class="o">.</span><span class="n">_load_checkpoints_to_cpu</span><span class="p">:</span>
|
|
<span class="n">map_location_fn</span> <span class="o">=</span> <span class="n">cpu_map_location</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">map_location_fn</span> <span class="o">=</span> <span class="n">gpu_map_location</span>
|
|
<span class="n">model_00</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">checkpoints_paths</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">map_location</span><span class="o">=</span><span class="n">map_location_fn</span><span class="p">)</span>
|
|
<span class="n">model_00</span> <span class="o">=</span> <span class="n">rename_keys</span><span class="p">(</span><span class="n">model_00</span><span class="p">,</span> <span class="n">layer_rename_config</span><span class="p">)</span>
|
|
<span class="n">vocab_size</span> <span class="o">=</span> <span class="n">model_00</span><span class="p">[</span>
|
|
<span class="s2">"model.language_model.embedding.word_embeddings.weight"</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span>
|
|
<span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="n">training_tp_size</span>
|
|
<span class="k">del</span> <span class="n">model_00</span>
|
|
|
|
<span class="n">hf_config</span> <span class="o">=</span> <span class="n">transformers</span><span class="o">.</span><span class="n">GPT2Config</span><span class="p">(</span>
|
|
<span class="n">vocab_size</span><span class="o">=</span><span class="n">vocab_size</span><span class="p">,</span>
|
|
<span class="n">n_positions</span><span class="o">=</span><span class="n">nemo_model_config</span><span class="p">[</span><span class="s1">'max_position_embeddings'</span><span class="p">],</span>
|
|
<span class="n">n_embd</span><span class="o">=</span><span class="n">nemo_model_config</span><span class="p">[</span><span class="s1">'hidden_size'</span><span class="p">],</span>
|
|
<span class="n">n_layer</span><span class="o">=</span><span class="n">nemo_model_config</span><span class="p">[</span><span class="s1">'num_layers'</span><span class="p">],</span>
|
|
<span class="n">n_head</span><span class="o">=</span><span class="n">nemo_model_config</span><span class="p">[</span><span class="s1">'num_attention_heads'</span><span class="p">],</span>
|
|
<span class="n">n_inner</span><span class="o">=</span><span class="n">nemo_model_config</span><span class="p">[</span><span class="s1">'ffn_hidden_size'</span><span class="p">],</span>
|
|
<span class="n">activation_function</span><span class="o">=</span><span class="n">nemo_model_config</span><span class="p">[</span><span class="s1">'activation'</span><span class="p">],</span>
|
|
<span class="n">layer_norm_epsilon</span><span class="o">=</span><span class="n">nemo_model_config</span><span class="p">[</span><span class="s1">'layernorm_epsilon'</span><span class="p">],</span>
|
|
<span class="p">)</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">n_kv_head</span> <span class="o">=</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">n_head</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="n">nemo_model_config</span><span class="p">[</span><span class="s1">'bias'</span><span class="p">]</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">apply_query_key_layer_scaling</span> <span class="o">=</span> <span class="kc">False</span>
|
|
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">position_embedding_type</span> <span class="o">=</span> <span class="n">nemo_model_config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span>
|
|
<span class="s1">'position_embedding_type'</span><span class="p">,</span> <span class="s1">'learned_absolute'</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">position_embedding_type</span> <span class="o">==</span> <span class="s1">'rope'</span><span class="p">:</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">position_embedding_type</span> <span class="o">=</span> <span class="s1">'rope_gpt_neox'</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">rotary_base</span> <span class="o">=</span> <span class="n">nemo_model_config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'rotary_base'</span><span class="p">,</span> <span class="mf">10000.0</span><span class="p">)</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">rotary_pct</span> <span class="o">=</span> <span class="n">nemo_model_config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'rotary_percentage'</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">)</span>
|
|
<span class="k">assert</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">rotary_pct</span> <span class="o">>=</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">hf_config</span><span class="o">.</span><span class="n">rotary_pct</span> <span class="o"><=</span> <span class="mi">1</span>
|
|
|
|
<span class="n">rotary_scaling_factor</span> <span class="o">=</span> <span class="n">nemo_model_config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span>
|
|
<span class="s1">'seq_len_interpolation_factor'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">rotary_scaling_factor</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">rotary_scaling</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="k">assert</span> <span class="n">rotary_scaling_factor</span> <span class="o">></span> <span class="mi">1</span>
|
|
<span class="n">hf_config</span><span class="o">.</span><span class="n">rotary_scaling</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s1">'type'</span><span class="p">:</span> <span class="s1">'linear'</span><span class="p">,</span>
|
|
<span class="s1">'factor'</span><span class="p">:</span> <span class="n">rotary_scaling_factor</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="k">if</span> <span class="n">dtype</span> <span class="o">==</span> <span class="s1">'auto'</span><span class="p">:</span>
|
|
<span class="n">dtype</span> <span class="o">=</span> <span class="n">nemo_model_config</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'precision'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">dtype</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">dtype</span> <span class="o">=</span> <span class="s1">'float16'</span>
|
|
<span class="k">elif</span> <span class="s1">'bf16'</span> <span class="ow">in</span> <span class="n">dtype</span> <span class="ow">or</span> <span class="s1">'bfloat16'</span> <span class="ow">in</span> <span class="n">dtype</span><span class="p">:</span>
|
|
<span class="n">dtype</span> <span class="o">=</span> <span class="s1">'bfloat16'</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">dtype</span> <span class="o">=</span> <span class="s1">'float16'</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Specified dtype 'auto'; inferred dtype </span><span class="si">{</span><span class="n">dtype</span><span class="si">!r}</span><span class="s2">."</span><span class="p">)</span>
|
|
|
|
<span class="k">return</span> <span class="bp">cls</span><span class="p">(</span><span class="n">architecture</span><span class="o">=</span><span class="s1">'GPTForCausalLM'</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">num_hidden_layers</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_layer</span><span class="p">,</span>
|
|
<span class="n">num_attention_heads</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_head</span><span class="p">,</span>
|
|
<span class="n">num_key_value_heads</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_kv_head</span><span class="p">,</span>
|
|
<span class="n">hidden_size</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_embd</span><span class="p">,</span>
|
|
<span class="n">intermediate_size</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_inner</span><span class="p">,</span>
|
|
<span class="n">norm_epsilon</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">layer_norm_epsilon</span><span class="p">,</span>
|
|
<span class="n">vocab_size</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">,</span>
|
|
<span class="n">position_embedding_type</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">position_embedding_type</span><span class="p">,</span>
|
|
<span class="n">max_position_embeddings</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">n_positions</span><span class="p">,</span>
|
|
<span class="n">hidden_act</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">activation_function</span><span class="p">,</span>
|
|
<span class="n">bias</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">bias</span><span class="p">,</span>
|
|
<span class="n">apply_query_key_layer_scaling</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span>
|
|
<span class="n">apply_query_key_layer_scaling</span><span class="p">,</span>
|
|
<span class="n">rotary_pct</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">rotary_pct</span><span class="p">,</span>
|
|
<span class="n">rotary_base</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">rotary_base</span><span class="p">,</span>
|
|
<span class="n">rotary_scaling</span><span class="o">=</span><span class="n">hf_config</span><span class="o">.</span><span class="n">rotary_scaling</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">quantization</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></div>
|
|
</div>
|
|
|
|
</pre></div>
|
|
|
|
</article>
|
|
|
|
|
|
|
|
|
|
|
|
<footer class="prev-next-footer d-print-none">
|
|
|
|
<div class="prev-next-area">
|
|
</div>
|
|
</footer>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<div class="bd-sidebar-secondary"></div>
|
|
|
|
|
|
|
|
|
|
|
|
</div>
|
|
<footer class="bd-footer-content">
|
|
|
|
</footer>
|
|
|
|
</main>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Scripts loaded after <body> so the DOM is not blocked -->
|
|
<script defer src="../../../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf"></script>
|
|
<script defer src="../../../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf"></script>
|
|
|
|
<footer class="bd-footer">
|
|
<div class="bd-footer__inner bd-page-width">
|
|
|
|
<div class="footer-items__start">
|
|
|
|
<div class="footer-item">
|
|
<a class="footer-brand logo" href="https://www.nvidia.com">
|
|
<img src="../../../../_static/nvidia-logo-horiz-rgb-1c-blk-for-screen.svg" class="logo__image only-light" alt="NVIDIA"/>
|
|
<img src="../../../../_static/nvidia-logo-horiz-rgb-1c-wht-for-screen.svg" class="logo__image only-dark" alt="NVIDIA"/>
|
|
</a></div>
|
|
|
|
<div class="footer-item">
|
|
|
|
<div class="footer-links">
|
|
|
|
|
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/">Privacy Policy</a>
|
|
|
|
|
|
|
|
|
|
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-center/">Manage My Privacy</a>
|
|
|
|
|
|
|
|
|
|
|
<a class="external" href="https://www.nvidia.com/en-us/preferences/start/">Do Not Sell or Share My Data</a>
|
|
|
|
|
|
|
|
|
|
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/terms-of-service/">Terms of Service</a>
|
|
|
|
|
|
|
|
|
|
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/accessibility/">Accessibility</a>
|
|
|
|
|
|
|
|
|
|
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/company-policies/">Corporate Policies</a>
|
|
|
|
|
|
|
|
|
|
|
<a class="external" href="https://www.nvidia.com/en-us/product-security/">Product Security</a>
|
|
|
|
|
|
|
|
|
|
|
<a class="external" href="https://www.nvidia.com/en-us/contact/">Contact</a>
|
|
|
|
|
|
|
|
</div>
|
|
</div>
|
|
|
|
<div class="footer-item">
|
|
|
|
|
|
|
|
|
|
<p class="copyright">
|
|
|
|
Copyright © 2025, NVidia.
|
|
<br/>
|
|
|
|
</p>
|
|
</div>
|
|
|
|
<div class="footer-item">
|
|
<div class="extra_footer">
|
|
|
|
<p>Last updated on June 03, 2025.</p>
|
|
|
|
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/9ae2ce6">9ae2ce6</a>.</p>
|
|
|
|
</div></div>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
</div>
|
|
|
|
</footer>
|
|
</body>
|
|
</html> |