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
ae05ac189f
TensorRT-LLMs/latest/_modules/tensorrt_llm/layers/mlp.html
Kaiyu Xie ae05ac189f Update latest GitHub pages to v1.0.0rc6
2025-08-07 06:26:14 +00:00

1255 lines
112 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.layers.mlp &#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/layers/mlp';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.0.0rc6';
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="1.0.0rc6" />
</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">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 (Experimental)</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Performance</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-benchmarking.html">Benchmarking</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../performance/performance-tuning-guide/index.html">Performance Tuning Guide</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/benchmarking-default-performance.html">Benchmarking Default Performance</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/useful-build-time-flags.html">Useful Build-Time Flags</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.html">Tuning Max Batch Size and Max Num Tokens</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/deciding-model-sharding-strategy.html">Deciding Model Sharding Strategy</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/fp8-quantization.html">FP8 Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/useful-runtime-flags.html">Useful Runtime Options</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-analysis.html">Performance Analysis</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../reference/troubleshooting.html">Troubleshooting</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../reference/support-matrix.html">Support Matrix</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../reference/precision.html">Numerical Precision</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../reference/memory.html">Memory Usage of TensorRT-LLM</a></li>
<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.layers.mlp</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<h1>Source code for tensorrt_llm.layers.mlp</h1><div class="highlight"><pre>
<span></span><span class="c1"># SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION &amp; AFFILIATES. All rights reserved.</span>
<span class="c1"># SPDX-License-Identifier: Apache-2.0</span>
<span class="c1">#</span>
<span class="c1"># Licensed under the Apache License, Version 2.0 (the &quot;License&quot;);</span>
<span class="c1"># you may not use this file except in compliance with the License.</span>
<span class="c1"># You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Optional</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">tensorrt</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">trt</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">.._common</span><span class="w"> </span><span class="kn">import</span> <span class="n">default_net</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">..functional</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span><span class="n">ACT2FN</span><span class="p">,</span> <span class="n">AllReduceParams</span><span class="p">,</span> <span class="n">cast</span><span class="p">,</span> <span class="n">chunk</span><span class="p">,</span> <span class="n">concat</span><span class="p">,</span>
<span class="n">gemm_swiglu</span><span class="p">,</span> <span class="n">is_gated_activation</span><span class="p">,</span>
<span class="n">low_latency_gemm_swiglu</span><span class="p">)</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">..mapping</span><span class="w"> </span><span class="kn">import</span> <span class="n">Mapping</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">..module</span><span class="w"> </span><span class="kn">import</span> <span class="n">Module</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">..quantization</span><span class="w"> </span><span class="kn">import</span> <span class="n">QuantMode</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">quantize</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">..quantization.layers</span><span class="w"> </span><span class="kn">import</span> <span class="n">FP8Linear</span><span class="p">,</span> <span class="n">FP8RowLinear</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">.linear</span><span class="w"> </span><span class="kn">import</span> <span class="n">ColumnLinear</span><span class="p">,</span> <span class="n">RowLinear</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">.lora</span><span class="w"> </span><span class="kn">import</span> <span class="n">LoraRuntimeParams</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">.normalization</span><span class="w"> </span><span class="kn">import</span> <span class="n">LayerNorm</span>
<div class="viewcode-block" id="fc_gate_lora">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.fc_gate_lora">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">fc_gate_lora</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">lora</span><span class="p">,</span> <span class="n">fused_gate_up_lora</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="p">):</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_h_to_4h&quot;</span><span class="p">)</span>
<span class="n">mlp_gate_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_gate&quot;</span><span class="p">)</span>
<span class="n">mlp_gate_up_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_gate_up&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">mlp_gate_up_lora_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">fused_gate_up_lora</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
<span class="n">mlp_gate_up_lora</span> <span class="o">=</span> <span class="n">fused_gate_up_lora</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="n">mlp_gate_up_lora_params</span><span class="p">)</span>
<span class="k">return</span> <span class="n">mlp_gate_up_lora</span>
<span class="k">elif</span> <span class="n">mlp_fc_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="n">mlp_gate_lora_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_in_lora_params</span> <span class="o">=</span> <span class="n">LoraRuntimeParams</span><span class="p">(</span>
<span class="n">lora_ranks</span><span class="o">=</span><span class="p">[</span>
<span class="n">mlp_fc_lora_params</span><span class="o">.</span><span class="n">lora_ranks</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
<span class="n">mlp_gate_lora_params</span><span class="o">.</span><span class="n">lora_ranks</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="p">],</span>
<span class="n">lora_weights_pointers</span><span class="o">=</span><span class="p">[</span>
<span class="n">mlp_fc_lora_params</span><span class="o">.</span><span class="n">lora_weights_pointers</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
<span class="n">mlp_gate_lora_params</span><span class="o">.</span><span class="n">lora_weights_pointers</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="p">],</span>
<span class="n">host_request_types</span><span class="o">=</span><span class="n">mlp_fc_lora_params</span><span class="o">.</span><span class="n">host_request_types</span><span class="p">,</span>
<span class="n">host_context_lengths</span><span class="o">=</span><span class="n">mlp_fc_lora_params</span><span class="o">.</span><span class="n">host_context_lengths</span><span class="p">)</span>
<span class="n">mlp_fc_lora</span><span class="p">,</span> <span class="n">mlp_gate_lora</span> <span class="o">=</span> <span class="n">lora</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">mlp_in_lora_params</span><span class="p">)</span>
<span class="n">mlp_in_result</span> <span class="o">=</span> <span class="n">concat</span><span class="p">([</span><span class="n">mlp_gate_lora</span><span class="p">,</span> <span class="n">mlp_fc_lora</span><span class="p">],</span>
<span class="n">dim</span><span class="o">=</span><span class="n">mlp_fc_lora</span><span class="o">.</span><span class="n">rank</span><span class="p">()</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span>
<span class="k">return</span> <span class="n">mlp_in_result</span>
<span class="k">return</span> <span class="kc">None</span></div>
<div class="viewcode-block" id="fc_gate_dora">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.fc_gate_dora">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">fc_gate_dora</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">dora</span><span class="p">,</span> <span class="n">fused_gate_up_dora</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="p">):</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_h_to_4h&quot;</span><span class="p">)</span>
<span class="n">mlp_gate_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_gate&quot;</span><span class="p">)</span>
<span class="n">mlp_gate_up_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_gate_up&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">mlp_gate_up_lora_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">fused_gate_up_dora</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
<span class="k">return</span> <span class="n">fused_gate_up_dora</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">mlp_gate_up_lora_params</span><span class="p">)</span>
<span class="k">if</span> <span class="n">mlp_fc_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="n">mlp_gate_lora_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_in_lora_params</span> <span class="o">=</span> <span class="n">LoraRuntimeParams</span><span class="p">(</span>
<span class="n">lora_ranks</span><span class="o">=</span><span class="p">[</span>
<span class="n">mlp_fc_lora_params</span><span class="o">.</span><span class="n">lora_ranks</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
<span class="n">mlp_gate_lora_params</span><span class="o">.</span><span class="n">lora_ranks</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="p">],</span>
<span class="n">lora_weights_pointers</span><span class="o">=</span><span class="p">[</span>
<span class="n">mlp_fc_lora_params</span><span class="o">.</span><span class="n">lora_weights_pointers</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
<span class="n">mlp_gate_lora_params</span><span class="o">.</span><span class="n">lora_weights_pointers</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="p">],</span>
<span class="n">host_request_types</span><span class="o">=</span><span class="n">mlp_fc_lora_params</span><span class="o">.</span><span class="n">host_request_types</span><span class="p">,</span>
<span class="n">host_context_lengths</span><span class="o">=</span><span class="n">mlp_fc_lora_params</span><span class="o">.</span><span class="n">host_context_lengths</span><span class="p">)</span>
<span class="k">return</span> <span class="n">dora</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">mlp_in_lora_params</span><span class="p">)</span>
<span class="k">return</span> <span class="kc">None</span></div>
<div class="viewcode-block" id="MLP">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.MLP">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">MLP</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span>
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">hidden_size</span><span class="p">,</span>
<span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">hidden_act</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="kc">None</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">quant_mode</span><span class="o">=</span><span class="n">QuantMode</span><span class="p">(</span><span class="mi">0</span><span class="p">),</span>
<span class="n">inner_layernorm</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="mf">1e-05</span><span class="p">,</span>
<span class="n">is_expert</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="k">if</span> <span class="n">hidden_act</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">ACT2FN</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;unsupported activation function: </span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">hidden_act</span><span class="p">))</span>
<span class="n">fc_output_size</span> <span class="o">=</span> <span class="mi">2</span> <span class="o">*</span> <span class="n">ffn_hidden_size</span> <span class="k">if</span> <span class="n">hidden_act</span> <span class="ow">in</span> <span class="p">[</span>
<span class="s1">&#39;swiglu&#39;</span><span class="p">,</span> <span class="s1">&#39;gegelu&#39;</span>
<span class="p">]</span> <span class="k">else</span> <span class="n">ffn_hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span> <span class="o">=</span> <span class="n">LayerNorm</span><span class="p">(</span><span class="n">ffn_hidden_size</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="n">eps</span><span class="p">)</span> <span class="k">if</span> <span class="n">inner_layernorm</span> <span class="k">else</span> <span class="kc">None</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="n">hidden_size</span><span class="p">,</span>
<span class="n">fc_output_size</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">gather_output</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">proj</span> <span class="o">=</span> <span class="n">RowLinear</span><span class="p">(</span><span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">hidden_size</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">is_expert</span><span class="o">=</span><span class="n">is_expert</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span> <span class="o">=</span> <span class="n">hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ffn_hidden_size</span> <span class="o">=</span> <span class="n">ffn_hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">=</span> <span class="n">hidden_act</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dtype</span> <span class="o">=</span> <span class="n">dtype</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="n">bias</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_group</span> <span class="o">=</span> <span class="n">tp_group</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">=</span> <span class="n">tp_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">quant_mode</span> <span class="o">=</span> <span class="n">quant_mode</span>
<span class="bp">self</span><span class="o">.</span><span class="n">eps</span> <span class="o">=</span> <span class="n">eps</span>
<span class="bp">self</span><span class="o">.</span><span class="n">is_expert</span> <span class="o">=</span> <span class="n">is_expert</span>
<span class="c1"># see optimize_model&#39;s add_lora for LoRA initialization</span>
<span class="bp">self</span><span class="o">.</span><span class="n">lora</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dora</span> <span class="o">=</span> <span class="kc">None</span>
<div class="viewcode-block" id="MLP.forward">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.MLP.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">hidden_states</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">gegelu_limit</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_gate_up&quot;</span>
<span class="p">)</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">,</span> <span class="sa">f</span><span class="s2">&quot;LoRA module &#39;mlp_gate_up&#39; is not supported in </span><span class="si">{</span><span class="bp">self</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="k">if</span> <span class="n">is_gated_activation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="p">):</span>
<span class="n">inter</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="n">lora_result</span> <span class="o">=</span> <span class="n">fc_gate_lora</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">lora</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">lora_layer_params</span><span class="p">)</span>
<span class="k">if</span> <span class="n">lora_result</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">inter</span> <span class="o">+</span> <span class="n">lora_result</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">dora</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">fc_gate_dora</span><span class="p">(</span><span class="n">inter</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dora</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fused_gate_up_dora</span><span class="p">,</span>
<span class="n">lora_layer_params</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_h_to_4h&quot;</span><span class="p">)</span>
<span class="n">inter</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="n">mlp_fc_lora_params</span><span class="p">)</span>
<span class="n">mlp_proj_lora_params</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_proj_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_4h_to_h&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">==</span> <span class="s1">&#39;gegelu&#39;</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="p">](</span><span class="n">inter</span><span class="p">,</span> <span class="n">gegelu_limit</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="p">](</span><span class="n">inter</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span><span class="p">(</span><span class="n">inter</span><span class="p">)</span>
<span class="n">output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">proj</span><span class="p">(</span><span class="n">inter</span><span class="p">,</span> <span class="n">lora_runtime_params</span><span class="o">=</span><span class="n">mlp_proj_lora_params</span><span class="p">)</span>
<span class="k">return</span> <span class="n">output</span></div>
</div>
<div class="viewcode-block" id="GatedMLP">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.GatedMLP">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">GatedMLP</span><span class="p">(</span><span class="n">MLP</span><span class="p">):</span>
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">hidden_size</span><span class="p">,</span>
<span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">hidden_act</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="kc">None</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">quant_mode</span><span class="o">=</span><span class="n">QuantMode</span><span class="p">(</span><span class="mi">0</span><span class="p">),</span>
<span class="n">inner_layernorm</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="mf">1e-05</span><span class="p">,</span>
<span class="n">is_expert</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">hidden_act</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">quant_mode</span><span class="o">=</span><span class="n">quant_mode</span><span class="p">,</span>
<span class="n">inner_layernorm</span><span class="o">=</span><span class="n">inner_layernorm</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="n">eps</span><span class="p">,</span>
<span class="n">is_expert</span><span class="o">=</span><span class="n">is_expert</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span> <span class="o">=</span> <span class="n">hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ffn_hidden_size</span> <span class="o">=</span> <span class="n">ffn_hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_group</span> <span class="o">=</span> <span class="n">tp_group</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">=</span> <span class="n">tp_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gate</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">gather_output</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<div class="viewcode-block" id="GatedMLP.forward">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.GatedMLP.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">hidden_states</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">all_reduce_params</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">AllReduceParams</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_gate_up&quot;</span>
<span class="p">)</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">,</span> <span class="sa">f</span><span class="s2">&quot;LoRA module &#39;mlp_gate_up&#39; is not supported in </span><span class="si">{</span><span class="bp">self</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_h_to_4h&quot;</span><span class="p">)</span>
<span class="n">mlp_gate_lora_params</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_gate_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_gate&quot;</span><span class="p">)</span>
<span class="n">mlp_proj_lora_params</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_proj_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_4h_to_h&quot;</span><span class="p">)</span>
<span class="n">inter</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="n">mlp_fc_lora_params</span><span class="p">)</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="p">](</span><span class="n">inter</span><span class="p">)</span>
<span class="n">gate</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">gate</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">mlp_gate_lora_params</span><span class="p">)</span>
<span class="n">intermediate</span> <span class="o">=</span> <span class="n">inter</span> <span class="o">*</span> <span class="n">gate</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">intermediate</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span><span class="p">(</span><span class="n">intermediate</span><span class="p">)</span>
<span class="n">output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">proj</span><span class="p">(</span><span class="n">intermediate</span><span class="p">,</span>
<span class="n">lora_runtime_params</span><span class="o">=</span><span class="n">mlp_proj_lora_params</span><span class="p">,</span>
<span class="n">all_reduce_params</span><span class="o">=</span><span class="n">all_reduce_params</span><span class="p">)</span>
<span class="k">return</span> <span class="n">output</span></div>
</div>
<div class="viewcode-block" id="FusedGatedMLP">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.FusedGatedMLP">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">FusedGatedMLP</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span>
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">hidden_size</span><span class="p">,</span>
<span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">hidden_act</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="kc">None</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">quant_mode</span><span class="o">=</span><span class="n">QuantMode</span><span class="p">(</span><span class="mi">0</span><span class="p">),</span>
<span class="n">inner_layernorm</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="mf">1e-05</span><span class="p">,</span>
<span class="n">is_expert</span><span class="o">=</span><span class="kc">False</span><span class="p">,</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">hidden_size</span> <span class="o">=</span> <span class="n">hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ffn_hidden_size</span> <span class="o">=</span> <span class="n">ffn_hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">=</span> <span class="n">hidden_act</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="n">bias</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dtype</span> <span class="o">=</span> <span class="n">dtype</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_group</span> <span class="o">=</span> <span class="n">tp_group</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">=</span> <span class="n">tp_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">quant_mode</span> <span class="o">=</span> <span class="n">quant_mode</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span> <span class="o">=</span> <span class="n">ColumnLinear</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="bp">self</span><span class="o">.</span><span class="n">ffn_hidden_size</span> <span class="o">*</span> <span class="mi">2</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="bp">self</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="bp">self</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="bp">self</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">False</span><span class="p">,</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span> <span class="o">=</span> <span class="n">LayerNorm</span><span class="p">(</span><span class="n">ffn_hidden_size</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="n">eps</span><span class="p">)</span> <span class="k">if</span> <span class="n">inner_layernorm</span> <span class="k">else</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">proj</span> <span class="o">=</span> <span class="n">RowLinear</span><span class="p">(</span><span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">hidden_size</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">is_expert</span><span class="o">=</span><span class="n">is_expert</span><span class="p">)</span>
<span class="c1"># see optimize_model&#39;s add_lora for LoRA initialization</span>
<span class="bp">self</span><span class="o">.</span><span class="n">lora</span> <span class="o">=</span> <span class="kc">None</span> <span class="c1"># used for split up and gate proj</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fused_gate_up_lora</span> <span class="o">=</span> <span class="kc">None</span> <span class="c1"># used for merged up_gate proj</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dora</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fused_gate_up_dora</span> <span class="o">=</span> <span class="kc">None</span>
<div class="viewcode-block" id="FusedGatedMLP.fc_gate_plugin">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.FusedGatedMLP.fc_gate_plugin">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">fc_gate_plugin</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">lora_layer_params</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="c1"># Combine the following pattern</span>
<span class="c1">#</span>
<span class="c1"># SiLU(FC(x)) * Gate(x)</span>
<span class="c1">#</span>
<span class="c1"># into:</span>
<span class="c1">#</span>
<span class="c1"># SwiGLU(FusedFC(x))</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">low_latency_gemm_swiglu_plugin</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">p_dtype</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">low_latency_gemm_swiglu_plugin</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">p_dtype</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">gemm_swiglu_plugin</span>
<span class="n">use_fp8</span> <span class="o">=</span> <span class="n">p_dtype</span> <span class="o">==</span> <span class="s1">&#39;fp8&#39;</span>
<span class="k">assert</span> <span class="n">use_fp8</span><span class="p">,</span> <span class="s2">&quot;gemm_swiglu_plugin and low_latency_gemm_swiglu_plugin only supports fp8 now&quot;</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_h_to_4h&quot;</span><span class="p">)</span>
<span class="n">mlp_gate_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_gate&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">mlp_fc_lora_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">mlp_gate_lora_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;LoRA of splitting fc and gate is not yet implemented for gemm_swiglu_plugin&quot;</span>
<span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">!=</span> <span class="s1">&#39;silu&#39;</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Activation </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="si">}</span><span class="s2"> not yet implemented for gemm_swiglu_plugin&quot;</span>
<span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">bias</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;bias not yet implemented for gemm_swiglu_plugin fp8&quot;</span><span class="p">)</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span><span class="p">,</span>
<span class="n">FP8Linear</span><span class="p">),</span> <span class="s2">&quot;fp8 gemm_swiglu only supports fp8 weights&quot;</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">proj</span><span class="p">,</span>
<span class="n">FP8RowLinear</span><span class="p">),</span> <span class="s2">&quot;fp8 gemm_swiglu only supports fp8 weights&quot;</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">shape</span> <span class="o">==</span> <span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">ffn_hidden_size</span> <span class="o">*</span> <span class="mi">2</span> <span class="o">//</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span><span class="p">),</span> <span class="s2">&quot;fp8 gemm_swiglu only supports (k, n) weights&quot;</span>
<span class="n">scale_d0</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span><span class="o">.</span><span class="n">weights_scaling_factor</span><span class="o">.</span><span class="n">raw_value</span><span class="o">.</span><span class="n">item</span><span class="p">()</span> <span class="o">*</span>
<span class="bp">self</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">item</span><span class="p">())</span>
<span class="n">scale_d1</span> <span class="o">=</span> <span class="n">scale_d0</span>
<span class="n">scale_output</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">proj</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">item</span><span class="p">(</span>
<span class="p">)</span>
<span class="n">activation_scaling_factor</span> <span class="o">=</span> <span class="n">cast</span><span class="p">(</span>
<span class="bp">self</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">value</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<span class="k">if</span> <span class="n">hidden_states</span><span class="o">.</span><span class="n">dtype</span> <span class="o">!=</span> <span class="n">trt</span><span class="o">.</span><span class="n">fp8</span><span class="p">:</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">quantize</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">activation_scaling_factor</span><span class="p">,</span>
<span class="s1">&#39;fp8&#39;</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">low_latency_gemm_swiglu_plugin</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">low_latency_gemm_swiglu</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">fused_fc</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_d0</span><span class="p">,</span> <span class="n">scale_d1</span><span class="p">,</span> <span class="n">scale_output</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">gemm_swiglu</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">fused_fc</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="kc">None</span><span class="p">,</span>
<span class="n">scale_d0</span><span class="p">,</span> <span class="n">scale_d1</span><span class="p">,</span> <span class="n">scale_output</span><span class="p">)</span>
<span class="n">lora_result</span> <span class="o">=</span> <span class="n">fc_gate_lora</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">lora</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fused_gate_up_lora</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="p">)</span>
<span class="k">if</span> <span class="n">lora_result</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">inter</span> <span class="o">+</span> <span class="n">lora_result</span>
<span class="k">return</span> <span class="n">inter</span></div>
<div class="viewcode-block" id="FusedGatedMLP.fc_gate">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.FusedGatedMLP.fc_gate">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">fc_gate</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">lora_layer_params</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="c1"># Combine the following pattern</span>
<span class="c1">#</span>
<span class="c1"># SiLU(FC(x)) * Gate(x)</span>
<span class="c1">#</span>
<span class="c1"># into:</span>
<span class="c1">#</span>
<span class="c1"># SwiGLU(FusedFC(x))</span>
<span class="c1">#</span>
<span class="c1"># Upside is we don&#39;t need to modify 4 different weight loading paths just to concat weights</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">lora_result</span> <span class="o">=</span> <span class="n">fc_gate_lora</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">lora</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fused_gate_up_lora</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="p">)</span>
<span class="k">if</span> <span class="n">lora_result</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">inter</span> <span class="o">+</span> <span class="n">lora_result</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">dora</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">fc_gate_dora</span><span class="p">(</span><span class="n">inter</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dora</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">fused_gate_up_lora</span><span class="p">,</span>
<span class="n">lora_layer_params</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">==</span> <span class="s1">&#39;silu&#39;</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="s1">&#39;swiglu&#39;</span><span class="p">](</span><span class="n">inter</span><span class="p">)</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">==</span> <span class="s1">&#39;gelu&#39;</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="s1">&#39;geglu&#39;</span><span class="p">](</span><span class="n">inter</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Activation </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="si">}</span><span class="s2"> not yet implemented for </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="si">}</span><span class="s2">.&quot;</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">inter</span></div>
<div class="viewcode-block" id="FusedGatedMLP.forward">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.FusedGatedMLP.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">hidden_states</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">all_reduce_params</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">AllReduceParams</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
<span class="k">if</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">gemm_swiglu_plugin</span> <span class="ow">or</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">low_latency_gemm_swiglu_plugin</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc_gate_plugin</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc_gate</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span><span class="p">(</span><span class="n">inter</span><span class="p">)</span>
<span class="n">mlp_proj_lora_params</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_proj_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_4h_to_h&quot;</span><span class="p">)</span>
<span class="n">output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">proj</span><span class="p">(</span><span class="n">inter</span><span class="p">,</span>
<span class="n">lora_runtime_params</span><span class="o">=</span><span class="n">mlp_proj_lora_params</span><span class="p">,</span>
<span class="n">all_reduce_params</span><span class="o">=</span><span class="n">all_reduce_params</span><span class="p">)</span>
<span class="k">return</span> <span class="n">output</span></div>
</div>
<div class="viewcode-block" id="LinearGELU">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.LinearGELU">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">LinearGELU</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">dim_in</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">dim_out</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">approximate</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s1">&#39;tanh&#39;</span><span class="p">,</span>
<span class="n">bias</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">mapping</span><span class="o">=</span><span class="n">Mapping</span><span class="p">(),</span>
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">proj</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span><span class="n">dim_in</span><span class="p">,</span>
<span class="n">dim_out</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">)</span>
<span class="k">if</span> <span class="n">approximate</span> <span class="o">!=</span> <span class="s1">&#39;tanh&#39;</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s1">&#39;GELU only support tanh now.&#39;</span><span class="p">)</span>
<div class="viewcode-block" id="LinearGELU.forward">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.LinearGELU.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">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">proj</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="s1">&#39;gelu_pytorch_tanh&#39;</span><span class="p">](</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="k">return</span> <span class="n">hidden_states</span></div>
</div>
<div class="viewcode-block" id="LinearGEGLU">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.LinearGEGLU">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">LinearGEGLU</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">dim_in</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">dim_out</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">approximate</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s1">&#39;tanh&#39;</span><span class="p">,</span>
<span class="n">bias</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">mapping</span><span class="o">=</span><span class="n">Mapping</span><span class="p">(),</span>
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">proj</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span><span class="n">dim_in</span><span class="p">,</span>
<span class="n">dim_out</span> <span class="o">*</span> <span class="mi">2</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">)</span>
<span class="k">if</span> <span class="n">approximate</span> <span class="o">!=</span> <span class="s1">&#39;tanh&#39;</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s1">&#39;GELU only support tanh now.&#39;</span><span class="p">)</span>
<div class="viewcode-block" id="LinearGEGLU.forward">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.LinearGEGLU.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">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">proj</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">hidden_states</span><span class="p">,</span> <span class="n">gate</span> <span class="o">=</span> <span class="n">chunk</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="mi">2</span><span class="p">,</span>
<span class="n">dim</span><span class="o">=</span><span class="p">(</span><span class="n">hidden_states</span><span class="o">.</span><span class="n">ndim</span><span class="p">()</span> <span class="o">-</span> <span class="mi">1</span><span class="p">))</span>
<span class="k">return</span> <span class="n">hidden_states</span> <span class="o">*</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="s1">&#39;gelu_pytorch_tanh&#39;</span><span class="p">](</span><span class="n">gate</span><span class="p">)</span></div>
</div>
<div class="viewcode-block" id="LinearApproximateGELU">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.LinearApproximateGELU">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">LinearApproximateGELU</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">dim_in</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">dim_out</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">bias</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">mapping</span><span class="o">=</span><span class="n">Mapping</span><span class="p">(),</span>
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">proj</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span><span class="n">dim_in</span><span class="p">,</span>
<span class="n">dim_out</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">)</span>
<div class="viewcode-block" id="LinearApproximateGELU.forward">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.LinearApproximateGELU.forward">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">proj</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span> <span class="o">*</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="s1">&#39;sigmoid&#39;</span><span class="p">](</span><span class="mf">1.702</span> <span class="o">*</span> <span class="n">x</span><span class="p">)</span></div>
</div>
<div class="viewcode-block" id="LinearSwiGLU">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.LinearSwiGLU">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">LinearSwiGLU</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">dim_in</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">dim_out</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">bias</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">mapping</span><span class="o">=</span><span class="n">Mapping</span><span class="p">(),</span>
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">proj</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span><span class="n">dim_in</span><span class="p">,</span>
<span class="n">dim_out</span> <span class="o">*</span> <span class="mi">2</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">=</span> <span class="s1">&#39;silu&#39;</span>
<div class="viewcode-block" id="LinearSwiGLU.forward">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.LinearSwiGLU.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">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">proj</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">hidden_states</span><span class="p">,</span> <span class="n">gate</span> <span class="o">=</span> <span class="n">chunk</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span>
<span class="mi">2</span><span class="p">,</span>
<span class="n">dim</span><span class="o">=</span><span class="p">(</span><span class="n">hidden_states</span><span class="o">.</span><span class="n">ndim</span><span class="p">()</span> <span class="o">-</span> <span class="mi">1</span><span class="p">))</span>
<span class="k">return</span> <span class="n">hidden_states</span> <span class="o">*</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="p">](</span><span class="n">gate</span><span class="p">)</span></div>
</div>
<div class="viewcode-block" id="LinearActivation">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.LinearActivation">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">LinearActivation</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">dim_in</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">dim_out</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">bias</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
<span class="n">activation</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;silu&quot;</span><span class="p">,</span>
<span class="n">mapping</span><span class="o">=</span><span class="n">Mapping</span><span class="p">(),</span>
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">proj</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span><span class="n">dim_in</span><span class="p">,</span>
<span class="n">dim_out</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">=</span> <span class="n">activation</span>
<div class="viewcode-block" id="LinearActivation.forward">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.LinearActivation.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">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">proj</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="k">return</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">activation</span><span class="p">](</span><span class="n">hidden_states</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 06, 2025.</p>
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/a16ba64">a16ba64</a>.</p>
</div></div>
</div>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink