mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-26 13:43:38 +08:00
1482 lines
91 KiB
HTML
1482 lines
91 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" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||
|
||
<title>trtllm-eval — 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 = 'commands/trtllm-eval';</script>
|
||
<script>
|
||
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.2.0rc6';
|
||
DOCUMENTATION_OPTIONS.show_version_warning_banner =
|
||
false;
|
||
</script>
|
||
|
||
<link rel="icon" href="../_static/favicon.png"/>
|
||
|
||
<link rel="index" title="Index" href="../genindex.html" />
|
||
<link rel="search" title="Search" href="../search.html" />
|
||
<link rel="next" title="trtllm-serve" href="trtllm-serve/index.html" />
|
||
<link rel="prev" title="trtllm-bench" href="trtllm-bench.html" />
|
||
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
||
<meta name="docsearch:language" content="en"/>
|
||
<meta name="docsearch:version" content="1.2.0rc6" />
|
||
|
||
|
||
</head>
|
||
|
||
|
||
|
||
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
|
||
|
||
|
||
|
||
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
|
||
|
||
|
||
|
||
<div id="pst-scroll-pixel-helper"></div>
|
||
|
||
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
|
||
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
|
||
|
||
|
||
<dialog id="pst-search-dialog">
|
||
|
||
<form class="bd-search d-flex align-items-center"
|
||
action="../search.html"
|
||
method="get">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<input type="search"
|
||
class="form-control"
|
||
name="q"
|
||
placeholder="Search the docs ..."
|
||
aria-label="Search the docs ..."
|
||
autocomplete="off"
|
||
autocorrect="off"
|
||
autocapitalize="off"
|
||
spellcheck="false"/>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
|
||
</form>
|
||
</dialog>
|
||
|
||
<div class="pst-async-banner-revealer d-none">
|
||
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
|
||
</div>
|
||
|
||
|
||
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
|
||
<div class="bd-header__inner bd-page-width">
|
||
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
|
||
<span class="fa-solid fa-bars"></span>
|
||
</button>
|
||
|
||
|
||
<div class="col-lg-3 navbar-header-items__start">
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
|
||
|
||
|
||
<a class="navbar-brand logo" href="../index.html">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<img src="../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT LLM - Home"/>
|
||
<img src="../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT LLM - Home"/>
|
||
|
||
|
||
<p class="title logo__title">TensorRT LLM</p>
|
||
|
||
</a></div>
|
||
|
||
</div>
|
||
|
||
<div class="col-lg-9 navbar-header-items">
|
||
|
||
<div class="me-auto navbar-header-items__center">
|
||
|
||
<div class="navbar-item">
|
||
|
||
|
||
<div class="version-switcher__container dropdown pst-js-only">
|
||
<button id="pst-version-switcher-button-2"
|
||
type="button"
|
||
class="version-switcher__button btn btn-sm dropdown-toggle"
|
||
data-bs-toggle="dropdown"
|
||
aria-haspopup="listbox"
|
||
aria-controls="pst-version-switcher-list-2"
|
||
aria-label="Version switcher list"
|
||
>
|
||
Choose version <!-- this text may get changed later by javascript -->
|
||
<span class="caret"></span>
|
||
</button>
|
||
<div id="pst-version-switcher-list-2"
|
||
class="version-switcher__menu dropdown-menu list-group-flush py-0"
|
||
role="listbox" aria-labelledby="pst-version-switcher-button-2">
|
||
<!-- dropdown will be populated by javascript on page load -->
|
||
</div>
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="navbar-header-items__end">
|
||
|
||
<div class="navbar-item navbar-persistent--container">
|
||
|
||
|
||
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
</div>
|
||
|
||
|
||
<div class="navbar-item">
|
||
|
||
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
||
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
||
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
||
</button></div>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="navbar-persistent--mobile">
|
||
|
||
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
||
<i class="fa-solid fa-magnifying-glass"></i>
|
||
<span class="search-button__default-text">Search</span>
|
||
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
||
</button>
|
||
</div>
|
||
|
||
|
||
|
||
<button class="pst-navbar-icon sidebar-toggle secondary-toggle" aria-label="On this page">
|
||
<span class="fa-solid fa-outdent"></span>
|
||
</button>
|
||
|
||
</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/curl_responses_client.html">Curl Responses 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>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_responses_client.html">OpenAI Responses Client</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-on-trtllm.html">Deployment Guide for Qwen3 on TensorRT LLM - Blackwell & Hopper 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>
|
||
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-kimi-k2-thinking-on-trtllm.html">Deployment Guide for Kimi K2 Thinking on TensorRT LLM - Blackwell</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="current nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="trtllm-bench.html">trtllm-bench</a></li>
|
||
|
||
<li class="toctree-l1 current active"><a class="current reference internal" href="#">trtllm-eval</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="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="trtllm-serve/trtllm-serve.html">trtllm-serve</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="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/guided-decoding.html">Guided Decoding</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>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/helix.html">Helix Parallelism</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../features/kv-cache-connector.html">KV Cache Connector</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 active" aria-current="page"><span class="ellipsis">trtllm-eval</span></li>
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<div id="searchbox"></div>
|
||
<article class="bd-article">
|
||
|
||
<section id="trtllm-eval">
|
||
<h1>trtllm-eval<a class="headerlink" href="#trtllm-eval" title="Link to this heading">#</a></h1>
|
||
<section id="about">
|
||
<h2>About<a class="headerlink" href="#about" title="Link to this heading">#</a></h2>
|
||
<p>The <code class="docutils literal notranslate"><span class="pre">trtllm-eval</span></code> command provides developers with a unified entry point for accuracy evaluation. It shares the core evaluation logic with the <a class="reference external" href="https://github.com/NVIDIA/TensorRT-LLM/tree/main/tests/integration/defs/accuracy">accuracy test suite</a> of TensorRT LLM.</p>
|
||
<p><code class="docutils literal notranslate"><span class="pre">trtllm-eval</span></code> is built on the offline API – LLM API. Compared to the online <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code>, the offline API provides clearer error messages and simplifies the debugging workflow.</p>
|
||
<p>The following tasks are currently supported:</p>
|
||
<div class="pst-scrollable-table-container"><table class="table">
|
||
<colgroup>
|
||
<col style="width: 22.2%" />
|
||
<col style="width: 27.8%" />
|
||
<col style="width: 16.7%" />
|
||
<col style="width: 16.7%" />
|
||
<col style="width: 16.7%" />
|
||
</colgroup>
|
||
<thead>
|
||
<tr class="row-odd"><th class="head"><p>Dataset</p></th>
|
||
<th class="head"><p>Task</p></th>
|
||
<th class="head"><p>Metric</p></th>
|
||
<th class="head"><p>Default ISL</p></th>
|
||
<th class="head"><p>Default OSL</p></th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr class="row-even"><td><p>CNN Dailymail</p></td>
|
||
<td><p>summarization</p></td>
|
||
<td><p>rouge</p></td>
|
||
<td><p>924</p></td>
|
||
<td><p>100</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>MMLU</p></td>
|
||
<td><p>QA; multiple choice</p></td>
|
||
<td><p>accuracy</p></td>
|
||
<td><p>4,094</p></td>
|
||
<td><p>2</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>GSM8K</p></td>
|
||
<td><p>QA; regex matching</p></td>
|
||
<td><p>accuracy</p></td>
|
||
<td><p>4,096</p></td>
|
||
<td><p>256</p></td>
|
||
</tr>
|
||
<tr class="row-odd"><td><p>GPQA</p></td>
|
||
<td><p>QA; multiple choice</p></td>
|
||
<td><p>accuracy</p></td>
|
||
<td><p>32,768</p></td>
|
||
<td><p>4,096</p></td>
|
||
</tr>
|
||
<tr class="row-even"><td><p>JSON mode eval</p></td>
|
||
<td><p>structured generation</p></td>
|
||
<td><p>accuracy</p></td>
|
||
<td><p>1,024</p></td>
|
||
<td><p>512</p></td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</div>
|
||
<div class="admonition note">
|
||
<p class="admonition-title">Note</p>
|
||
<p><code class="docutils literal notranslate"><span class="pre">trtllm-eval</span></code> originates from the TensorRT LLM accuracy test suite and serves as a lightweight utility for verifying and debugging accuracy. At this time, <code class="docutils literal notranslate"><span class="pre">trtllm-eval</span></code> is intended solely for development and is not recommended for production use.</p>
|
||
</div>
|
||
</section>
|
||
<section id="usage-and-examples">
|
||
<h2>Usage and Examples<a class="headerlink" href="#usage-and-examples" title="Link to this heading">#</a></h2>
|
||
<p>Some evaluation tasks (e.g., GSM8K and GPQA) depend on the <code class="docutils literal notranslate"><span class="pre">lm_eval</span></code> package. To run these tasks, you need to install <code class="docutils literal notranslate"><span class="pre">lm_eval</span></code> with:</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>pip<span class="w"> </span>install<span class="w"> </span>-r<span class="w"> </span>requirements-dev.txt
|
||
</pre></div>
|
||
</div>
|
||
<p>Alternatively, you can install the <code class="docutils literal notranslate"><span class="pre">lm_eval</span></code> version specified in <code class="docutils literal notranslate"><span class="pre">requirements-dev.txt</span></code>.</p>
|
||
<p>Here are some examples:</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Evaluate Llama-3.1-8B-Instruct on MMLU</span>
|
||
trtllm-eval<span class="w"> </span>--model<span class="w"> </span>meta-llama/Llama-3.1-8B-Instruct<span class="w"> </span>mmlu
|
||
|
||
<span class="c1"># Evaluate Llama-3.1-8B-Instruct on GSM8K</span>
|
||
trtllm-eval<span class="w"> </span>--model<span class="w"> </span>meta-llama/Llama-3.1-8B-Instruct<span class="w"> </span>gsm8k
|
||
|
||
<span class="c1"># Evaluate Llama-3.3-70B-Instruct on GPQA Diamond</span>
|
||
trtllm-eval<span class="w"> </span>--model<span class="w"> </span>meta-llama/Llama-3.3-70B-Instruct<span class="w"> </span>gpqa_diamond
|
||
</pre></div>
|
||
</div>
|
||
<p>The <code class="docutils literal notranslate"><span class="pre">--model</span></code> argument accepts either a Hugging Face model ID or a local checkpoint path. By default, <code class="docutils literal notranslate"><span class="pre">trtllm-eval</span></code> runs the model with the PyTorch backend; you can pass <code class="docutils literal notranslate"><span class="pre">--backend</span> <span class="pre">tensorrt</span></code> to switch to the TensorRT backend.</p>
|
||
<p>Alternatively, the <code class="docutils literal notranslate"><span class="pre">--model</span></code> argument also accepts a local path to pre-built TensorRT engines. In this case, you should pass the Hugging Face tokenizer path to the <code class="docutils literal notranslate"><span class="pre">--tokenizer</span></code> argument.</p>
|
||
<p>For more details, see <code class="docutils literal notranslate"><span class="pre">trtllm-eval</span> <span class="pre">--help</span></code> and <code class="docutils literal notranslate"><span class="pre">trtllm-eval</span> <span class="pre"><task></span> <span class="pre">--help</span></code>.</p>
|
||
</section>
|
||
<section id="syntax">
|
||
<h2>Syntax<a class="headerlink" href="#syntax" title="Link to this heading">#</a></h2>
|
||
<section id="trtllm-eval">
|
||
<h3>trtllm-eval<a class="headerlink" href="#trtllm-eval" title="Link to this heading">#</a></h3>
|
||
<p class="rubric">Usage</p>
|
||
<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>trtllm-eval<span class="w"> </span><span class="o">[</span>OPTIONS<span class="o">]</span><span class="w"> </span>COMMAND<span class="w"> </span><span class="o">[</span>ARGS<span class="o">]</span>...
|
||
</pre></div>
|
||
</div>
|
||
<p class="rubric">Options</p>
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-model">
|
||
<span class="sig-name descname"><span class="pre">--model</span></span><span class="sig-prename descclassname"> <span class="pre"><model></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-model" title="Link to this definition">#</a></dt>
|
||
<dd><p><strong>Required</strong> model name | HF checkpoint path | TensorRT engine path</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-tokenizer">
|
||
<span class="sig-name descname"><span class="pre">--tokenizer</span></span><span class="sig-prename descclassname"> <span class="pre"><tokenizer></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-tokenizer" title="Link to this definition">#</a></dt>
|
||
<dd><p>Path | Name of the tokenizer.Specify this value only if using TensorRT engine as model.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-backend">
|
||
<span class="sig-name descname"><span class="pre">--backend</span></span><span class="sig-prename descclassname"> <span class="pre"><backend></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-backend" title="Link to this definition">#</a></dt>
|
||
<dd><p>The backend to use for evaluation. Default is pytorch backend.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Options<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>pytorch | tensorrt</p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-log_level">
|
||
<span class="sig-name descname"><span class="pre">--log_level</span></span><span class="sig-prename descclassname"> <span class="pre"><log_level></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-log_level" title="Link to this definition">#</a></dt>
|
||
<dd><p>The logging level.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Options<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>internal_error | error | warning | info | verbose | debug | trace</p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-max_beam_width">
|
||
<span class="sig-name descname"><span class="pre">--max_beam_width</span></span><span class="sig-prename descclassname"> <span class="pre"><max_beam_width></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-max_beam_width" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum number of beams for beam search decoding.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-max_batch_size">
|
||
<span class="sig-name descname"><span class="pre">--max_batch_size</span></span><span class="sig-prename descclassname"> <span class="pre"><max_batch_size></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-max_batch_size" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum number of requests that the engine can schedule.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-max_num_tokens">
|
||
<span class="sig-name descname"><span class="pre">--max_num_tokens</span></span><span class="sig-prename descclassname"> <span class="pre"><max_num_tokens></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-max_num_tokens" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum number of batched input tokens after padding is removed in each batch.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-max_seq_len">
|
||
<span class="sig-name descname"><span class="pre">--max_seq_len</span></span><span class="sig-prename descclassname"> <span class="pre"><max_seq_len></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-max_seq_len" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum total length of one request, including prompt and outputs. If unspecified, the value is deduced from the model config.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-tp_size">
|
||
<span class="sig-name descname"><span class="pre">--tp_size</span></span><span class="sig-prename descclassname"> <span class="pre"><tp_size></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-tp_size" title="Link to this definition">#</a></dt>
|
||
<dd><p>Tensor parallelism size.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-pp_size">
|
||
<span class="sig-name descname"><span class="pre">--pp_size</span></span><span class="sig-prename descclassname"> <span class="pre"><pp_size></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-pp_size" title="Link to this definition">#</a></dt>
|
||
<dd><p>Pipeline parallelism size.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-ep_size">
|
||
<span class="sig-name descname"><span class="pre">--ep_size</span></span><span class="sig-prename descclassname"> <span class="pre"><ep_size></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-ep_size" title="Link to this definition">#</a></dt>
|
||
<dd><p>expert parallelism size</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpus_per_node">
|
||
<span class="sig-name descname"><span class="pre">--gpus_per_node</span></span><span class="sig-prename descclassname"> <span class="pre"><gpus_per_node></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpus_per_node" title="Link to this definition">#</a></dt>
|
||
<dd><p>Number of GPUs per node. Default to None, and it will be detected automatically.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-kv_cache_free_gpu_memory_fraction">
|
||
<span class="sig-name descname"><span class="pre">--kv_cache_free_gpu_memory_fraction</span></span><span class="sig-prename descclassname"> <span class="pre"><kv_cache_free_gpu_memory_fraction></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-kv_cache_free_gpu_memory_fraction" title="Link to this definition">#</a></dt>
|
||
<dd><p>Free GPU memory fraction reserved for KV Cache, after allocating model weights and buffers.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-trust_remote_code">
|
||
<span class="sig-name descname"><span class="pre">--trust_remote_code</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-trust_remote_code" title="Link to this definition">#</a></dt>
|
||
<dd><p>Flag for HF transformers.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-revision">
|
||
<span class="sig-name descname"><span class="pre">--revision</span></span><span class="sig-prename descclassname"> <span class="pre"><revision></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-revision" title="Link to this definition">#</a></dt>
|
||
<dd><p>The revision to use for the HuggingFace model (branch name, tag name, or commit id).</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-config">
|
||
<span id="cmdoption-trtllm-eval-extra_llm_api_options"></span><span class="sig-name descname"><span class="pre">--config</span></span><span class="sig-prename descclassname"></span><span class="sig-prename descclassname"><span class="pre">,</span> </span><span class="sig-name descname"><span class="pre">--extra_llm_api_options</span></span><span class="sig-prename descclassname"> <span class="pre"><extra_llm_api_options></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-config" title="Link to this definition">#</a></dt>
|
||
<dd><p>Path to a YAML file that overwrites the parameters. Can be specified as either –config or –extra_llm_api_options.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-disable_kv_cache_reuse">
|
||
<span class="sig-name descname"><span class="pre">--disable_kv_cache_reuse</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-disable_kv_cache_reuse" title="Link to this definition">#</a></dt>
|
||
<dd><p>Flag for disabling KV cache reuse.</p>
|
||
</dd></dl>
|
||
|
||
<section id="trtllm-eval-cnn-dailymail">
|
||
<h4>cnn_dailymail<a class="headerlink" href="#trtllm-eval-cnn-dailymail" title="Link to this heading">#</a></h4>
|
||
<p class="rubric">Usage</p>
|
||
<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>trtllm-eval<span class="w"> </span>cnn_dailymail<span class="w"> </span><span class="o">[</span>OPTIONS<span class="o">]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="rubric">Options</p>
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-cnn_dailymail-dataset_path">
|
||
<span class="sig-name descname"><span class="pre">--dataset_path</span></span><span class="sig-prename descclassname"> <span class="pre"><dataset_path></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-cnn_dailymail-dataset_path" title="Link to this definition">#</a></dt>
|
||
<dd><p>The path to CNN Dailymail dataset. If unspecified, the dataset is downloaded from HF hub.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-cnn_dailymail-num_samples">
|
||
<span class="sig-name descname"><span class="pre">--num_samples</span></span><span class="sig-prename descclassname"> <span class="pre"><num_samples></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-cnn_dailymail-num_samples" title="Link to this definition">#</a></dt>
|
||
<dd><p>Number of samples to run the evaluation; None means full dataset.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-cnn_dailymail-random_seed">
|
||
<span class="sig-name descname"><span class="pre">--random_seed</span></span><span class="sig-prename descclassname"> <span class="pre"><random_seed></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-cnn_dailymail-random_seed" title="Link to this definition">#</a></dt>
|
||
<dd><p>Random seed for dataset processing.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-cnn_dailymail-rouge_path">
|
||
<span class="sig-name descname"><span class="pre">--rouge_path</span></span><span class="sig-prename descclassname"> <span class="pre"><rouge_path></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-cnn_dailymail-rouge_path" title="Link to this definition">#</a></dt>
|
||
<dd><p>The path to rouge repository.If unspecified, the repository is downloaded from HF hub.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-cnn_dailymail-apply_chat_template">
|
||
<span class="sig-name descname"><span class="pre">--apply_chat_template</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-cnn_dailymail-apply_chat_template" title="Link to this definition">#</a></dt>
|
||
<dd><p>Whether to apply chat template.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-cnn_dailymail-system_prompt">
|
||
<span class="sig-name descname"><span class="pre">--system_prompt</span></span><span class="sig-prename descclassname"> <span class="pre"><system_prompt></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-cnn_dailymail-system_prompt" title="Link to this definition">#</a></dt>
|
||
<dd><p>System prompt.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-cnn_dailymail-max_input_length">
|
||
<span class="sig-name descname"><span class="pre">--max_input_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_input_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-cnn_dailymail-max_input_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum prompt length.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-cnn_dailymail-max_output_length">
|
||
<span class="sig-name descname"><span class="pre">--max_output_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_output_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-cnn_dailymail-max_output_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum generation length.</p>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="trtllm-eval-gpqa-diamond">
|
||
<h4>gpqa_diamond<a class="headerlink" href="#trtllm-eval-gpqa-diamond" title="Link to this heading">#</a></h4>
|
||
<p class="rubric">Usage</p>
|
||
<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>trtllm-eval<span class="w"> </span>gpqa_diamond<span class="w"> </span><span class="o">[</span>OPTIONS<span class="o">]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="rubric">Options</p>
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_diamond-dataset_path">
|
||
<span class="sig-name descname"><span class="pre">--dataset_path</span></span><span class="sig-prename descclassname"> <span class="pre"><dataset_path></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_diamond-dataset_path" title="Link to this definition">#</a></dt>
|
||
<dd><p>The path to GPQA dataset. If unspecified, the dataset is downloaded from HF hub.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_diamond-num_samples">
|
||
<span class="sig-name descname"><span class="pre">--num_samples</span></span><span class="sig-prename descclassname"> <span class="pre"><num_samples></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_diamond-num_samples" title="Link to this definition">#</a></dt>
|
||
<dd><p>Number of samples to run the evaluation; None means full dataset.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_diamond-random_seed">
|
||
<span class="sig-name descname"><span class="pre">--random_seed</span></span><span class="sig-prename descclassname"> <span class="pre"><random_seed></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_diamond-random_seed" title="Link to this definition">#</a></dt>
|
||
<dd><p>Random seed for dataset processing.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_diamond-apply_chat_template">
|
||
<span class="sig-name descname"><span class="pre">--apply_chat_template</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_diamond-apply_chat_template" title="Link to this definition">#</a></dt>
|
||
<dd><p>Whether to apply chat template.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_diamond-chat_template_kwargs">
|
||
<span class="sig-name descname"><span class="pre">--chat_template_kwargs</span></span><span class="sig-prename descclassname"> <span class="pre"><chat_template_kwargs></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_diamond-chat_template_kwargs" title="Link to this definition">#</a></dt>
|
||
<dd><p>Chat template kwargs as JSON string, e.g., ‘{“thinking_budget”: 0}’</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_diamond-system_prompt">
|
||
<span class="sig-name descname"><span class="pre">--system_prompt</span></span><span class="sig-prename descclassname"> <span class="pre"><system_prompt></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_diamond-system_prompt" title="Link to this definition">#</a></dt>
|
||
<dd><p>System prompt.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_diamond-max_input_length">
|
||
<span class="sig-name descname"><span class="pre">--max_input_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_input_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_diamond-max_input_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum prompt length.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_diamond-max_output_length">
|
||
<span class="sig-name descname"><span class="pre">--max_output_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_output_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_diamond-max_output_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum generation length.</p>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="trtllm-eval-gpqa-extended">
|
||
<h4>gpqa_extended<a class="headerlink" href="#trtllm-eval-gpqa-extended" title="Link to this heading">#</a></h4>
|
||
<p class="rubric">Usage</p>
|
||
<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>trtllm-eval<span class="w"> </span>gpqa_extended<span class="w"> </span><span class="o">[</span>OPTIONS<span class="o">]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="rubric">Options</p>
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_extended-dataset_path">
|
||
<span class="sig-name descname"><span class="pre">--dataset_path</span></span><span class="sig-prename descclassname"> <span class="pre"><dataset_path></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_extended-dataset_path" title="Link to this definition">#</a></dt>
|
||
<dd><p>The path to GPQA dataset. If unspecified, the dataset is downloaded from HF hub.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_extended-num_samples">
|
||
<span class="sig-name descname"><span class="pre">--num_samples</span></span><span class="sig-prename descclassname"> <span class="pre"><num_samples></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_extended-num_samples" title="Link to this definition">#</a></dt>
|
||
<dd><p>Number of samples to run the evaluation; None means full dataset.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_extended-random_seed">
|
||
<span class="sig-name descname"><span class="pre">--random_seed</span></span><span class="sig-prename descclassname"> <span class="pre"><random_seed></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_extended-random_seed" title="Link to this definition">#</a></dt>
|
||
<dd><p>Random seed for dataset processing.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_extended-apply_chat_template">
|
||
<span class="sig-name descname"><span class="pre">--apply_chat_template</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_extended-apply_chat_template" title="Link to this definition">#</a></dt>
|
||
<dd><p>Whether to apply chat template.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_extended-chat_template_kwargs">
|
||
<span class="sig-name descname"><span class="pre">--chat_template_kwargs</span></span><span class="sig-prename descclassname"> <span class="pre"><chat_template_kwargs></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_extended-chat_template_kwargs" title="Link to this definition">#</a></dt>
|
||
<dd><p>Chat template kwargs as JSON string, e.g., ‘{“thinking_budget”: 0}’</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_extended-system_prompt">
|
||
<span class="sig-name descname"><span class="pre">--system_prompt</span></span><span class="sig-prename descclassname"> <span class="pre"><system_prompt></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_extended-system_prompt" title="Link to this definition">#</a></dt>
|
||
<dd><p>System prompt.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_extended-max_input_length">
|
||
<span class="sig-name descname"><span class="pre">--max_input_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_input_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_extended-max_input_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum prompt length.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_extended-max_output_length">
|
||
<span class="sig-name descname"><span class="pre">--max_output_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_output_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_extended-max_output_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum generation length.</p>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="trtllm-eval-gpqa-main">
|
||
<h4>gpqa_main<a class="headerlink" href="#trtllm-eval-gpqa-main" title="Link to this heading">#</a></h4>
|
||
<p class="rubric">Usage</p>
|
||
<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>trtllm-eval<span class="w"> </span>gpqa_main<span class="w"> </span><span class="o">[</span>OPTIONS<span class="o">]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="rubric">Options</p>
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_main-dataset_path">
|
||
<span class="sig-name descname"><span class="pre">--dataset_path</span></span><span class="sig-prename descclassname"> <span class="pre"><dataset_path></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_main-dataset_path" title="Link to this definition">#</a></dt>
|
||
<dd><p>The path to GPQA dataset. If unspecified, the dataset is downloaded from HF hub.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_main-num_samples">
|
||
<span class="sig-name descname"><span class="pre">--num_samples</span></span><span class="sig-prename descclassname"> <span class="pre"><num_samples></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_main-num_samples" title="Link to this definition">#</a></dt>
|
||
<dd><p>Number of samples to run the evaluation; None means full dataset.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_main-random_seed">
|
||
<span class="sig-name descname"><span class="pre">--random_seed</span></span><span class="sig-prename descclassname"> <span class="pre"><random_seed></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_main-random_seed" title="Link to this definition">#</a></dt>
|
||
<dd><p>Random seed for dataset processing.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_main-apply_chat_template">
|
||
<span class="sig-name descname"><span class="pre">--apply_chat_template</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_main-apply_chat_template" title="Link to this definition">#</a></dt>
|
||
<dd><p>Whether to apply chat template.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_main-chat_template_kwargs">
|
||
<span class="sig-name descname"><span class="pre">--chat_template_kwargs</span></span><span class="sig-prename descclassname"> <span class="pre"><chat_template_kwargs></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_main-chat_template_kwargs" title="Link to this definition">#</a></dt>
|
||
<dd><p>Chat template kwargs as JSON string, e.g., ‘{“thinking_budget”: 0}’</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_main-system_prompt">
|
||
<span class="sig-name descname"><span class="pre">--system_prompt</span></span><span class="sig-prename descclassname"> <span class="pre"><system_prompt></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_main-system_prompt" title="Link to this definition">#</a></dt>
|
||
<dd><p>System prompt.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_main-max_input_length">
|
||
<span class="sig-name descname"><span class="pre">--max_input_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_input_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_main-max_input_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum prompt length.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gpqa_main-max_output_length">
|
||
<span class="sig-name descname"><span class="pre">--max_output_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_output_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gpqa_main-max_output_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum generation length.</p>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="trtllm-eval-gsm8k">
|
||
<h4>gsm8k<a class="headerlink" href="#trtllm-eval-gsm8k" title="Link to this heading">#</a></h4>
|
||
<p class="rubric">Usage</p>
|
||
<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>trtllm-eval<span class="w"> </span>gsm8k<span class="w"> </span><span class="o">[</span>OPTIONS<span class="o">]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="rubric">Options</p>
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gsm8k-dataset_path">
|
||
<span class="sig-name descname"><span class="pre">--dataset_path</span></span><span class="sig-prename descclassname"> <span class="pre"><dataset_path></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gsm8k-dataset_path" title="Link to this definition">#</a></dt>
|
||
<dd><p>The path to GSM8K dataset. If unspecified, the dataset is downloaded from HF hub.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gsm8k-num_samples">
|
||
<span class="sig-name descname"><span class="pre">--num_samples</span></span><span class="sig-prename descclassname"> <span class="pre"><num_samples></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gsm8k-num_samples" title="Link to this definition">#</a></dt>
|
||
<dd><p>Number of samples to run the evaluation; None means full dataset.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gsm8k-random_seed">
|
||
<span class="sig-name descname"><span class="pre">--random_seed</span></span><span class="sig-prename descclassname"> <span class="pre"><random_seed></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gsm8k-random_seed" title="Link to this definition">#</a></dt>
|
||
<dd><p>Random seed for dataset processing.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gsm8k-apply_chat_template">
|
||
<span class="sig-name descname"><span class="pre">--apply_chat_template</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-gsm8k-apply_chat_template" title="Link to this definition">#</a></dt>
|
||
<dd><p>Whether to apply chat template.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gsm8k-chat_template_kwargs">
|
||
<span class="sig-name descname"><span class="pre">--chat_template_kwargs</span></span><span class="sig-prename descclassname"> <span class="pre"><chat_template_kwargs></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gsm8k-chat_template_kwargs" title="Link to this definition">#</a></dt>
|
||
<dd><p>Chat template kwargs as JSON string, e.g., ‘{“thinking_budget”: 0}’</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gsm8k-fewshot_as_multiturn">
|
||
<span class="sig-name descname"><span class="pre">--fewshot_as_multiturn</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-gsm8k-fewshot_as_multiturn" title="Link to this definition">#</a></dt>
|
||
<dd><p>Apply fewshot as multiturn.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gsm8k-system_prompt">
|
||
<span class="sig-name descname"><span class="pre">--system_prompt</span></span><span class="sig-prename descclassname"> <span class="pre"><system_prompt></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gsm8k-system_prompt" title="Link to this definition">#</a></dt>
|
||
<dd><p>System prompt.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gsm8k-max_input_length">
|
||
<span class="sig-name descname"><span class="pre">--max_input_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_input_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gsm8k-max_input_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum prompt length.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-gsm8k-max_output_length">
|
||
<span class="sig-name descname"><span class="pre">--max_output_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_output_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-gsm8k-max_output_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum generation length.</p>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="trtllm-eval-json-mode-eval">
|
||
<h4>json_mode_eval<a class="headerlink" href="#trtllm-eval-json-mode-eval" title="Link to this heading">#</a></h4>
|
||
<p class="rubric">Usage</p>
|
||
<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>trtllm-eval<span class="w"> </span>json_mode_eval<span class="w"> </span><span class="o">[</span>OPTIONS<span class="o">]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="rubric">Options</p>
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-json_mode_eval-dataset_path">
|
||
<span class="sig-name descname"><span class="pre">--dataset_path</span></span><span class="sig-prename descclassname"> <span class="pre"><dataset_path></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-json_mode_eval-dataset_path" title="Link to this definition">#</a></dt>
|
||
<dd><p>The path to JSON Mode Eval dataset. If unspecified, the dataset is downloaded from HF hub.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-json_mode_eval-num_samples">
|
||
<span class="sig-name descname"><span class="pre">--num_samples</span></span><span class="sig-prename descclassname"> <span class="pre"><num_samples></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-json_mode_eval-num_samples" title="Link to this definition">#</a></dt>
|
||
<dd><p>Number of samples to run the evaluation; None means full dataset.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-json_mode_eval-random_seed">
|
||
<span class="sig-name descname"><span class="pre">--random_seed</span></span><span class="sig-prename descclassname"> <span class="pre"><random_seed></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-json_mode_eval-random_seed" title="Link to this definition">#</a></dt>
|
||
<dd><p>Random seed for dataset processing.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-json_mode_eval-system_prompt">
|
||
<span class="sig-name descname"><span class="pre">--system_prompt</span></span><span class="sig-prename descclassname"> <span class="pre"><system_prompt></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-json_mode_eval-system_prompt" title="Link to this definition">#</a></dt>
|
||
<dd><p>System prompt.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-json_mode_eval-max_input_length">
|
||
<span class="sig-name descname"><span class="pre">--max_input_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_input_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-json_mode_eval-max_input_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum prompt length.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-json_mode_eval-max_output_length">
|
||
<span class="sig-name descname"><span class="pre">--max_output_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_output_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-json_mode_eval-max_output_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum generation length.</p>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="trtllm-eval-longbench-v2">
|
||
<h4>longbench_v2<a class="headerlink" href="#trtllm-eval-longbench-v2" title="Link to this heading">#</a></h4>
|
||
<p class="rubric">Usage</p>
|
||
<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>trtllm-eval<span class="w"> </span>longbench_v2<span class="w"> </span><span class="o">[</span>OPTIONS<span class="o">]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="rubric">Options</p>
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-dataset_path">
|
||
<span class="sig-name descname"><span class="pre">--dataset_path</span></span><span class="sig-prename descclassname"> <span class="pre"><dataset_path></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-dataset_path" title="Link to this definition">#</a></dt>
|
||
<dd><p>Path to LongBench v2 dataset (HF dataset name or local path).</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-prompts_dir">
|
||
<span class="sig-name descname"><span class="pre">--prompts_dir</span></span><span class="sig-prename descclassname"> <span class="pre"><prompts_dir></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-prompts_dir" title="Link to this definition">#</a></dt>
|
||
<dd><p>Path to directory containing prompt templates.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-num_samples">
|
||
<span class="sig-name descname"><span class="pre">--num_samples</span></span><span class="sig-prename descclassname"> <span class="pre"><num_samples></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-num_samples" title="Link to this definition">#</a></dt>
|
||
<dd><p>Number of samples to evaluate (None for all).</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-start_idx">
|
||
<span class="sig-name descname"><span class="pre">--start_idx</span></span><span class="sig-prename descclassname"> <span class="pre"><start_idx></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-start_idx" title="Link to this definition">#</a></dt>
|
||
<dd><p>Start index for evaluation.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-difficulty">
|
||
<span class="sig-name descname"><span class="pre">--difficulty</span></span><span class="sig-prename descclassname"> <span class="pre"><difficulty></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-difficulty" title="Link to this definition">#</a></dt>
|
||
<dd><p>Filter by difficulty level.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Options<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>easy | hard</p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-length">
|
||
<span class="sig-name descname"><span class="pre">--length</span></span><span class="sig-prename descclassname"> <span class="pre"><length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Filter by length category.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Options<span class="colon">:</span></dt>
|
||
<dd class="field-odd"><p>short | medium | long</p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-domain">
|
||
<span class="sig-name descname"><span class="pre">--domain</span></span><span class="sig-prename descclassname"> <span class="pre"><domain></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-domain" title="Link to this definition">#</a></dt>
|
||
<dd><p>Filter by domain.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-cot">
|
||
<span class="sig-name descname"><span class="pre">--cot</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-cot" title="Link to this definition">#</a></dt>
|
||
<dd><p>Enable Chain-of-Thought reasoning.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-no_context">
|
||
<span class="sig-name descname"><span class="pre">--no_context</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-no_context" title="Link to this definition">#</a></dt>
|
||
<dd><p>Test without long context.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-rag">
|
||
<span class="sig-name descname"><span class="pre">--rag</span></span><span class="sig-prename descclassname"> <span class="pre"><rag></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-rag" title="Link to this definition">#</a></dt>
|
||
<dd><p>Use top-N retrieved contexts (0 to disable).</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-max_len">
|
||
<span class="sig-name descname"><span class="pre">--max_len</span></span><span class="sig-prename descclassname"> <span class="pre"><max_len></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-max_len" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum input and output length in tokens for truncation when building prompts.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-output_dir">
|
||
<span class="sig-name descname"><span class="pre">--output_dir</span></span><span class="sig-prename descclassname"> <span class="pre"><output_dir></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-output_dir" title="Link to this definition">#</a></dt>
|
||
<dd><p>Directory to save results.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-random_seed">
|
||
<span class="sig-name descname"><span class="pre">--random_seed</span></span><span class="sig-prename descclassname"> <span class="pre"><random_seed></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-random_seed" title="Link to this definition">#</a></dt>
|
||
<dd><p>Random seed for dataset processing.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-apply_chat_template">
|
||
<span class="sig-name descname"><span class="pre">--apply_chat_template</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-apply_chat_template" title="Link to this definition">#</a></dt>
|
||
<dd><p>Whether to apply chat template.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-system_prompt">
|
||
<span class="sig-name descname"><span class="pre">--system_prompt</span></span><span class="sig-prename descclassname"> <span class="pre"><system_prompt></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-system_prompt" title="Link to this definition">#</a></dt>
|
||
<dd><p>System prompt.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-max_input_length">
|
||
<span class="sig-name descname"><span class="pre">--max_input_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_input_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-max_input_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum prompt length in sampling parameters.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-max_output_length">
|
||
<span class="sig-name descname"><span class="pre">--max_output_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_output_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-max_output_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum generation length in sampling parameters.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-longbench_v2-chat_template_kwargs">
|
||
<span class="sig-name descname"><span class="pre">--chat_template_kwargs</span></span><span class="sig-prename descclassname"> <span class="pre"><chat_template_kwargs></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-longbench_v2-chat_template_kwargs" title="Link to this definition">#</a></dt>
|
||
<dd><p>A JSON string specifying chat template arguments, used to enable features like thinking mode. Examples: ‘{“enable_thinking”: true}’ for Qwen3, or ‘{“thinking”: true}’ for DeepSeek-V3.2.</p>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="trtllm-eval-mmlu">
|
||
<h4>mmlu<a class="headerlink" href="#trtllm-eval-mmlu" title="Link to this heading">#</a></h4>
|
||
<p class="rubric">Usage</p>
|
||
<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>trtllm-eval<span class="w"> </span>mmlu<span class="w"> </span><span class="o">[</span>OPTIONS<span class="o">]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="rubric">Options</p>
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmlu-dataset_path">
|
||
<span class="sig-name descname"><span class="pre">--dataset_path</span></span><span class="sig-prename descclassname"> <span class="pre"><dataset_path></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmlu-dataset_path" title="Link to this definition">#</a></dt>
|
||
<dd><p>The path to MMLU dataset. The commands to prepare the dataset: wget <a class="reference external" href="https://people.eecs.berkeley.edu/~hendrycks/data.tar">https://people.eecs.berkeley.edu/~hendrycks/data.tar</a> && tar -xf data.tar. If unspecified, the dataset is downloaded automatically.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmlu-num_samples">
|
||
<span class="sig-name descname"><span class="pre">--num_samples</span></span><span class="sig-prename descclassname"> <span class="pre"><num_samples></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmlu-num_samples" title="Link to this definition">#</a></dt>
|
||
<dd><p>Number of samples to run the evaluation; None means full dataset.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmlu-num_fewshot">
|
||
<span class="sig-name descname"><span class="pre">--num_fewshot</span></span><span class="sig-prename descclassname"> <span class="pre"><num_fewshot></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmlu-num_fewshot" title="Link to this definition">#</a></dt>
|
||
<dd><p>Number of fewshot.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmlu-random_seed">
|
||
<span class="sig-name descname"><span class="pre">--random_seed</span></span><span class="sig-prename descclassname"> <span class="pre"><random_seed></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmlu-random_seed" title="Link to this definition">#</a></dt>
|
||
<dd><p>Random seed for dataset processing.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmlu-apply_chat_template">
|
||
<span class="sig-name descname"><span class="pre">--apply_chat_template</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmlu-apply_chat_template" title="Link to this definition">#</a></dt>
|
||
<dd><p>Whether to apply chat template.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmlu-chat_template_kwargs">
|
||
<span class="sig-name descname"><span class="pre">--chat_template_kwargs</span></span><span class="sig-prename descclassname"> <span class="pre"><chat_template_kwargs></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmlu-chat_template_kwargs" title="Link to this definition">#</a></dt>
|
||
<dd><p>Chat template kwargs as JSON string, e.g., ‘{“thinking_budget”: 0}’</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmlu-system_prompt">
|
||
<span class="sig-name descname"><span class="pre">--system_prompt</span></span><span class="sig-prename descclassname"> <span class="pre"><system_prompt></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmlu-system_prompt" title="Link to this definition">#</a></dt>
|
||
<dd><p>System prompt.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmlu-max_input_length">
|
||
<span class="sig-name descname"><span class="pre">--max_input_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_input_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmlu-max_input_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum prompt length.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmlu-max_output_length">
|
||
<span class="sig-name descname"><span class="pre">--max_output_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_output_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmlu-max_output_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum generation length.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmlu-check_accuracy">
|
||
<span class="sig-name descname"><span class="pre">--check_accuracy</span></span><span class="sig-prename descclassname"></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmlu-check_accuracy" title="Link to this definition">#</a></dt>
|
||
<dd></dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmlu-accuracy_threshold">
|
||
<span class="sig-name descname"><span class="pre">--accuracy_threshold</span></span><span class="sig-prename descclassname"> <span class="pre"><accuracy_threshold></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmlu-accuracy_threshold" title="Link to this definition">#</a></dt>
|
||
<dd></dd></dl>
|
||
|
||
</section>
|
||
<section id="trtllm-eval-mmmu">
|
||
<h4>mmmu<a class="headerlink" href="#trtllm-eval-mmmu" title="Link to this heading">#</a></h4>
|
||
<p class="rubric">Usage</p>
|
||
<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>trtllm-eval<span class="w"> </span>mmmu<span class="w"> </span><span class="o">[</span>OPTIONS<span class="o">]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="rubric">Options</p>
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmmu-dataset_path">
|
||
<span class="sig-name descname"><span class="pre">--dataset_path</span></span><span class="sig-prename descclassname"> <span class="pre"><dataset_path></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmmu-dataset_path" title="Link to this definition">#</a></dt>
|
||
<dd><p>The path to MMMU dataset. If unspecified, the dataset is downloaded from HF hub.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmmu-num_samples">
|
||
<span class="sig-name descname"><span class="pre">--num_samples</span></span><span class="sig-prename descclassname"> <span class="pre"><num_samples></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmmu-num_samples" title="Link to this definition">#</a></dt>
|
||
<dd><p>Number of samples to run the evaluation; None means full dataset.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmmu-random_seed">
|
||
<span class="sig-name descname"><span class="pre">--random_seed</span></span><span class="sig-prename descclassname"> <span class="pre"><random_seed></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmmu-random_seed" title="Link to this definition">#</a></dt>
|
||
<dd><p>Random seed for dataset processing.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmmu-chat_template_kwargs">
|
||
<span class="sig-name descname"><span class="pre">--chat_template_kwargs</span></span><span class="sig-prename descclassname"> <span class="pre"><chat_template_kwargs></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmmu-chat_template_kwargs" title="Link to this definition">#</a></dt>
|
||
<dd><p>Chat template kwargs as JSON string, e.g., ‘{“thinking_budget”: 0}’</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmmu-system_prompt">
|
||
<span class="sig-name descname"><span class="pre">--system_prompt</span></span><span class="sig-prename descclassname"> <span class="pre"><system_prompt></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmmu-system_prompt" title="Link to this definition">#</a></dt>
|
||
<dd><p>The system prompt to be added on the prompt. If specified, it will add {‘role’: ‘system’, ‘content’: system_prompt} to the prompt.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmmu-max_input_length">
|
||
<span class="sig-name descname"><span class="pre">--max_input_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_input_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmmu-max_input_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum prompt length.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="std option">
|
||
<dt class="sig sig-object std" id="cmdoption-trtllm-eval-mmmu-max_output_length">
|
||
<span class="sig-name descname"><span class="pre">--max_output_length</span></span><span class="sig-prename descclassname"> <span class="pre"><max_output_length></span></span><a class="headerlink" href="#cmdoption-trtllm-eval-mmmu-max_output_length" title="Link to this definition">#</a></dt>
|
||
<dd><p>Maximum generation length.</p>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
</section>
|
||
</section>
|
||
</section>
|
||
|
||
|
||
</article>
|
||
|
||
|
||
|
||
|
||
|
||
<footer class="prev-next-footer d-print-none">
|
||
|
||
<div class="prev-next-area">
|
||
<a class="left-prev"
|
||
href="trtllm-bench.html"
|
||
title="previous page">
|
||
<i class="fa-solid fa-angle-left"></i>
|
||
<div class="prev-next-info">
|
||
<p class="prev-next-subtitle">previous</p>
|
||
<p class="prev-next-title">trtllm-bench</p>
|
||
</div>
|
||
</a>
|
||
<a class="right-next"
|
||
href="trtllm-serve/index.html"
|
||
title="next page">
|
||
<div class="prev-next-info">
|
||
<p class="prev-next-subtitle">next</p>
|
||
<p class="prev-next-title">trtllm-serve</p>
|
||
</div>
|
||
<i class="fa-solid fa-angle-right"></i>
|
||
</a>
|
||
</div>
|
||
</footer>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
|
||
|
||
<dialog id="pst-secondary-sidebar-modal"></dialog>
|
||
<div id="pst-secondary-sidebar" class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
|
||
|
||
|
||
<div class="sidebar-secondary-item">
|
||
<div
|
||
id="pst-page-navigation-heading-2"
|
||
class="page-toc tocsection onthispage">
|
||
<i class="fa-solid fa-list"></i> On this page
|
||
</div>
|
||
<nav class="bd-toc-nav page-toc" aria-labelledby="pst-page-navigation-heading-2">
|
||
<ul class="visible nav section-nav flex-column">
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#about">About</a></li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#usage-and-examples">Usage and Examples</a></li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#syntax">Syntax</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#trtllm-eval">trtllm-eval</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#trtllm-eval-cnn-dailymail">cnn_dailymail</a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#trtllm-eval-gpqa-diamond">gpqa_diamond</a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#trtllm-eval-gpqa-extended">gpqa_extended</a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#trtllm-eval-gpqa-main">gpqa_main</a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#trtllm-eval-gsm8k">gsm8k</a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#trtllm-eval-json-mode-eval">json_mode_eval</a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#trtllm-eval-longbench-v2">longbench_v2</a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#trtllm-eval-mmlu">mmlu</a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#trtllm-eval-mmmu">mmmu</a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</nav></div>
|
||
|
||
</div></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 December 15, 2025.</p>
|
||
|
||
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/9ba1426">9ba1426</a>.</p>
|
||
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
</footer>
|
||
</body>
|
||
</html> |