mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
1117 lines
97 KiB
HTML
1117 lines
97 KiB
HTML
|
||
|
||
<!DOCTYPE html>
|
||
|
||
|
||
<html lang="en" data-content_root="../../../" >
|
||
|
||
<head>
|
||
<meta charset="utf-8" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||
<title>tensorrt_llm.quantization.mode — TensorRT LLM</title>
|
||
|
||
|
||
|
||
<script data-cfasync="false">
|
||
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
|
||
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
|
||
</script>
|
||
<!--
|
||
this give us a css class that will be invisible only if js is disabled
|
||
-->
|
||
<noscript>
|
||
<style>
|
||
.pst-js-only { display: none !important; }
|
||
|
||
</style>
|
||
</noscript>
|
||
|
||
<!-- Loaded before other Sphinx assets -->
|
||
<link href="../../../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
|
||
<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
|
||
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=8f2a1f02" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/styles/nvidia-sphinx-theme.css?v=933278ad" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css?v=76b2166b" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/autodoc_pydantic.css" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/togglebutton.css?v=13237357" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/custom.css?v=19d20f17" />
|
||
|
||
<!-- So that users can add custom icons -->
|
||
<script src="../../../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script>
|
||
<!-- Pre-loaded scripts that we'll load fully later -->
|
||
<link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" />
|
||
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" />
|
||
|
||
|
||
|
||
<script src="../../../_static/documentation_options.js?v=5929fcd5"></script>
|
||
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
|
||
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||
<script src="../../../_static/clipboard.min.js?v=a7894cd8"></script>
|
||
<script src="../../../_static/copybutton.js?v=65e89d2a"></script>
|
||
<script>let toggleHintShow = 'Click to show';</script>
|
||
<script>let toggleHintHide = 'Click to hide';</script>
|
||
<script>let toggleOpenOnPrint = 'true';</script>
|
||
<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
|
||
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
|
||
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
|
||
<script>DOCUMENTATION_OPTIONS.pagename = '_modules/tensorrt_llm/quantization/mode';</script>
|
||
<script>
|
||
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.2.0rc4';
|
||
DOCUMENTATION_OPTIONS.show_version_warning_banner =
|
||
false;
|
||
</script>
|
||
|
||
<link rel="icon" href="../../../_static/favicon.png"/>
|
||
|
||
<link rel="index" title="Index" href="../../../genindex.html" />
|
||
<link rel="search" title="Search" href="../../../search.html" />
|
||
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
||
<meta name="docsearch:language" content="en"/>
|
||
<meta name="docsearch:version" content="1.2.0rc4" />
|
||
|
||
|
||
</head>
|
||
|
||
|
||
|
||
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
|
||
|
||
|
||
|
||
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
|
||
|
||
|
||
|
||
<div id="pst-scroll-pixel-helper"></div>
|
||
|
||
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
|
||
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
|
||
|
||
|
||
<dialog id="pst-search-dialog">
|
||
|
||
<form class="bd-search d-flex align-items-center"
|
||
action="../../../search.html"
|
||
method="get">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<input type="search"
|
||
class="form-control"
|
||
name="q"
|
||
placeholder="Search the docs ..."
|
||
aria-label="Search the docs ..."
|
||
autocomplete="off"
|
||
autocorrect="off"
|
||
autocapitalize="off"
|
||
spellcheck="false"/>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
|
||
</form>
|
||
</dialog>
|
||
|
||
<div class="pst-async-banner-revealer d-none">
|
||
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
|
||
</div>
|
||
|
||
|
||
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
|
||
<div class="bd-header__inner bd-page-width">
|
||
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
|
||
<span class="fa-solid fa-bars"></span>
|
||
</button>
|
||
|
||
|
||
<div class="col-lg-3 navbar-header-items__start">
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
|
||
|
||
|
||
<a class="navbar-brand logo" href="../../../index.html">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<img src="../../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT LLM - Home"/>
|
||
<img src="../../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT LLM - Home"/>
|
||
|
||
|
||
<p class="title logo__title">TensorRT LLM</p>
|
||
|
||
</a></div>
|
||
|
||
</div>
|
||
|
||
<div class="col-lg-9 navbar-header-items">
|
||
|
||
<div class="me-auto navbar-header-items__center">
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
<div class="version-switcher__container dropdown pst-js-only">
|
||
<button id="pst-version-switcher-button-2"
|
||
type="button"
|
||
class="version-switcher__button btn btn-sm dropdown-toggle"
|
||
data-bs-toggle="dropdown"
|
||
aria-haspopup="listbox"
|
||
aria-controls="pst-version-switcher-list-2"
|
||
aria-label="Version switcher list"
|
||
>
|
||
Choose version <!-- this text may get changed later by javascript -->
|
||
<span class="caret"></span>
|
||
</button>
|
||
<div id="pst-version-switcher-list-2"
|
||
class="version-switcher__menu dropdown-menu list-group-flush py-0"
|
||
role="listbox" aria-labelledby="pst-version-switcher-button-2">
|
||
<!-- dropdown will be populated by javascript on page load -->
|
||
</div>
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="navbar-header-items__end">
|
||
|
||
<div class="navbar-item navbar-persistent--container">
|
||
|
||
|
||
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
</div>
|
||
|
||
|
||
<div class="navbar-item">
|
||
|
||
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
||
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
||
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
||
</button></div>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="navbar-persistent--mobile">
|
||
|
||
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
</header>
|
||
|
||
|
||
<div class="bd-container">
|
||
<div class="bd-container__inner bd-page-width">
|
||
|
||
|
||
|
||
<dialog id="pst-primary-sidebar-modal"></dialog>
|
||
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<a class="navbar-brand logo" href="../../../index.html">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<img src="../../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT LLM - Home"/>
|
||
<img src="../../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT LLM - Home"/>
|
||
|
||
|
||
<p class="title logo__title">TensorRT LLM</p>
|
||
|
||
</a>
|
||
|
||
|
||
|
||
<div class="sidebar-header-items sidebar-primary__section">
|
||
|
||
|
||
<div class="sidebar-header-items__center">
|
||
|
||
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
<div class="version-switcher__container dropdown pst-js-only">
|
||
<button id="pst-version-switcher-button-3"
|
||
type="button"
|
||
class="version-switcher__button btn btn-sm dropdown-toggle"
|
||
data-bs-toggle="dropdown"
|
||
aria-haspopup="listbox"
|
||
aria-controls="pst-version-switcher-list-3"
|
||
aria-label="Version switcher list"
|
||
>
|
||
Choose version <!-- this text may get changed later by javascript -->
|
||
<span class="caret"></span>
|
||
</button>
|
||
<div id="pst-version-switcher-list-3"
|
||
class="version-switcher__menu dropdown-menu list-group-flush py-0"
|
||
role="listbox" aria-labelledby="pst-version-switcher-button-3">
|
||
<!-- dropdown will be populated by javascript on page load -->
|
||
</div>
|
||
</div></div>
|
||
|
||
|
||
</div>
|
||
|
||
|
||
|
||
<div class="sidebar-header-items__end">
|
||
|
||
<div class="navbar-item">
|
||
|
||
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
||
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
||
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
||
</button></div>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
|
||
<div class="sidebar-primary-items__start sidebar-primary__section">
|
||
<div class="sidebar-primary-item">
|
||
|
||
|
||
|
||
<nav class="bd-docs-nav bd-links"
|
||
aria-label="Table of Contents">
|
||
<p class="bd-links__title" role="heading" aria-level="1">Table of Contents</p>
|
||
<div class="bd-toc-item navbar-nav"><p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../overview.html">Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../quick-start-guide.html">Quick Start Guide</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../installation/index.html">Installation</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../installation/containers.html">Pre-built release container images on NGC</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../installation/linux.html">Installing on Linux via <code class="docutils literal notranslate"><span class="pre">pip</span></code></a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Deployment Guide</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../examples/llm_api_examples.html">LLM Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference.html">Generate text</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_async.html">Generate text asynchronously</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_async_streaming.html">Generate text in streaming</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_logits_processor.html">Control generated text using logits processor</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_sparse_attention.html">Sparse Attention</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_speculative_decoding.html">Speculative Decoding</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_kv_cache_connector.html">KV Cache Connector</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_kv_cache_offloading.html">KV Cache Offloading</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_runtime.html">Runtime Configuration Examples</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_sampling.html">Sampling Techniques Showcase</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_llm_distributed.html">Run LLM-API with pytorch backend on Slurm</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_trtllm_bench.html">Run trtllm-bench with pytorch backend on Slurm</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_trtllm_serve.html">Run trtllm-serve with pytorch backend on Slurm</a></li>
|
||
</ul>
|
||
</details></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../examples/trtllm_serve_examples.html">Online Serving Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/curl_chat_client.html">Curl Chat Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/curl_completion_client.html">Curl Completion Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/genai_perf_client.html">Genai Perf Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/genai_perf_client_for_multimodal.html">Genai Perf Client For Multimodal</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_chat_client.html">OpenAI Chat Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_chat_client_for_multimodal.html">OpenAI Chat Client for Multimodal</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client_for_lora.html">Openai Completion Client For Lora</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client_json_schema.html">OpenAI Completion Client with JSON Schema</a></li>
|
||
</ul>
|
||
</details></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../examples/dynamo_k8s_example.html">Dynamo K8s Example</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../deployment-guide/index.html">Model Recipes</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/deployment-guide-for-deepseek-r1-on-trtllm.html">Deployment Guide for DeepSeek R1 on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/deployment-guide-for-llama3.3-70b-on-trtllm.html">Deployment Guide for Llama3.3 70B on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/deployment-guide-for-llama4-scout-on-trtllm.html">Deployment Guide for Llama4 Scout 17B on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/deployment-guide-for-gpt-oss-on-trtllm.html">Deployment Guide for GPT-OSS on TensorRT-LLM - Blackwell Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../deployment-guide/deployment-guide-for-qwen3-next-on-trtllm.html">Deployment Guide for Qwen3 Next on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Models</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../models/supported-models.html">Supported Models</a></li>
|
||
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../models/adding-new-model.html">Adding a New Model</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">CLI Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-bench.html">trtllm-bench</a></li>
|
||
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-eval.html">trtllm-eval</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../commands/trtllm-serve/index.html">trtllm-serve</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../commands/trtllm-serve/trtllm-serve.html">trtllm-serve</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../commands/trtllm-serve/run-benchmark-with-trtllm-serve.html">Run benchmarking with <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code></a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">API Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api/index.html">LLM API Introduction</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api/reference.html">API Reference</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Features</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/feature-combination-matrix.html">Feature Combination Matrix</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/disagg-serving.html">Disaggregated Serving</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/kvcache.html">KV Cache System</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/long-sequence.html">Long Sequences</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/lora.html">LoRA (Low-Rank Adaptation)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/multi-modality.html">Multimodal Support in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/overlap-scheduler.html">Overlap Scheduler</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/paged-attention-ifb-scheduler.html">Paged Attention, IFB, and Request Scheduling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/parallel-strategy.html">Parallelism in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/quantization.html">Quantization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/sampling.html">Sampling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/additional-outputs.html">Additional Outputs</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/speculative-decoding.html">Speculative Decoding</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/checkpoint-loading.html">Checkpoint Loading</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/auto_deploy/auto-deploy.html">AutoDeploy (Prototype)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/ray-orchestrator.html">Ray Orchestrator (Prototype)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../features/torch_compile_and_piecewise_cuda_graph.html">Torch Compile & Piecewise CUDA Graph</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Developer Guide</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/overview.html">Architecture Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/perf-analysis.html">Performance Analysis</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/perf-benchmarking.html">TensorRT LLM Benchmarking</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/ci-overview.html">Continuous Integration Overview</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/dev-containers.html">Using Dev Containers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/api-change.html">LLM API Change Guide</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../developer-guide/kv-transfer.html">Introduction to KV Cache Transmission</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog10_ADP_Balance_Strategy.html">ADP Balance Strategy</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog11_GPT_OSS_Eagle3.html">Running GPT-OSS-120B with Eagle3 Speculative Decoding on GB200/B200 (TensorRT LLM)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog12_Combining_Guided_Decoding_and_Speculative_Decoding.html">Combining Guided Decoding and Speculative Decoding: Making CPU and GPU Cooperate Seamlessly</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog13_Inference_Time_Compute_Implementation_in_TensorRT-LLM.html">Inference Time Compute Implementation in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog14_Scaling_Expert_Parallelism_in_TensorRT-LLM_part3.html">Scaling Expert Parallelism in TensorRT LLM (Part 3: Pushing the Performance Boundary)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html">Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html">DeepSeek R1 MTP Implementation and Optimization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog3_Optimizing_DeepSeek_R1_Throughput_on_NVIDIA_Blackwell_GPUs.html">Optimizing DeepSeek R1 Throughput on NVIDIA Blackwell GPUs: A Deep Dive for Developers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog4_Scaling_Expert_Parallelism_in_TensorRT-LLM.html">Scaling Expert Parallelism in TensorRT LLM (Part 1: Design and Implementation of Large-scale EP)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog5_Disaggregated_Serving_in_TensorRT-LLM.html">Disaggregated Serving in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog6_Llama4_maverick_eagle_guide.html">How to launch Llama4 Maverick + Eagle3 TensorRT LLM server</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog7_NGram_performance_Analysis_And_Auto_Enablement.html">N-Gram Speculative Decoding in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog8_Scaling_Expert_Parallelism_in_TensorRT-LLM_part2.html">Scaling Expert Parallelism in TensorRT LLM (Part 2: Performance Status and Optimization)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.html">Running a High Performance GPT-OSS-120B Inference Server with TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/Best_perf_practice_on_DeepSeek-R1_in_TensorRT-LLM.html">How to get best performance on DeepSeek-R1 in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Quick Links</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/releases">Releases</a></li>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM">Github Code</a></li>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/issues?q=is%3Aissue%20state%3Aopen%20label%3Aroadmap">Roadmap</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Use TensorRT Engine</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../legacy/tensorrt_quickstart.html">LLM API with TensorRT Engine</a></li>
|
||
</ul>
|
||
</div>
|
||
</nav></div>
|
||
</div>
|
||
|
||
|
||
<div class="sidebar-primary-items__end sidebar-primary__section">
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
<main id="main-content" class="bd-main" role="main">
|
||
|
||
|
||
<div class="bd-content">
|
||
<div class="bd-article-container">
|
||
|
||
<div class="bd-header-article d-print-none">
|
||
<div class="header-article-items header-article__inner">
|
||
|
||
<div class="header-article-items__start">
|
||
|
||
<div class="header-article-item">
|
||
|
||
<nav aria-label="Breadcrumb" class="d-print-none">
|
||
<ul class="bd-breadcrumbs">
|
||
|
||
<li class="breadcrumb-item breadcrumb-home">
|
||
<a href="../../../index.html" class="nav-link" aria-label="Home">
|
||
<i class="fa-solid fa-home"></i>
|
||
</a>
|
||
</li>
|
||
|
||
<li class="breadcrumb-item"><a href="../../index.html" class="nav-link">Module code</a></li>
|
||
|
||
<li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">tensorrt_llm.quantization.mode</span></li>
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<div id="searchbox"></div>
|
||
<article class="bd-article">
|
||
|
||
<h1>Source code for tensorrt_llm.quantization.mode</h1><div class="highlight"><pre>
|
||
<span></span><span class="c1"># SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.</span>
|
||
<span class="c1"># SPDX-License-Identifier: Apache-2.0</span>
|
||
<span class="c1">#</span>
|
||
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
||
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
||
<span class="c1"># You may obtain a copy of the License at</span>
|
||
<span class="c1">#</span>
|
||
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
||
<span class="c1">#</span>
|
||
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
||
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
||
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
||
<span class="c1"># See the License for the specific language governing permissions and</span>
|
||
<span class="c1"># limitations under the License.</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">enum</span><span class="w"> </span><span class="kn">import</span> <span class="n">IntFlag</span><span class="p">,</span> <span class="n">auto</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">from</span><span class="w"> </span><span class="nn">strenum</span><span class="w"> </span><span class="kn">import</span> <span class="n">StrEnum</span>
|
||
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">.._utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">BaseEnumMeta</span>
|
||
|
||
|
||
<div class="viewcode-block" id="QuantAlgo">
|
||
<a class="viewcode-back" href="../../../llm-api/reference.html#tensorrt_llm.quantization.QuantAlgo">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">QuantAlgo</span><span class="p">(</span><span class="n">StrEnum</span><span class="p">,</span> <span class="n">metaclass</span><span class="o">=</span><span class="n">BaseEnumMeta</span><span class="p">):</span>
|
||
<span class="n">W8A16</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W4A16</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W4A16_AWQ</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W4A8_AWQ</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W8A16_GPTQ</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W4A16_GPTQ</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W8A8_SQ_PER_CHANNEL</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W8A8_SQ_PER_TENSOR_PLUGIN</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W4A8_QSERVE_PER_GROUP</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W4A8_QSERVE_PER_CHANNEL</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">FP8</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">FP8_PER_CHANNEL_PER_TOKEN</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">FP8_BLOCK_SCALES</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">INT8</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">MIXED_PRECISION</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">NVFP4</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W4A8_NVFP4_FP8</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W4A8_MXFP4_FP8</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W4A8_MXFP4_MXFP8</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W4A16_MXFP4</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">NO_QUANT</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span></div>
|
||
|
||
|
||
|
||
<span class="n">QUANT_ALGO_LIST</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">set</span><span class="p">(</span><span class="n">QuantAlgo</span><span class="p">)</span> <span class="o">-</span> <span class="p">{</span><span class="n">QuantAlgo</span><span class="o">.</span><span class="n">INT8</span><span class="p">})</span>
|
||
<span class="n">KV_CACHE_QUANT_ALGO_LIST</span> <span class="o">=</span> <span class="p">[</span><span class="n">QuantAlgo</span><span class="o">.</span><span class="n">FP8</span><span class="p">,</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">INT8</span><span class="p">,</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">NVFP4</span><span class="p">]</span>
|
||
<span class="n">W8A8_SQ_PLUGIN_LIST</span> <span class="o">=</span> <span class="p">[</span>
|
||
<span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W8A8_SQ_PER_TENSOR_PLUGIN</span><span class="p">,</span>
|
||
<span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN</span><span class="p">,</span>
|
||
<span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN</span><span class="p">,</span>
|
||
<span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN</span><span class="p">,</span>
|
||
<span class="p">]</span>
|
||
<span class="n">MODELOPT_FLOW_QUANTIZATIONS</span> <span class="o">=</span> <span class="p">{</span>
|
||
<span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A16_AWQ</span><span class="p">,</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">FP8</span><span class="p">,</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W8A8_SQ_PER_CHANNEL</span><span class="p">,</span>
|
||
<span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A8_AWQ</span>
|
||
<span class="p">}</span>
|
||
|
||
|
||
<div class="viewcode-block" id="QuantMode">
|
||
<a class="viewcode-back" href="../../../legacy/python-api/tensorrt_llm.quantization.html#tensorrt_llm.quantization.QuantMode">[docs]</a>
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">QuantMode</span><span class="p">(</span><span class="n">IntFlag</span><span class="p">):</span>
|
||
<span class="c1"># [WARNING] KEEP BELOW DEFINITION IN SYNC WITH cpp/tensorrt_llm/common/quantization.h</span>
|
||
|
||
<span class="c1"># The weights are quantized to 4 bits.</span>
|
||
<span class="n">INT4_WEIGHTS</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># The weights are quantized to 8 bits.</span>
|
||
<span class="n">INT8_WEIGHTS</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># The activations are quantized.</span>
|
||
<span class="n">ACTIVATIONS</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># The method uses one scaling factor per channel. It's pre-computed (static) from the weights.</span>
|
||
<span class="n">PER_CHANNEL</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># The method uses one scaling factor per token. It's computed on-the-fly.</span>
|
||
<span class="n">PER_TOKEN</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># The method uses one scaling factor per group. It's pre-computed (static) from the weights.</span>
|
||
<span class="n">PER_GROUP</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># The KV cache is quantized in INT8.</span>
|
||
<span class="n">INT8_KV_CACHE</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># The KV cache is quantized in FP8.</span>
|
||
<span class="n">FP8_KV_CACHE</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># FP8 QDQ</span>
|
||
<span class="n">FP8_QDQ</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># FP8 rowwise</span>
|
||
<span class="n">FP8_ROWWISE</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># FP8 block scales for Deepseek</span>
|
||
<span class="n">FP8_1x128_128x128</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># W4A8 qserve</span>
|
||
<span class="n">W4A8_QSERVE</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># FP4</span>
|
||
<span class="n">NVFP4</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">NVFP4_KV_CACHE</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># W4A8 NVFP4</span>
|
||
<span class="n">W4A8_NVFP4_FP8</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="c1"># W4A8 MXFP4</span>
|
||
<span class="n">W4A8_MXFP4_FP8</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W4A8_MXFP4_MXFP8</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
<span class="n">W4A16_MXFP4</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
|
||
<span class="c1"># The smallest power-of-two that is not used by a flag. Do not call auto() after that line.</span>
|
||
<span class="n">COUNT</span> <span class="o">=</span> <span class="n">auto</span><span class="p">()</span>
|
||
|
||
<span class="c1"># Bitmask to detect if weights, activations or both are quantized.</span>
|
||
<span class="n">WEIGHTS_AND_ACTIVATIONS</span> <span class="o">=</span> <span class="n">INT4_WEIGHTS</span> <span class="o">|</span> <span class="n">INT8_WEIGHTS</span> <span class="o">|</span> <span class="n">ACTIVATIONS</span>
|
||
<span class="c1"># The mask of all valid flags.</span>
|
||
<span class="n">VALID_FLAGS</span> <span class="o">=</span> <span class="n">COUNT</span> <span class="o">-</span> <span class="mi">1</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">__deepcopy__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">memo</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span>
|
||
|
||
<span class="c1"># All the bits set? You can restrict the test to the bits indicated by "mask".</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">_all</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bits</span><span class="p">,</span> <span class="n">mask</span><span class="o">=</span><span class="n">VALID_FLAGS</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="p">(</span><span class="bp">self</span> <span class="o">&</span> <span class="n">mask</span><span class="p">)</span> <span class="o">==</span> <span class="n">bits</span>
|
||
|
||
<span class="c1"># Is one of the bits of the mask set?</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">_any</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bits</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="p">(</span><span class="bp">self</span> <span class="o">&</span> <span class="n">bits</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">0</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">is_int8_weight_only</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_all</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">INT8_WEIGHTS</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">WEIGHTS_AND_ACTIVATIONS</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">is_int4_weight_only</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_all</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">INT4_WEIGHTS</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">WEIGHTS_AND_ACTIVATIONS</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">is_weight_only</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_int4_weight_only</span><span class="p">()</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_int8_weight_only</span><span class="p">()</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">is_int8_weight_only_per_group</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_int8_weight_only</span><span class="p">()</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">PER_GROUP</span><span class="p">)</span>
|
||
|
||
<span class="c1"># TODO: Using the current flags cannot distinguish between w4aFP8 AWQ and w4a8 QServe.</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">is_qserve_w4a8</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">W4A8_QSERVE</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">is_int4_weight_only_per_group</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_int4_weight_only</span><span class="p">()</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">PER_GROUP</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_act_and_weight_quant</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_all</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">INT8_WEIGHTS</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">ACTIVATIONS</span><span class="p">,</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">WEIGHTS_AND_ACTIVATIONS</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_act_or_weight_quant</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">INT4_WEIGHTS</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">INT8_WEIGHTS</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">ACTIVATIONS</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_per_token_dynamic_scaling</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">PER_TOKEN</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_fp8_block_scales</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">FP8_1x128_128x128</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_act_static_scaling</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">has_per_token_dynamic_scaling</span><span class="p">(</span>
|
||
<span class="p">)</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">has_fp8_rowwise</span><span class="p">()</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_per_channel_scaling</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">PER_CHANNEL</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_per_group_scaling</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">PER_GROUP</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_int8_kv_cache</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">INT8_KV_CACHE</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_fp8_kv_cache</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">FP8_KV_CACHE</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_fp4_kv_cache</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">NVFP4_KV_CACHE</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_kv_cache_quant</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">has_int8_kv_cache</span><span class="p">()</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">has_fp8_kv_cache</span><span class="p">()</span>
|
||
<span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">has_fp4_kv_cache</span><span class="p">())</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_fp8_qdq</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">FP8_QDQ</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_fp8_rowwise</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">FP8_ROWWISE</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_nvfp4</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">NVFP4</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_w4a8_nvfp4_fp8</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">W4A8_NVFP4_FP8</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_w4a8_mxfp4_fp8</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">W4A8_MXFP4_FP8</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_w4a8_mxfp4_mxfp8</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">W4A8_MXFP4_MXFP8</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_w4a16_mxfp4</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">W4A16_MXFP4</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_mxfp4</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">W4A8_MXFP4_FP8</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">W4A8_MXFP4_MXFP8</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">W4A16_MXFP4</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_weight_quant</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">INT4_WEIGHTS</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">INT8_WEIGHTS</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">has_any_quant</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">exclude_kv_cache</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">):</span>
|
||
<span class="n">has_quant</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">INT4_WEIGHTS</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">INT8_WEIGHTS</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">ACTIVATIONS</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">FP8_QDQ</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">FP8_ROWWISE</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">W4A8_QSERVE</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">FP8_1x128_128x128</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">NVFP4</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">W4A8_NVFP4_FP8</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">W4A8_MXFP4_FP8</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">W4A16_MXFP4</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">W4A8_MXFP4_MXFP8</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">exclude_kv_cache</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="n">has_quant</span>
|
||
|
||
<span class="k">return</span> <span class="n">has_quant</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">_any</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">INT8_KV_CACHE</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">FP8_KV_CACHE</span>
|
||
<span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">NVFP4_KV_CACHE</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_int8_kv_cache</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">INT8_KV_CACHE</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_fp8_kv_cache</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">FP8_KV_CACHE</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_fp4_kv_cache</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">NVFP4_KV_CACHE</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_fp8_qdq</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">FP8_QDQ</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">set_fp8_rowwise</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="bp">self</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">FP8_ROWWISE</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">PER_TOKEN</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">PER_CHANNEL</span>
|
||
|
||
<span class="nd">@staticmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">from_description</span><span class="p">(</span><span class="n">quantize_weights</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">quantize_activations</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">per_token</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">per_channel</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">per_group</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">use_int4_weights</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">use_int8_kv_cache</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">use_fp8_kv_cache</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">use_fp8_qdq</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">use_fp8_block_scales</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">use_fp8_rowwise</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">use_nvfp4</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">use_w4a8_nvfp4_fp8</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">use_w4a8_qserve</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">use_w4a8_mxfp4_fp8</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">use_w4a8_mxfp4_mxfp8</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">use_w4a16_mxfp4</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">raise_error</span><span class="p">():</span>
|
||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Unsupported combination of QuantMode args: "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">quantize_weights</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">quantize_activations</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">per_token</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">per_channel</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">per_group</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">use_int4_weights</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">use_int8_kv_cache</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">use_fp8_kv_cache</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">use_fp8_qdq</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">use_fp8_block_scales</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">use_fp8_rowwise</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">use_nvfp4</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">use_w4a8_qserve</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">use_w4a8_mxfp4_fp8</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">use_w4a8_mxfp4_mxfp8</span><span class="si">=}</span><span class="s2">, "</span>
|
||
<span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">use_w4a16_mxfp4</span><span class="si">=}</span><span class="s2">"</span><span class="p">)</span>
|
||
|
||
<span class="c1"># We must quantize weights when we quantize activations.</span>
|
||
<span class="k">if</span> <span class="n">quantize_activations</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">quantize_weights</span><span class="p">:</span>
|
||
<span class="n">raise_error</span><span class="p">()</span>
|
||
|
||
<span class="c1"># If we set per_token or per_channel, we must quantize both weights and activations.</span>
|
||
<span class="k">if</span> <span class="p">(</span><span class="n">per_token</span> <span class="ow">or</span> <span class="n">per_channel</span><span class="p">)</span> <span class="ow">and</span> <span class="ow">not</span> <span class="p">(</span><span class="n">quantize_weights</span>
|
||
<span class="ow">and</span> <span class="n">quantize_activations</span><span class="p">):</span>
|
||
<span class="n">raise_error</span><span class="p">()</span>
|
||
|
||
<span class="n">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="c1"># Do we quantize the weights - if so, do we use INT4 or INT8?</span>
|
||
<span class="k">if</span> <span class="n">quantize_weights</span> <span class="ow">and</span> <span class="n">use_int4_weights</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">INT4_WEIGHTS</span>
|
||
<span class="k">elif</span> <span class="n">quantize_weights</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">INT8_WEIGHTS</span>
|
||
|
||
<span class="c1"># Do we quantize the activations?</span>
|
||
<span class="k">if</span> <span class="n">quantize_activations</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">ACTIVATIONS</span>
|
||
|
||
<span class="c1"># Per-channel/per-token/per-group additional flags.</span>
|
||
<span class="k">if</span> <span class="n">per_channel</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">PER_CHANNEL</span>
|
||
<span class="k">if</span> <span class="n">per_token</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">PER_TOKEN</span>
|
||
<span class="k">if</span> <span class="n">per_group</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">PER_GROUP</span>
|
||
|
||
<span class="c1"># Int8 KV cache</span>
|
||
<span class="k">if</span> <span class="n">use_int8_kv_cache</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">INT8_KV_CACHE</span>
|
||
|
||
<span class="c1"># FP8 KV cache</span>
|
||
<span class="k">if</span> <span class="n">use_fp8_kv_cache</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">FP8_KV_CACHE</span>
|
||
|
||
<span class="k">if</span> <span class="n">use_fp8_qdq</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">FP8_QDQ</span>
|
||
|
||
<span class="k">if</span> <span class="n">use_fp8_rowwise</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">FP8_ROWWISE</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">PER_TOKEN</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">PER_CHANNEL</span>
|
||
|
||
<span class="k">if</span> <span class="n">use_fp8_block_scales</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">FP8_1x128_128x128</span>
|
||
|
||
<span class="k">if</span> <span class="n">use_nvfp4</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">NVFP4</span>
|
||
|
||
<span class="k">if</span> <span class="n">use_w4a8_nvfp4_fp8</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">W4A8_NVFP4_FP8</span>
|
||
|
||
<span class="c1"># W4A8 QServe</span>
|
||
<span class="k">if</span> <span class="n">use_w4a8_qserve</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">W4A8_QSERVE</span>
|
||
|
||
<span class="k">if</span> <span class="n">use_w4a8_mxfp4_fp8</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">W4A8_MXFP4_FP8</span>
|
||
|
||
<span class="k">if</span> <span class="n">use_w4a8_mxfp4_mxfp8</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">W4A8_MXFP4_MXFP8</span>
|
||
|
||
<span class="k">if</span> <span class="n">use_w4a16_mxfp4</span><span class="p">:</span>
|
||
<span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span> <span class="o">|</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">W4A16_MXFP4</span>
|
||
|
||
<span class="k">return</span> <span class="n">mode</span>
|
||
|
||
<span class="nd">@staticmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">use_smooth_quant</span><span class="p">(</span><span class="n">per_token</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">per_channel</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">from_description</span><span class="p">(</span><span class="kc">True</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="n">per_token</span><span class="p">,</span> <span class="n">per_channel</span><span class="p">)</span>
|
||
|
||
<span class="nd">@staticmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">use_qserve</span><span class="p">(</span><span class="n">per_group</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">from_description</span><span class="p">(</span><span class="n">quantize_weights</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">quantize_activations</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">per_group</span><span class="o">=</span><span class="n">per_group</span><span class="p">,</span>
|
||
<span class="n">use_int4_weights</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">use_w4a8_qserve</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
|
||
<span class="nd">@staticmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">use_weight_only</span><span class="p">(</span><span class="n">use_int4_weights</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">per_group</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">from_description</span><span class="p">(</span><span class="n">quantize_weights</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">quantize_activations</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">per_token</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">per_channel</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">per_group</span><span class="o">=</span><span class="n">per_group</span><span class="p">,</span>
|
||
<span class="n">use_int4_weights</span><span class="o">=</span><span class="n">use_int4_weights</span><span class="p">)</span>
|
||
|
||
<span class="nd">@staticmethod</span>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">from_quant_algo</span><span class="p">(</span>
|
||
<span class="n">quant_algo</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">QuantAlgo</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||
<span class="n">kv_cache_quant_algo</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">QuantAlgo</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||
<span class="p">)</span> <span class="o">-></span> <span class="s2">"QuantMode"</span><span class="p">:</span>
|
||
<span class="k">assert</span> <span class="n">quant_algo</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">quant_algo</span> <span class="ow">in</span> <span class="n">QUANT_ALGO_LIST</span>
|
||
<span class="k">assert</span> <span class="n">kv_cache_quant_algo</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">kv_cache_quant_algo</span> <span class="ow">in</span> <span class="n">KV_CACHE_QUANT_ALGO_LIST</span>
|
||
<span class="k">if</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W8A16</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_weight_only</span><span class="p">(</span><span class="n">use_int4_weights</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A16</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_weight_only</span><span class="p">(</span><span class="n">use_int4_weights</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A16_AWQ</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_weight_only</span><span class="p">(</span><span class="n">use_int4_weights</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">per_group</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A8_AWQ</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_weight_only</span><span class="p">(</span><span class="n">use_int4_weights</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">per_group</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A16_GPTQ</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_weight_only</span><span class="p">(</span><span class="n">use_int4_weights</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">per_group</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W8A16_GPTQ</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_weight_only</span><span class="p">(</span><span class="n">use_int4_weights</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">per_group</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W8A8_SQ_PER_CHANNEL</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_smooth_quant</span><span class="p">(</span><span class="n">per_token</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">per_channel</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W8A8_SQ_PER_TENSOR_PLUGIN</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_smooth_quant</span><span class="p">(</span><span class="n">per_token</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">per_channel</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W8A8_SQ_PER_CHANNEL_PER_TOKEN_PLUGIN</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_smooth_quant</span><span class="p">(</span><span class="n">per_token</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">per_channel</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W8A8_SQ_PER_CHANNEL_PER_TENSOR_PLUGIN</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_smooth_quant</span><span class="p">(</span><span class="n">per_token</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||
<span class="n">per_channel</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W8A8_SQ_PER_TENSOR_PER_TOKEN_PLUGIN</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_smooth_quant</span><span class="p">(</span><span class="n">per_token</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||
<span class="n">per_channel</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A8_QSERVE_PER_GROUP</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_qserve</span><span class="p">(</span><span class="n">per_group</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A8_QSERVE_PER_CHANNEL</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">use_qserve</span><span class="p">(</span><span class="n">per_group</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">FP8</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">from_description</span><span class="p">(</span><span class="n">use_fp8_qdq</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">FP8_PER_CHANNEL_PER_TOKEN</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">from_description</span><span class="p">(</span><span class="n">use_fp8_rowwise</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">FP8_BLOCK_SCALES</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">from_description</span><span class="p">(</span><span class="n">use_fp8_block_scales</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">NVFP4</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">from_description</span><span class="p">(</span><span class="n">use_nvfp4</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A8_NVFP4_FP8</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">from_description</span><span class="p">(</span><span class="n">use_w4a8_nvfp4_fp8</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A8_MXFP4_FP8</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">from_description</span><span class="p">(</span><span class="n">use_w4a8_mxfp4_fp8</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A8_MXFP4_MXFP8</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">from_description</span><span class="p">(</span><span class="n">use_w4a8_mxfp4_mxfp8</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">elif</span> <span class="n">quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">W4A16_MXFP4</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">QuantMode</span><span class="o">.</span><span class="n">from_description</span><span class="p">(</span><span class="n">use_w4a16_mxfp4</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">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="k">if</span> <span class="n">kv_cache_quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">INT8</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">quant_mode</span><span class="o">.</span><span class="n">set_int8_kv_cache</span><span class="p">()</span>
|
||
<span class="k">elif</span> <span class="n">kv_cache_quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">FP8</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">quant_mode</span><span class="o">.</span><span class="n">set_fp8_kv_cache</span><span class="p">()</span>
|
||
<span class="k">elif</span> <span class="n">kv_cache_quant_algo</span> <span class="o">==</span> <span class="n">QuantAlgo</span><span class="o">.</span><span class="n">NVFP4</span><span class="p">:</span>
|
||
<span class="n">quant_mode</span> <span class="o">=</span> <span class="n">quant_mode</span><span class="o">.</span><span class="n">set_fp4_kv_cache</span><span class="p">()</span>
|
||
|
||
<span class="k">return</span> <span class="n">quant_mode</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">to_dict</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="p">{</span>
|
||
<span class="s1">'use_smooth_quant'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_act_and_weight_quant</span><span class="p">(),</span>
|
||
<span class="s1">'per_channel'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_per_channel_scaling</span><span class="p">(),</span>
|
||
<span class="s1">'per_token'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_per_token_dynamic_scaling</span><span class="p">(),</span>
|
||
<span class="s1">'per_group'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_per_group_scaling</span><span class="p">(),</span>
|
||
<span class="s1">'int8_kv_cache'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_int8_kv_cache</span><span class="p">(),</span>
|
||
<span class="s1">'enable_fp8'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_fp8_qdq</span><span class="p">(),</span>
|
||
<span class="s1">'enable_fp8_rowwise'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_fp8_rowwise</span><span class="p">(),</span>
|
||
<span class="s1">'enable_fp8_block_scales'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_fp8_block_scales</span><span class="p">(),</span>
|
||
<span class="s1">'enable_nvfp4'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_nvfp4</span><span class="p">(),</span>
|
||
<span class="s1">'enable_w4a8_nvfp4_fp8'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_w4a8_nvfp4_fp8</span><span class="p">(),</span>
|
||
<span class="s1">'enable_w4a8_mxfp4_fp8'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_w4a8_mxfp4_fp8</span><span class="p">(),</span>
|
||
<span class="s1">'enable_w4a8_mxfp4_mxfp8'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_w4a8_mxfp4_mxfp8</span><span class="p">(),</span>
|
||
<span class="s1">'enable_w4a16_mxfp4'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_w4a16_mxfp4</span><span class="p">(),</span>
|
||
<span class="s1">'fp8_kv_cache'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">has_fp8_kv_cache</span><span class="p">(),</span>
|
||
<span class="s1">'use_weight_only'</span><span class="p">:</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">is_weight_only</span><span class="p">(),</span>
|
||
<span class="s1">'weight_only_precision'</span><span class="p">:</span>
|
||
<span class="s1">'int8'</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_int8_weight_only</span><span class="p">()</span> <span class="k">else</span> <span class="s1">'int4'</span><span class="p">,</span>
|
||
<span class="p">}</span></div>
|
||
|
||
|
||
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">GroupwiseQuantAlgo</span><span class="p">:</span>
|
||
<span class="n">BIAS</span> <span class="o">=</span> <span class="mi">1</span>
|
||
<span class="n">ZERO</span> <span class="o">=</span> <span class="mi">2</span>
|
||
<span class="n">PRE_QUANT_SCALE</span> <span class="o">=</span> <span class="mi">4</span>
|
||
<span class="n">W4A8_ALPHA</span> <span class="o">=</span> <span class="mi">8</span>
|
||
<span class="n">INT8_WEIGHT</span> <span class="o">=</span> <span class="mi">16</span>
|
||
</pre></div>
|
||
|
||
</article>
|
||
|
||
|
||
|
||
|
||
|
||
<footer class="prev-next-footer d-print-none">
|
||
|
||
<div class="prev-next-area">
|
||
</div>
|
||
</footer>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
<div class="bd-sidebar-secondary"></div>
|
||
|
||
|
||
|
||
|
||
|
||
</div>
|
||
<footer class="bd-footer-content">
|
||
|
||
</footer>
|
||
|
||
</main>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
<!-- Scripts loaded after <body> so the DOM is not blocked -->
|
||
<script defer src="../../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf"></script>
|
||
<script defer src="../../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf"></script>
|
||
|
||
|
||
<footer class="bd-footer">
|
||
<div class="bd-footer__inner bd-page-width">
|
||
|
||
<div class="footer-items__start">
|
||
|
||
<div class="footer-item">
|
||
<a class="footer-brand logo" href="https://www.nvidia.com">
|
||
<img src="../../../_static/nvidia-logo-horiz-rgb-1c-blk-for-screen.svg" class="logo__image only-light" alt="NVIDIA"/>
|
||
<img src="../../../_static/nvidia-logo-horiz-rgb-1c-wht-for-screen.svg" class="logo__image only-dark" alt="NVIDIA"/>
|
||
</a></div>
|
||
|
||
<div class="footer-item">
|
||
|
||
<div class="footer-links">
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/">Privacy Policy</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-center/">Your Privacy Choices</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/terms-of-service/">Terms of Service</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/accessibility/">Accessibility</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/company-policies/">Corporate Policies</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/product-security/">Product Security</a>
|
||
|
|
||
|
||
|
||
|
||
<a class="external" href="https://www.nvidia.com/en-us/contact/">Contact</a>
|
||
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
<div class="footer-item">
|
||
|
||
|
||
|
||
|
||
<p class="copyright">
|
||
|
||
Copyright © 2025, NVidia.
|
||
<br/>
|
||
|
||
</p>
|
||
</div>
|
||
|
||
<div class="footer-item">
|
||
<div class="extra_footer">
|
||
|
||
<p>Last updated on November 23, 2025.</p>
|
||
|
||
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/a761585">a761585</a>.</p>
|
||
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
</footer>
|
||
</body>
|
||
</html> |