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
7fcecdb5ed
TensorRT-LLMs/_modules/tensorrt_llm/models/llama/model.html
Kaiyu Xie 7fcecdb5ed Update GitHub pages in root to v1.1.0rc0
2025-08-15 14:08:05 +00:00

1274 lines
130 KiB
HTML
Raw Blame History

<!DOCTYPE html>
<html lang="en" data-content_root="../../../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>tensorrt_llm.models.llama.model &#8212; TensorRT-LLM</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!--
this give us a css class that will be invisible only if js is disabled
-->
<noscript>
<style>
.pst-js-only { display: none !important; }
</style>
</noscript>
<!-- Loaded before other Sphinx assets -->
<link href="../../../../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link href="../../../../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="../../../../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../../../../_static/styles/nvidia-sphinx-theme.css?v=df3ac72c" />
<link rel="stylesheet" type="text/css" href="../../../../_static/copybutton.css?v=76b2166b" />
<link rel="stylesheet" type="text/css" href="../../../../_static/autodoc_pydantic.css" />
<link rel="stylesheet" type="text/css" href="../../../../_static/togglebutton.css?v=13237357" />
<link rel="stylesheet" type="text/css" href="../../../../_static/custom.css?v=95073da6" />
<!-- 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/llama/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 = '1.1.0rc0';
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="1.1.0rc0" />
</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/containers.html">Pre-built release container images on NGC</a></li>
<li class="toctree-l1"><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-l1"><a class="reference internal" href="../../../../installation/build-from-source-linux.html">Building from Source Code on Linux</a></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"><a class="reference internal" href="../../../../deployment-guide/quick-start-recipe-for-llama4-scout-on-trtllm.html">Quick Start Recipe for Llama4 Scout 17B on TensorRT-LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../deployment-guide/quick-start-recipe-for-deepseek-r1-on-trtllm.html">Quick Start Recipe for DeepSeek R1 on TensorRT-LLM - Blackwell &amp; Hopper Hardware</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../deployment-guide/quick-start-recipe-for-llama3.3-70b-on-trtllm.html">Quick Start Recipe for Llama3.3 70B on TensorRT-LLM - Blackwell &amp; Hopper Hardware</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">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">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 class="simple">
</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_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_speculative_decoding.html">Speculative Decoding</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>
</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-bench.html">trtllm-bench</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../commands/trtllm-build.html">trtllm-build</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">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 (Prototype)</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>
<li class="toctree-l1"><a class="reference internal" href="../../../../reference/ci-overview.html">Continuous Integration Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../reference/dev-containers.html">Using Dev Containers</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.llama.model</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<h1>Source code for tensorrt_llm.models.llama.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">import</span><span class="w"> </span><span class="nn">os</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">transformers</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">..._utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">pad_vocab_size</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">AllReduceFusionOp</span><span class="p">,</span> <span class="n">AllReduceParams</span><span class="p">,</span> <span class="n">Tensor</span><span class="p">,</span>
<span class="n">allgather</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">div</span><span class="p">,</span> <span class="n">non_gated_version</span><span class="p">,</span>
<span class="n">recv</span><span class="p">,</span> <span class="n">send</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="p">(</span><span class="n">MOE</span><span class="p">,</span> <span class="n">Attention</span><span class="p">,</span> <span class="n">AttentionMaskType</span><span class="p">,</span> <span class="n">ColumnLinear</span><span class="p">,</span>
<span class="n">Embedding</span><span class="p">,</span> <span class="n">FusedGatedMLP</span><span class="p">,</span> <span class="n">GatedMLP</span><span class="p">,</span>
<span class="n">PositionEmbeddingType</span><span class="p">,</span> <span class="n">RmsNorm</span><span class="p">)</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">...lora_helper</span><span class="w"> </span><span class="kn">import</span> <span class="n">LoraConfig</span><span class="p">,</span> <span class="n">use_lora</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">...mapping</span><span class="w"> </span><span class="kn">import</span> <span class="n">Mapping</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">...module</span><span class="w"> </span><span class="kn">import</span> <span class="n">Module</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">...quantization.functional</span><span class="w"> </span><span class="kn">import</span> <span class="n">fused_layernorm</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">has_safetensors</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">..model_weights_loader</span><span class="w"> </span><span class="kn">import</span> <span class="n">ModelWeightsLoader</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="p">(</span><span class="n">DecoderLayerList</span><span class="p">,</span> <span class="n">DecoderModelForCausalLM</span><span class="p">,</span>
<span class="n">QuantConfig</span><span class="p">)</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">LLaMAConfig</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_llama</span><span class="p">,</span> <span class="n">load_weights_from_deepcompressor</span><span class="p">,</span>
<span class="n">load_weights_from_gptq</span><span class="p">,</span> <span class="n">load_weights_from_hf_by_shard</span><span class="p">,</span>
<span class="n">load_weights_from_hf_model</span><span class="p">,</span>
<span class="n">load_weights_from_hf_safetensors</span><span class="p">,</span>
<span class="n">load_weights_from_meta_ckpt</span><span class="p">)</span>
<span class="k">class</span><span class="w"> </span><span class="nc">LLaMADecoderLayer</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">config</span><span class="p">:</span> <span class="n">LLaMAConfig</span><span class="p">,</span> <span class="n">layer_idx</span><span class="p">:</span> <span class="nb">int</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">layer_idx</span> <span class="o">=</span> <span class="n">layer_idx</span>
<span class="n">layer_idx</span> <span class="o">+=</span> <span class="n">config</span><span class="o">.</span><span class="n">layer_idx_offset</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">mapping</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">mapping</span>
<span class="k">if</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">use_input_layernorm_in_first_layer</span>
<span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_idx</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_idx</span> <span class="o">&gt;</span> <span class="mi">0</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">RmsNorm</span><span class="p">(</span><span class="n">normalized_shape</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">eps</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">norm_epsilon</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="n">layers_range</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">pp_layers</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="bp">self</span><span class="o">.</span><span class="n">local_layer_idx</span> <span class="o">=</span> <span class="n">layer_idx</span> <span class="o">-</span> <span class="n">layers_range</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">is_last_local_layer</span> <span class="o">=</span> <span class="n">layer_idx</span> <span class="o">==</span> <span class="n">layers_range</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">attention</span> <span class="o">=</span> <span class="n">Attention</span><span class="p">(</span>
<span class="n">local_layer_idx</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">local_layer_idx</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">attention_head_size</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">head_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">num_kv_heads</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">num_key_value_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">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="n">attention_mask_type</span><span class="o">=</span><span class="n">AttentionMaskType</span><span class="o">.</span><span class="n">causal</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">attn_bias</span><span class="p">,</span>
<span class="n">position_embedding_type</span><span class="o">=</span><span class="n">PositionEmbeddingType</span><span class="o">.</span><span class="n">rope_gpt_neox</span><span class="p">,</span>
<span class="n">rotary_embedding_base</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">rotary_base</span><span class="p">,</span>
<span class="n">rotary_embedding_scaling</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">rotary_scaling</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">tp_rank</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_rank</span><span class="p">,</span>
<span class="n">q_scaling</span><span class="o">=</span><span class="mf">1.0</span> <span class="o">/</span> <span class="n">config</span><span class="o">.</span><span class="n">attention_multiplier</span><span class="p">,</span>
<span class="n">quant_mode</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">quant_mode</span><span class="p">,</span>
<span class="n">cp_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">cp_group</span><span class="p">,</span>
<span class="n">cp_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">cp_size</span><span class="p">,</span>
<span class="n">cp_rank</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">cp_rank</span><span class="p">)</span>
<span class="n">mlp_hidden_size</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span> <span class="o">*</span> <span class="mi">4</span> <span class="k">if</span> <span class="n">config</span><span class="o">.</span><span class="n">intermediate_size</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">config</span><span class="o">.</span><span class="n">intermediate_size</span>
<span class="n">ClsMLP</span> <span class="o">=</span> <span class="n">GatedMLP</span>
<span class="n">mlp_kwargs</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">if</span> <span class="n">config</span><span class="o">.</span><span class="n">moe</span><span class="o">.</span><span class="n">has_moe</span><span class="p">():</span>
<span class="n">ClsMLP</span> <span class="o">=</span> <span class="n">MOE</span>
<span class="n">mlp_kwargs</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;moe_config&quot;</span><span class="p">:</span> <span class="n">config</span><span class="o">.</span><span class="n">moe</span><span class="p">,</span>
<span class="s2">&quot;mapping&quot;</span><span class="p">:</span> <span class="n">config</span><span class="o">.</span><span class="n">mapping</span><span class="p">,</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">ClsMLP</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">ffn_hidden_size</span><span class="o">=</span><span class="n">mlp_hidden_size</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">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="n">bias</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">mlp_bias</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">quant_mode</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">quant_mode</span><span class="p">,</span>
<span class="o">**</span><span class="n">mlp_kwargs</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">RmsNorm</span><span class="p">(</span><span class="n">normalized_shape</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">eps</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">norm_epsilon</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="c1"># Residual MLP that applies on pre-attention input</span>
<span class="c1"># TODO: change to self.has_residual_mlp = self.config.residual_mlp after ModelOpt quantize config is updated</span>
<span class="bp">self</span><span class="o">.</span><span class="n">has_residual_mlp</span> <span class="o">=</span> <span class="kc">False</span>
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="p">,</span>
<span class="s2">&quot;residual_mlp&quot;</span><span class="p">)</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">residual_mlp</span> <span class="ow">is</span> <span class="kc">True</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">has_residual_mlp</span> <span class="o">=</span> <span class="kc">True</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">has_residual_mlp</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">residual_layernorm</span> <span class="o">=</span> <span class="n">RmsNorm</span><span class="p">(</span>
<span class="n">normalized_shape</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">eps</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">norm_epsilon</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="n">ClsMLP</span> <span class="o">=</span> <span class="n">GatedMLP</span> <span class="c1"># TODO: may use FusedGatedMLP to further speedup</span>
<span class="bp">self</span><span class="o">.</span><span class="n">residual_mlp</span> <span class="o">=</span> <span class="n">ClsMLP</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">ffn_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="c1"># residual mlp uses hidden_size</span>
<span class="n">hidden_act</span><span class="o">=</span><span class="n">non_gated_version</span><span class="p">(</span>
<span class="n">config</span><span class="o">.</span><span class="n">hidden_act</span><span class="p">),</span> <span class="c1"># back to non-gated</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="n">bias</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">mlp_bias</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">quant_mode</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">quant_mode</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">use_cache</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">spec_decoding_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">kv_cache_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">attention_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">lora_layer_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">next_layer_input_layernorm_args</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="k">assert</span> <span class="ow">not</span> <span class="p">(</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">reduce_fusion</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">has_residual_mlp</span>
<span class="p">),</span> <span class="s2">&quot;Custom all reduce and residual mlp can&#39;t be enabled at the same time.&quot;</span>
<span class="k">assert</span> <span class="ow">not</span> <span class="p">(</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">reduce_fusion</span>
<span class="ow">and</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">user_buffer</span>
<span class="ow">and</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">pp_reduce_scatter</span>
<span class="p">),</span> <span class="s2">&quot;User buffer reduce fusion enabled with PP reduce scatter is not supported now.&quot;</span>
<span class="k">assert</span> <span class="ow">not</span> <span class="p">(</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">reduce_fusion</span>
<span class="ow">and</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">norm_quant_fusion</span>
<span class="p">),</span> <span class="s2">&quot;Reduce fusion and quant fusion can&#39;t be enabled at the same time.&quot;</span>
<span class="k">if</span> <span class="n">default_net</span><span class="p">(</span>
<span class="p">)</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">reduce_fusion</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">local_layer_idx</span> <span class="o">&gt;</span> <span class="mi">0</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="k">elif</span> <span class="n">default_net</span><span class="p">(</span>
<span class="p">)</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">norm_quant_fusion</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">local_layer_idx</span> <span class="o">&gt;</span> <span class="mi">0</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="k">else</span><span class="p">:</span>
<span class="n">residual</span> <span class="o">=</span> <span class="n">hidden_states</span>
<span class="k">if</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">use_input_layernorm_in_first_layer</span>
<span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_idx</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_idx</span> <span class="o">&gt;</span> <span class="mi">0</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">input_layernorm</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">reduce_fusion_op</span> <span class="o">=</span> <span class="n">AllReduceFusionOp</span><span class="o">.</span><span class="n">NONE</span>
<span class="k">if</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">reduce_fusion</span><span class="p">:</span>
<span class="k">if</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">user_buffer</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">quant_mode</span><span class="o">.</span><span class="n">has_fp8_qdq</span><span class="p">():</span>
<span class="n">reduce_fusion_op</span> <span class="o">=</span> <span class="n">AllReduceFusionOp</span><span class="o">.</span><span class="n">RESIDUAL_RMS_NORM_QUANT_FP8</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">quant_mode</span><span class="o">.</span><span class="n">has_nvfp4</span><span class="p">():</span>
<span class="k">assert</span> <span class="n">default_net</span><span class="p">(</span>
<span class="p">)</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">gemm_plugin</span> <span class="o">==</span> <span class="s2">&quot;nvfp4&quot;</span><span class="p">,</span> <span class="s2">&quot;UB with nvfp4 model must use nvfp4 gemm plugin&quot;</span>
<span class="n">reduce_fusion_op</span> <span class="o">=</span> <span class="n">AllReduceFusionOp</span><span class="o">.</span><span class="n">RESIDUAL_RMS_NORM_QUANT_NVFP4</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="s2">&quot;UB must enabled with fp8 or nvfp4 model&quot;</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">reduce_fusion_op</span> <span class="o">=</span> <span class="n">AllReduceFusionOp</span><span class="o">.</span><span class="n">RESIDUAL_RMS_NORM</span>
<span class="n">reduce_fusion_scale</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</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">reduce_fusion</span> <span class="ow">and</span> <span class="n">default_net</span><span class="p">(</span>
<span class="p">)</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">user_buffer</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">mlp</span><span class="p">,</span> <span class="n">FusedGatedMLP</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">quant_mode</span><span class="o">.</span><span class="n">has_fp8_qdq</span><span class="p">():</span>
<span class="n">reduce_fusion_scale</span> <span class="o">=</span> <span class="n">constant</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">fused_fc</span><span class="o">.</span><span class="n">activation_scaling_factor</span><span class="o">.</span><span class="n">raw_value</span><span class="o">.</span>
<span class="n">copy</span><span class="p">())</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">quant_mode</span><span class="o">.</span><span class="n">has_nvfp4</span><span class="p">():</span>
<span class="n">reduce_fusion_scale</span> <span class="o">=</span> <span class="n">constant</span><span class="p">(</span>
<span class="p">[</span><span class="mf">1.0</span><span class="p">]</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">mlp</span><span class="o">.</span><span class="n">fused_fc</span><span class="o">.</span>
<span class="n">activation_global_scaling_factor</span><span class="o">.</span><span class="n">raw_value</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">quant_mode</span><span class="o">.</span><span class="n">has_fp8_qdq</span><span class="p">():</span>
<span class="n">reduce_fusion_scale</span> <span class="o">=</span> <span class="n">constant</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">fc</span><span class="o">.</span><span class="n">activation_scaling_factor</span><span class="o">.</span><span class="n">raw_value</span><span class="o">.</span><span class="n">copy</span><span class="p">())</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">quant_mode</span><span class="o">.</span><span class="n">has_nvfp4</span><span class="p">():</span>
<span class="n">reduce_fusion_scale</span> <span class="o">=</span> <span class="n">constant</span><span class="p">(</span>
<span class="p">[</span><span class="mf">1.0</span><span class="p">]</span> <span class="o">/</span>
<span class="bp">self</span><span class="o">.</span><span class="n">mlp</span><span class="o">.</span><span class="n">fc</span><span class="o">.</span><span class="n">activation_global_scaling_factor</span><span class="o">.</span><span class="n">raw_value</span><span class="p">)</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">use_cache</span><span class="o">=</span><span class="n">use_cache</span><span class="p">,</span>
<span class="n">spec_decoding_params</span><span class="o">=</span><span class="n">spec_decoding_params</span><span class="p">,</span>
<span class="n">kv_cache_params</span><span class="o">=</span><span class="n">kv_cache_params</span><span class="p">,</span>
<span class="n">attention_params</span><span class="o">=</span><span class="n">attention_params</span><span class="p">,</span>
<span class="n">lora_layer_params</span><span class="o">=</span><span class="n">lora_layer_params</span><span class="p">,</span>
<span class="n">all_reduce_params</span><span class="o">=</span><span class="n">AllReduceParams</span><span class="p">(</span>
<span class="n">fusion_op</span><span class="o">=</span><span class="n">reduce_fusion_op</span><span class="p">,</span>
<span class="n">residual</span><span class="o">=</span><span class="n">residual</span><span class="p">,</span>
<span class="n">norm_weight</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">post_layernorm</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">value</span><span class="p">,</span>
<span class="n">scale</span><span class="o">=</span><span class="n">reduce_fusion_scale</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">post_layernorm</span><span class="o">.</span><span class="n">eps</span><span class="p">))</span>
<span class="k">if</span> <span class="n">use_cache</span><span class="p">:</span>
<span class="n">attention_output</span><span class="p">,</span> <span class="n">presents</span> <span class="o">=</span> <span class="n">attention_output</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">has_residual_mlp</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">residual_attn</span> <span class="o">=</span> <span class="n">hidden_states</span>
<span class="c1"># arctic layer w/ residual mlp</span>
<span class="c1"># residual mlp</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">residual_layernorm</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">residual_mlp</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">residual_mlp</span> <span class="o">=</span> <span class="n">residual_attn</span> <span class="o">+</span> <span class="n">hidden_states</span>
<span class="c1"># parallel moe</span>
<span class="c1"># parallel moe layers applies on PRE-ATTENTION input residual, therefore achieving pre-fetching and better parallelism</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">residual</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">mlp</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="n">lora_layer_params</span><span class="o">=</span><span class="n">lora_layer_params</span><span class="p">)</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">residual_mlp</span> <span class="o">+</span> <span class="n">hidden_states</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</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">reduce_fusion</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">attention_output</span>
<span class="k">elif</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">norm_quant_fusion</span><span class="p">:</span>
<span class="n">hidden_states</span><span class="p">,</span> <span class="n">residual_attn</span><span class="p">,</span> <span class="n">act_per_block_scale</span> <span class="o">=</span> <span class="n">fused_layernorm</span><span class="p">(</span>
<span class="nb">input</span><span class="o">=</span><span class="n">attention_output</span><span class="p">,</span>
<span class="n">normalized_shape</span><span class="o">=</span><span class="bp">self</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">residual</span><span class="o">=</span><span class="n">residual</span><span class="p">,</span>
<span class="n">weight</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">post_layernorm</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">value</span><span class="p">,</span>
<span class="n">scale</span><span class="o">=</span><span class="n">div</span><span class="p">(</span>
<span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">mlp</span><span class="o">.</span><span class="n">fc</span><span class="o">.</span><span class="n">activation_global_scaling_factor</span><span class="o">.</span><span class="n">value</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mlp</span><span class="o">.</span><span class="n">fc</span><span class="o">.</span><span class="n">activation_global_scaling_factor</span><span class="o">.</span><span class="n">value</span> <span class="k">else</span>
<span class="kc">None</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">post_layernorm</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
<span class="n">p_dtype</span><span class="o">=</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="n">hidden_states</span><span class="p">,</span> <span class="n">residual_attn</span> <span class="o">=</span> <span class="p">(</span>
<span class="n">hidden_states</span><span class="p">,</span> <span class="n">act_per_block_scale</span><span class="p">),</span> <span class="n">residual_attn</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)</span>
<span class="k">else</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="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">residual_multiplier</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">if</span> <span class="n">next_layer_input_layernorm_args</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="c1">#this is middle layer</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">lora_layer_params</span><span class="o">=</span><span class="n">lora_layer_params</span><span class="p">,</span>
<span class="n">all_reduce_params</span><span class="o">=</span><span class="n">AllReduceParams</span><span class="p">(</span>
<span class="n">fusion_op</span><span class="o">=</span><span class="n">reduce_fusion_op</span><span class="p">,</span>
<span class="n">residual</span><span class="o">=</span><span class="n">residual_attn</span>
<span class="k">if</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">norm_quant_fusion</span> <span class="k">else</span>
<span class="n">residual</span><span class="p">,</span>
<span class="n">norm_weight</span><span class="o">=</span><span class="n">next_layer_input_layernorm_args</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
<span class="n">scale</span><span class="o">=</span><span class="n">next_layer_input_layernorm_args</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span>
<span class="n">eps</span><span class="o">=</span><span class="n">next_layer_input_layernorm_args</span><span class="p">[</span><span class="mi">1</span><span class="p">]))</span>
<span class="k">if</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">norm_quant_fusion</span><span class="p">:</span>
<span class="n">hidden_states</span><span class="p">,</span> <span class="n">residual</span><span class="p">,</span> <span class="n">act_per_block_scale</span> <span class="o">=</span> <span class="n">fused_layernorm</span><span class="p">(</span>
<span class="nb">input</span><span class="o">=</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="n">normalized_shape</span><span class="o">=</span><span class="bp">self</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">residual</span><span class="o">=</span><span class="n">residual_attn</span><span class="p">,</span>
<span class="n">weight</span><span class="o">=</span><span class="n">next_layer_input_layernorm_args</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
<span class="n">scale</span><span class="o">=</span><span class="n">div</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">next_layer_input_layernorm_args</span><span class="p">[</span><span class="mi">2</span><span class="p">])</span>
<span class="k">if</span> <span class="n">next_layer_input_layernorm_args</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span> <span class="k">else</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="n">next_layer_input_layernorm_args</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span>
<span class="n">p_dtype</span><span class="o">=</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="n">hidden_states</span> <span class="o">=</span> <span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="n">act_per_block_scale</span><span class="p">),</span> <span class="n">residual</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="n">default_net</span><span class="p">(</span>
<span class="p">)</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">pp_reduce_scatter</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_last_local_layer</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">is_last_pp_rank</span><span class="p">(</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">mlp</span><span class="p">(</span>
<span class="n">hidden_states</span><span class="p">,</span>
<span class="n">lora_layer_params</span><span class="o">=</span><span class="n">lora_layer_params</span><span class="p">,</span>
<span class="n">last_local_layer_residual</span><span class="o">=</span><span class="n">residual</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="p">(</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">reduce_fusion</span>
<span class="ow">and</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">user_buffer</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="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">lora_layer_params</span><span class="o">=</span><span class="n">lora_layer_params</span><span class="p">,</span>
<span class="n">all_reduce_params</span><span class="o">=</span><span class="n">AllReduceParams</span><span class="p">(</span>
<span class="n">fusion_op</span><span class="o">=</span><span class="n">AllReduceFusionOp</span><span class="o">.</span><span class="n">LAST_PROCESS_FOR_UB</span><span class="p">,</span>
<span class="n">residual</span><span class="o">=</span><span class="n">residual</span><span class="p">))</span>
<span class="k">else</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">mlp</span><span class="p">(</span>
<span class="n">hidden_states</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="o">=</span><span class="n">lora_layer_params</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="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">residual_multiplier</span>
<span class="k">if</span> <span class="n">use_cache</span><span class="p">:</span>
<span class="k">return</span> <span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">presents</span><span class="p">)</span>
<span class="k">return</span> <span class="n">hidden_states</span>
<div class="viewcode-block" id="LLaMAModel">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.LLaMAModel">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">LLaMAModel</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">config</span><span class="p">:</span> <span class="n">LLaMAConfig</span><span class="p">)</span> <span class="o">-&gt;</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">mapping</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">mapping</span>
<span class="bp">self</span><span class="o">.</span><span class="n">vocab_size</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">vocab_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">has_partial_lora_mask</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">has_partial_lora_mask</span>
<span class="bp">self</span><span class="o">.</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">is_first_pp_rank</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">config</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">,</span>
<span class="n">config</span><span class="o">.</span><span class="n">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">embedding_multiplier</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">embedding_multiplier</span>
<span class="bp">self</span><span class="o">.</span><span class="n">layers</span> <span class="o">=</span> <span class="n">DecoderLayerList</span><span class="p">(</span><span class="n">LLaMADecoderLayer</span><span class="p">,</span> <span class="n">config</span><span class="p">)</span>
<span class="k">if</span> <span class="n">config</span><span class="o">.</span><span class="n">fc_after_embed</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fc</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span><span class="mi">2</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">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">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="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">gather_output</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">is_last_pp_rank</span><span class="p">():</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ln_f</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">config</span><span class="o">.</span><span class="n">use_last_layernorm</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ln_f</span> <span class="o">=</span> <span class="n">RmsNorm</span><span class="p">(</span><span class="n">normalized_shape</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">eps</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">norm_epsilon</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="LLaMAModel.forward">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.LLaMAModel.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">position_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">use_cache</span><span class="o">=</span><span class="kc">False</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">spec_decoding_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">kv_cache_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">attention_params</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">hidden_states_for_embed</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">prompt_embedding_table</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Tensor</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">prompt_tasks</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Tensor</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">prompt_vocab_size</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Tensor</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">lora_params</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">ptuning_args</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">prompt_embedding_table</span><span class="p">,</span> <span class="n">prompt_tasks</span><span class="p">,</span> <span class="n">prompt_vocab_size</span>
<span class="p">]</span> <span class="k">if</span> <span class="n">prompt_embedding_table</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="k">else</span> <span class="p">[]</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">is_first_pp_rank</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">vocab_embedding</span><span class="p">(</span><span class="n">input_ids</span><span class="p">,</span> <span class="o">*</span><span class="n">ptuning_args</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_multiplier</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">recv</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">prev_pp_rank</span><span class="p">())</span>
<span class="k">if</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">pp_reduce_scatter</span><span class="p">:</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">allgather</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="bp">self</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">gather_dim</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="c1"># reshape to (-1, hidden_size)</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">hidden_states</span><span class="o">.</span><span class="n">view</span><span class="p">(</span>
<span class="n">concat</span><span class="p">([</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">]))</span>
<span class="k">if</span> <span class="n">hidden_states_for_embed</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">concat</span><span class="p">([</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">hidden_states_for_embed</span><span class="p">],</span>
<span class="n">dim</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="k">if</span> <span class="n">lora_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">has_partial_lora_mask</span><span class="p">:</span>
<span class="n">partial_lora_mask</span> <span class="o">=</span> <span class="n">input_ids</span> <span class="o">&gt;</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">vocab_size</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span>
<span class="n">lora_params</span><span class="o">.</span><span class="n">partial_lora_mask</span> <span class="o">=</span> <span class="n">unsqueeze</span><span class="p">(</span><span class="n">partial_lora_mask</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</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">layers</span><span class="o">.</span><span class="n">forward</span><span class="p">(</span>
<span class="n">hidden_states</span><span class="p">,</span>
<span class="n">use_cache</span><span class="o">=</span><span class="n">use_cache</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">kv_cache_params</span><span class="o">=</span><span class="n">kv_cache_params</span><span class="p">,</span>
<span class="n">attention_params</span><span class="o">=</span><span class="n">attention_params</span><span class="p">,</span>
<span class="n">lora_params</span><span class="o">=</span><span class="n">lora_params</span><span class="p">,</span>
<span class="n">spec_decoding_params</span><span class="o">=</span><span class="n">spec_decoding_params</span><span class="p">)</span>
<span class="k">if</span> <span class="n">use_cache</span><span class="p">:</span>
<span class="n">hidden_states</span><span class="p">,</span> <span class="n">presents</span> <span class="o">=</span> <span class="n">hidden_states</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">is_last_pp_rank</span><span class="p">():</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">ln_f</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">ln_f</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">send</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">next_pp_rank</span><span class="p">())</span>
<span class="k">if</span> <span class="n">use_cache</span><span class="p">:</span>
<span class="k">return</span> <span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">presents</span><span class="p">))</span>
<span class="k">return</span> <span class="n">hidden_states</span></div>
</div>
<div class="viewcode-block" id="LLaMAForCausalLM">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.LLaMAForCausalLM">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">LLaMAForCausalLM</span><span class="p">(</span><span class="n">DecoderModelForCausalLM</span><span class="p">):</span>
<span class="n">config_class</span> <span class="o">=</span> <span class="n">LLaMAConfig</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">LLaMAConfig</span><span class="p">):</span>
<span class="n">transformer</span> <span class="o">=</span> <span class="n">LLaMAModel</span><span class="p">(</span><span class="n">config</span><span class="p">)</span>
<span class="n">vocab_size_padded</span> <span class="o">=</span> <span class="n">pad_vocab_size</span><span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">,</span>
<span class="n">config</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">)</span>
<span class="k">if</span> <span class="n">config</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">is_last_pp_rank</span><span class="p">():</span>
<span class="n">lm_head</span> <span class="o">=</span> <span class="n">ColumnLinear</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">vocab_size_padded</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">dtype</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">gather_output</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">lm_head</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">quant_mode</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">quant_mode</span>
<span class="bp">self</span><span class="o">.</span><span class="n">mapping</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">mapping</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="n">transformer</span><span class="p">,</span> <span class="n">lm_head</span><span class="p">)</span>
<div class="viewcode-block" id="LLaMAForCausalLM.from_hugging_face">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.LLaMAForCausalLM.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_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;auto&#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">&#39;&#39;&#39; Create a LLaMAForCausalLM object from give parameters</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">transformers</span>
<span class="n">load_by_shard</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_by_shard&#39;</span><span class="p">,</span> <span class="kc">False</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">&#39;load_model_on_cpu&#39;</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>
<span class="n">quant_ckpt_path</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;quant_ckpt_path&#39;</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
<span class="n">use_autoawq</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;use_autoawq&#39;</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;TRTLLM_DISABLE_UNIFIED_CONVERTER&quot;</span>
<span class="p">)</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="ow">not</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="s2">&quot;vila&quot;</span> <span class="ow">in</span> <span class="n">hf_model_or_dir</span> <span class="ow">or</span> <span class="s2">&quot;llava&quot;</span> <span class="ow">in</span> <span class="n">hf_model_or_dir</span><span class="p">:</span>
<span class="n">hf_model_or_dir</span> <span class="o">=</span> <span class="n">load_hf_llama</span><span class="p">(</span><span class="n">hf_model_or_dir</span><span class="p">,</span>
<span class="n">load_model_on_cpu</span><span class="p">)</span>
<span class="k">elif</span> <span class="ow">not</span> <span class="n">load_by_shard</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">has_safetensors</span><span class="p">(</span>
<span class="n">hf_model_or_dir</span><span class="p">)</span> <span class="ow">and</span> <span class="p">(</span>
<span class="n">quant_config</span> <span class="ow">is</span> <span class="kc">None</span>
<span class="ow">or</span> <span class="ow">not</span> <span class="n">quant_config</span><span class="o">.</span><span class="n">quant_mode</span><span class="o">.</span><span class="n">has_any_quant</span><span class="p">()):</span>
<span class="n">hf_model_or_dir</span> <span class="o">=</span> <span class="n">load_hf_llama</span><span class="p">(</span><span class="n">hf_model_or_dir</span><span class="p">,</span>
<span class="n">load_model_on_cpu</span><span class="p">)</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">config</span> <span class="o">=</span> <span class="n">LLaMAConfig</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="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="k">if</span> <span class="n">config</span><span class="o">.</span><span class="n">remove_duplicated_kv_heads</span><span class="p">:</span>
<span class="n">config</span><span class="o">.</span><span class="n">num_key_value_heads</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">num_key_value_heads</span> <span class="o">//</span> <span class="mi">2</span>
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;TRTLLM_DISABLE_UNIFIED_CONVERTER&quot;</span><span class="p">)</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">custom_dict</span> <span class="o">=</span> <span class="p">{}</span>
<span class="n">model_name</span> <span class="o">=</span> <span class="n">hf_model</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">model_type</span> <span class="k">if</span> <span class="n">use_preloading</span> <span class="k">else</span> <span class="n">hf_model_or_dir</span>
<span class="k">if</span> <span class="s2">&quot;llava&quot;</span> <span class="ow">in</span> <span class="n">model_name</span><span class="p">:</span>
<span class="n">custom_dict</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;transformer&quot;</span><span class="p">:</span> <span class="s2">&quot;language_model.model&quot;</span><span class="p">,</span>
<span class="s2">&quot;lm_head&quot;</span><span class="p">:</span> <span class="s2">&quot;language_model.lm_head&quot;</span>
<span class="p">}</span>
<span class="k">elif</span> <span class="s2">&quot;vila&quot;</span> <span class="ow">in</span> <span class="n">model_name</span><span class="p">:</span>
<span class="n">hf_model_dir</span> <span class="o">+=</span> <span class="s2">&quot;/llm&quot;</span>
<span class="k">elif</span> <span class="s2">&quot;exaone&quot;</span> <span class="ow">in</span> <span class="n">model_name</span><span class="o">.</span><span class="n">lower</span><span class="p">():</span>
<span class="n">custom_dict</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;transformer&quot;</span><span class="p">:</span> <span class="s2">&quot;transformer&quot;</span><span class="p">,</span>
<span class="s2">&quot;layers&quot;</span><span class="p">:</span> <span class="s2">&quot;h&quot;</span><span class="p">,</span>
<span class="s2">&quot;vocab_embedding&quot;</span><span class="p">:</span> <span class="s2">&quot;wte&quot;</span><span class="p">,</span>
<span class="s2">&quot;lm_head&quot;</span><span class="p">:</span> <span class="s2">&quot;lm_head&quot;</span><span class="p">,</span>
<span class="s2">&quot;ln_f&quot;</span><span class="p">:</span> <span class="s2">&quot;ln_f&quot;</span><span class="p">,</span>
<span class="s2">&quot;attention&quot;</span><span class="p">:</span> <span class="s2">&quot;attn.attention&quot;</span><span class="p">,</span>
<span class="s2">&quot;dense&quot;</span><span class="p">:</span> <span class="s2">&quot;out_proj&quot;</span><span class="p">,</span>
<span class="s2">&quot;gate&quot;</span><span class="p">:</span> <span class="s2">&quot;c_fc_1&quot;</span><span class="p">,</span>
<span class="s2">&quot;proj&quot;</span><span class="p">:</span> <span class="s2">&quot;c_proj&quot;</span><span class="p">,</span>
<span class="s2">&quot;fc&quot;</span><span class="p">:</span> <span class="s2">&quot;c_fc_0&quot;</span><span class="p">,</span>
<span class="s2">&quot;input_layernorm&quot;</span><span class="p">:</span> <span class="s2">&quot;ln_1&quot;</span><span class="p">,</span>
<span class="s2">&quot;post_layernorm&quot;</span><span class="p">:</span> <span class="s2">&quot;ln_2&quot;</span><span class="p">,</span>
<span class="p">}</span>
<span class="k">elif</span> <span class="n">config</span><span class="o">.</span><span class="n">tie_word_embeddings</span><span class="p">:</span>
<span class="n">custom_dict</span> <span class="o">=</span> <span class="p">{</span><span class="s2">&quot;lm_head&quot;</span><span class="p">:</span> <span class="s2">&quot;model.embed_tokens&quot;</span><span class="p">}</span>
<span class="k">if</span> <span class="n">quant_ckpt_path</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">hf_model_dir</span> <span class="o">=</span> <span class="n">quant_ckpt_path</span>
<span class="n">arg_dict</span> <span class="o">=</span> <span class="p">{</span><span class="s2">&quot;use_autoawq&quot;</span><span class="p">:</span> <span class="kc">True</span><span class="p">}</span> <span class="k">if</span> <span class="n">use_autoawq</span> <span class="k">else</span> <span class="p">{}</span>
<span class="n">loader</span> <span class="o">=</span> <span class="n">ModelWeightsLoader</span><span class="p">(</span><span class="n">hf_model_dir</span><span class="p">,</span> <span class="n">custom_dict</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">config</span><span class="p">)</span>
<span class="n">loader</span><span class="o">.</span><span class="n">generate_tllm_weights</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">arg_dict</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="n">use_preloading</span><span class="p">:</span>
<span class="k">assert</span> <span class="ow">not</span> <span class="n">load_by_shard</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="p">,</span> <span class="n">config</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">load_by_shard</span><span class="p">:</span>
<span class="n">weights</span> <span class="o">=</span> <span class="n">load_weights_from_hf_by_shard</span><span class="p">(</span><span class="n">hf_model_dir</span><span class="p">,</span> <span class="n">config</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">has_safetensors</span><span class="p">(</span>
<span class="n">hf_model_dir</span><span class="p">)</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">config</span><span class="o">.</span><span class="n">quant_mode</span><span class="o">.</span><span class="n">has_any_quant</span><span class="p">():</span>
<span class="n">weights</span> <span class="o">=</span> <span class="n">load_weights_from_hf_safetensors</span><span class="p">(</span><span class="n">hf_model_dir</span><span class="p">,</span> <span class="n">config</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">quant_ckpt_path</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">quant_config</span><span class="o">.</span><span class="n">quant_mode</span><span class="o">.</span><span class="n">is_int4_weight_only</span><span class="p">():</span>
<span class="n">weights</span> <span class="o">=</span> <span class="n">load_weights_from_gptq</span><span class="p">(</span><span class="n">quant_ckpt_path</span><span class="p">,</span> <span class="n">config</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">quant_config</span><span class="o">.</span><span class="n">quant_mode</span><span class="o">.</span><span class="n">is_qserve_w4a8</span><span class="p">():</span>
<span class="n">weights</span> <span class="o">=</span> <span class="n">load_weights_from_deepcompressor</span><span class="p">(</span>
<span class="n">quant_ckpt_path</span><span class="p">,</span> <span class="n">config</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">&quot;quant_ckpt_path should be specified only for GPTQ or QServe&quot;</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">hf_model</span> <span class="o">=</span> <span class="n">load_hf_llama</span><span class="p">(</span><span class="n">hf_model_dir</span><span class="p">,</span> <span class="n">load_model_on_cpu</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="p">,</span> <span class="n">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">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></div>
<div class="viewcode-block" id="LLaMAForCausalLM.default_plugin_config">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.LLaMAForCausalLM.default_plugin_config">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">default_plugin_config</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="n">plugin_config</span> <span class="o">=</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">default_plugin_config</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">quant_mode</span><span class="o">.</span><span class="n">is_int4_weight_only_per_group</span><span class="p">():</span>
<span class="n">plugin_config</span><span class="o">.</span><span class="n">weight_only_groupwise_quant_matmul_plugin</span> <span class="o">=</span> <span class="s1">&#39;auto&#39;</span>
<span class="k">return</span> <span class="n">plugin_config</span></div>
<div class="viewcode-block" id="LLaMAForCausalLM.from_meta_ckpt">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.LLaMAForCausalLM.from_meta_ckpt">[docs]</a>
<span class="nd">@classmethod</span>
<span class="k">def</span><span class="w"> </span><span class="nf">from_meta_ckpt</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span>
<span class="n">meta_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">&#39;auto&#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="n">config</span> <span class="o">=</span> <span class="n">LLaMAConfig</span><span class="o">.</span><span class="n">from_meta_ckpt</span><span class="p">(</span><span class="n">meta_ckpt_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="n">weights</span> <span class="o">=</span> <span class="n">load_weights_from_meta_ckpt</span><span class="p">(</span><span class="n">meta_ckpt_dir</span><span class="p">,</span> <span class="n">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">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></div>
<div class="viewcode-block" id="LLaMAForCausalLM.quantize">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.LLaMAForCausalLM.quantize">[docs]</a>
<span class="nd">@classmethod</span>
<span class="k">def</span><span class="w"> </span><span class="nf">quantize</span><span class="p">(</span>
<span class="bp">cls</span><span class="p">,</span>
<span class="n">hf_model_dir</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">output_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">&#39;auto&#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="p">,</span>
<span class="n">device</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s1">&#39;cuda&#39;</span><span class="p">,</span>
<span class="n">calib_dataset</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s1">&#39;cnn_dailymail&#39;</span><span class="p">,</span>
<span class="n">calib_batches</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">512</span><span class="p">,</span>
<span class="n">calib_batch_size</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
<span class="n">calib_max_seq_length</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">512</span><span class="p">,</span>
<span class="n">random_seed</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1234</span><span class="p">,</span>
<span class="n">tokenizer_max_seq_length</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2048</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">,</span>
<span class="p">):</span>
<span class="k">if</span> <span class="n">quant_config</span><span class="o">.</span><span class="n">_requires_modelopt_quantization</span><span class="p">:</span>
<span class="c1"># modelopt quantization flow</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">quantize</span><span class="p">(</span><span class="n">hf_model_dir</span><span class="p">,</span>
<span class="n">output_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="n">device</span><span class="o">=</span><span class="n">device</span><span class="p">,</span>
<span class="n">calib_dataset</span><span class="o">=</span><span class="n">calib_dataset</span><span class="p">,</span>
<span class="n">calib_batches</span><span class="o">=</span><span class="n">calib_batches</span><span class="p">,</span>
<span class="n">calib_batch_size</span><span class="o">=</span><span class="n">calib_batch_size</span><span class="p">,</span>
<span class="n">calib_max_seq_length</span><span class="o">=</span><span class="n">calib_max_seq_length</span><span class="p">,</span>
<span class="n">random_seed</span><span class="o">=</span><span class="n">random_seed</span><span class="p">,</span>
<span class="n">tokenizer_max_seq_length</span><span class="o">=</span><span class="n">tokenizer_max_seq_length</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">quant_config</span><span class="o">.</span><span class="n">_requires_calibration</span><span class="p">:</span>
<span class="c1"># non-modelopt quantization flow</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">.</span><span class="w"> </span><span class="kn">import</span> <span class="n">convert</span>
<span class="n">config</span> <span class="o">=</span> <span class="n">LLaMAConfig</span><span class="o">.</span><span class="n">from_hugging_face</span><span class="p">(</span><span class="n">hf_model_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="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="s2">&quot;trust_remote_code&quot;</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span>
<span class="n">convert</span><span class="o">.</span><span class="n">quantize</span><span class="p">(</span><span class="n">hf_model_dir</span><span class="p">,</span>
<span class="n">output_dir</span><span class="p">,</span>
<span class="n">config</span><span class="o">=</span><span class="n">config</span><span class="p">,</span>
<span class="n">device</span><span class="o">=</span><span class="n">device</span><span class="p">,</span>
<span class="n">calib_dataset</span><span class="o">=</span><span class="n">calib_dataset</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">calib_batches</span><span class="o">=</span><span class="n">calib_batches</span><span class="p">,</span>
<span class="n">calib_max_seq_length</span><span class="o">=</span><span class="n">calib_max_seq_length</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;The quant_config (</span><span class="si">{</span><span class="n">quant_config</span><span class="si">}</span><span class="s2">) does not require calibration, try </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">.from_hugging_face instead.&quot;</span>
<span class="p">)</span></div>
<div class="viewcode-block" id="LLaMAForCausalLM.use_lora">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.LLaMAForCausalLM.use_lora">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">use_lora</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">lora_config</span><span class="p">:</span> <span class="n">LoraConfig</span><span class="p">):</span>
<span class="n">use_lora</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">lora_config</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 August 15, 2025.</p>
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/26f413a">26f413a</a>.</p>
</div></div>
</div>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink