kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
1d509f9205
TensorRT-LLMs/_modules/tensorrt_llm/llmapi/build_cache.html
Kaiyu Xie 1d509f9205 Update GitHub pages in root to v1.0.0rc6
2025-08-07 06:26:14 +00:00

958 lines
72 KiB
HTML
Raw Blame History

<!DOCTYPE html>
<html lang="en" data-content_root="../../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>tensorrt_llm.llmapi.build_cache &#8212; TensorRT-LLM</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!--
this give us a css class that will be invisible only if js is disabled
-->
<noscript>
<style>
.pst-js-only { display: none !important; }
</style>
</noscript>
<!-- Loaded before other Sphinx assets -->
<link href="../../../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" />
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../../../_static/styles/nvidia-sphinx-theme.css?v=df3ac72c" />
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css?v=76b2166b" />
<link rel="stylesheet" type="text/css" href="../../../_static/autodoc_pydantic.css" />
<link rel="stylesheet" type="text/css" href="../../../_static/togglebutton.css?v=13237357" />
<link rel="stylesheet" type="text/css" href="../../../_static/custom.css?v=95073da6" />
<!-- So that users can add custom icons -->
<script src="../../../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script>
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" />
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" />
<script src="../../../_static/documentation_options.js?v=5929fcd5"></script>
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../../../_static/copybutton.js?v=65e89d2a"></script>
<script>let toggleHintShow = 'Click to show';</script>
<script>let toggleHintHide = 'Click to hide';</script>
<script>let toggleOpenOnPrint = 'true';</script>
<script src="../../../_static/togglebutton.js?v=4a39c7ea"></script>
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
<script>DOCUMENTATION_OPTIONS.pagename = '_modules/tensorrt_llm/llmapi/build_cache';</script>
<script>
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.0.0rc6';
DOCUMENTATION_OPTIONS.show_version_warning_banner =
false;
</script>
<link rel="icon" href="../../../_static/favicon.png"/>
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
<meta name="docsearch:version" content="1.0.0rc6" />
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<dialog id="pst-search-dialog">
<form class="bd-search d-flex align-items-center"
action="../../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form>
</dialog>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
<div class="bd-header__inner bd-page-width">
<button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
<span class="fa-solid fa-bars"></span>
</button>
<div class="col-lg-3 navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="../../../index.html">
<img src="../../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
<img src="../../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
<p class="title logo__title">TensorRT-LLM</p>
</a></div>
</div>
<div class="col-lg-9 navbar-header-items">
<div class="me-auto navbar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-2"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-2"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-2"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-2">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="navbar-header-items__end">
<div class="navbar-item navbar-persistent--container">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="navbar-persistent--mobile">
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
</div>
</div>
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<dialog id="pst-primary-sidebar-modal"></dialog>
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
<a class="navbar-brand logo" href="../../../index.html">
<img src="../../../_static/nvidia-logo-horiz-rgb-blk-for-screen.svg" class="logo__image only-light" alt="TensorRT-LLM - Home"/>
<img src="../../../_static/nvidia-logo-horiz-rgb-wht-for-screen.svg" class="logo__image only-dark pst-js-only" alt="TensorRT-LLM - Home"/>
<p class="title logo__title">TensorRT-LLM</p>
</a>
<div class="sidebar-header-items sidebar-primary__section">
<div class="sidebar-header-items__center">
<div class="navbar-item">
<div class="version-switcher__container dropdown pst-js-only">
<button id="pst-version-switcher-button-3"
type="button"
class="version-switcher__button btn btn-sm dropdown-toggle"
data-bs-toggle="dropdown"
aria-haspopup="listbox"
aria-controls="pst-version-switcher-list-3"
aria-label="Version switcher list"
>
Choose version <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div id="pst-version-switcher-list-3"
class="version-switcher__menu dropdown-menu list-group-flush py-0"
role="listbox" aria-labelledby="pst-version-switcher-button-3">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div></div>
</div>
<div class="sidebar-header-items__end">
<div class="navbar-item">
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
</button></div>
</div>
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<nav class="bd-docs-nav bd-links"
aria-label="Table of Contents">
<p class="bd-links__title" role="heading" aria-level="1">Table of Contents</p>
<div class="bd-toc-item navbar-nav"><p aria-level="2" class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../quick-start-guide.html">Quick Start Guide</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../key-features.html">Key Features</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../torch.html">PyTorch Backend</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../release-notes.html">Release Notes</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Installation</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../installation/containers.html">Pre-built release container images on NGC</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../installation/linux.html">Installing on Linux via <code class="docutils literal notranslate"><span class="pre">pip</span></code></a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">LLM API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api/index.html">LLM API Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api/reference.html">API Reference</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Examples</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../examples/index.html">LLM Examples Introduction</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="simple">
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../examples/customization.html">LLM Common Customizations</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../examples/llm_api_examples.html">LLM Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference.html">Generate text</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_async.html">Generate text asynchronously</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_async_streaming.html">Generate text in streaming</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_logits_processor.html">Control generated text using logits processor</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_speculative_decoding.html">Speculative Decoding</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_runtime.html">Runtime Configuration Examples</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_sampling.html">Sampling Techniques Showcase</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_llm_distributed.html">Run LLM-API with pytorch backend on Slurm</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_trtllm_bench.html">Run trtllm-bench with pytorch backend on Slurm</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/llm_mgmn_trtllm_serve.html">Run trtllm-serve with pytorch backend on Slurm</a></li>
</ul>
</details></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../examples/trtllm_serve_examples.html">Online Serving Examples</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/curl_chat_client.html">Curl Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/curl_chat_client_for_multimodal.html">Curl Chat Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/curl_completion_client.html">Curl Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/genai_perf_client.html">Genai Perf Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/genai_perf_client_for_multimodal.html">Genai Perf Client For Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_chat_client.html">OpenAI Chat Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_chat_client_for_multimodal.html">OpenAI Chat Client for Multimodal</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client_for_lora.html">Openai Completion Client For Lora</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../examples/openai_completion_client_json_schema.html">OpenAI Completion Client with JSON Schema</a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Model Definition API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../python-api/tensorrt_llm.layers.html">Layers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../python-api/tensorrt_llm.functional.html">Functionals</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../python-api/tensorrt_llm.models.html">Models</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../python-api/tensorrt_llm.plugin.html">Plugin</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../python-api/tensorrt_llm.quantization.html">Quantization</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../python-api/tensorrt_llm.runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">C++ API</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/executor.html">Executor</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/runtime.html">Runtime</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-bench.html">trtllm-bench</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-build.html">trtllm-build</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../commands/trtllm-serve/index.html">trtllm-serve</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../commands/trtllm-serve/trtllm-serve.html">trtllm-serve</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../commands/trtllm-serve/run-benchmark-with-trtllm-serve.html">Run benchmarking with <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code></a></li>
</ul>
</details></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Architecture</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/overview.html">TensorRT-LLM Architecture</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/core-concepts.html">Model Definition</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/checkpoint.html">TensorRT-LLM Checkpoint</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/workflow.html">TensorRT-LLM Build Workflow</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/add-model.html">Adding a Model</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Advanced</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/gpt-attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/gpt-runtime.html">C++ GPT Runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/executor.html">Executor API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/graph-rewriting.html">Graph Rewriting Module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/lora.html">Run gpt-2b + LoRA using Executor / cpp runtime</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/expert-parallelism.html">Expert Parallelism in TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/kv-cache-management.html">KV Cache Management: Pools, Blocks, and Events</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/kv-cache-reuse.html">KV cache reuse</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/speculative-decoding.html">Speculative Sampling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/disaggregated-service.html">Disaggregated-Service (Experimental)</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Performance</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-benchmarking.html">Benchmarking</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../performance/performance-tuning-guide/index.html">Performance Tuning Guide</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/benchmarking-default-performance.html">Benchmarking Default Performance</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/useful-build-time-flags.html">Useful Build-Time Flags</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/tuning-max-batch-size-and-max-num-tokens.html">Tuning Max Batch Size and Max Num Tokens</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/deciding-model-sharding-strategy.html">Deciding Model Sharding Strategy</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/fp8-quantization.html">FP8 Quantization</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../performance/performance-tuning-guide/useful-runtime-flags.html">Useful Runtime Options</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-analysis.html">Performance Analysis</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Reference</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../reference/troubleshooting.html">Troubleshooting</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../reference/support-matrix.html">Support Matrix</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../reference/precision.html">Numerical Precision</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../reference/memory.html">Memory Usage of TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../reference/ci-overview.html">Continuous Integration Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../reference/dev-containers.html">Using Dev Containers</a></li>
</ul>
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Blogs</span></p>
<ul class="nav bd-sidenav">
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/Falcon180B-H200.html">Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/quantization-in-TRT-LLM.html">Speed up inference with SOTA quantization techniques in TRT-LLM</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog1_Pushing_Latency_Boundaries_Optimizing_DeepSeek-R1_Performance_on_NVIDIA_B200_GPUs.html">Pushing Latency Boundaries: Optimizing DeepSeek-R1 Performance on NVIDIA B200 GPUs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/tech_blog/blog2_DeepSeek_R1_MTP_Implementation_and_Optimization.html">DeepSeek R1 MTP Implementation and Optimization</a></li>
</ul>
</div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item">
<nav aria-label="Breadcrumb" class="d-print-none">
<ul class="bd-breadcrumbs">
<li class="breadcrumb-item breadcrumb-home">
<a href="../../../index.html" class="nav-link" aria-label="Home">
<i class="fa-solid fa-home"></i>
</a>
</li>
<li class="breadcrumb-item"><a href="../../index.html" class="nav-link">Module code</a></li>
<li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">tensorrt_llm.llmapi.build_cache</span></li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<h1>Source code for tensorrt_llm.llmapi.build_cache</h1><div class="highlight"><pre>
<span></span><span class="kn">import</span><span class="w"> </span><span class="nn">contextlib</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">datetime</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">enum</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">hashlib</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">json</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">shutil</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">dataclasses</span><span class="w"> </span><span class="kn">import</span> <span class="n">dataclass</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pathlib</span><span class="w"> </span><span class="kn">import</span> <span class="n">Path</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Optional</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">filelock</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">tensorrt_llm</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm</span><span class="w"> </span><span class="kn">import</span> <span class="n">BuildConfig</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.llmapi.utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">enable_llm_debug</span><span class="p">,</span> <span class="n">print_colored</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">tensorrt_llm.logger</span><span class="w"> </span><span class="kn">import</span> <span class="n">logger</span>
<span class="k">def</span><span class="w"> </span><span class="nf">get_build_cache_config_from_env</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="nb">tuple</span><span class="p">[</span><span class="nb">bool</span><span class="p">,</span> <span class="nb">str</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Get the build cache configuration from the environment variables</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">build_cache_enabled</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;TLLM_LLMAPI_BUILD_CACHE&#39;</span><span class="p">)</span> <span class="o">==</span> <span class="s1">&#39;1&#39;</span>
<span class="n">build_cache_root</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span>
<span class="s1">&#39;TLLM_LLMAPI_BUILD_CACHE_ROOT&#39;</span><span class="p">,</span>
<span class="s1">&#39;/tmp/.cache/tensorrt_llm/llmapi/&#39;</span><span class="p">)</span> <span class="c1"># nosec B108</span>
<span class="k">return</span> <span class="n">build_cache_enabled</span><span class="p">,</span> <span class="n">build_cache_root</span>
<div class="viewcode-block" id="BuildCacheConfig">
<a class="viewcode-back" href="../../../llm-api/reference.html#tensorrt_llm.llmapi.BuildCacheConfig">[docs]</a>
<span class="k">class</span><span class="w"> </span><span class="nc">BuildCacheConfig</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Configuration for the build cache.</span>
<span class="sd"> Attributes:</span>
<span class="sd"> cache_root (str): The root directory for the build cache.</span>
<span class="sd"> max_records (int): The maximum number of records to store in the cache.</span>
<span class="sd"> max_cache_storage_gb (float): The maximum amount of storage (in GB) to use for the cache.</span>
<span class="sd"> Note:</span>
<span class="sd"> The build-cache assumes the weights of the model are not changed during the execution. If the weights are</span>
<span class="sd"> changed, you should remove the caches manually.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="BuildCacheConfig.__init__">
<a class="viewcode-back" href="../../../llm-api/reference.html#tensorrt_llm.llmapi.BuildCacheConfig.__init__">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">cache_root</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Path</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">max_records</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10</span><span class="p">,</span>
<span class="n">max_cache_storage_gb</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mi">256</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cache_root</span> <span class="o">=</span> <span class="n">cache_root</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_max_records</span> <span class="o">=</span> <span class="n">max_records</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_max_cache_storage_gb</span> <span class="o">=</span> <span class="n">max_cache_storage_gb</span></div>
<span class="nd">@property</span>
<span class="k">def</span><span class="w"> </span><span class="nf">cache_root</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Path</span><span class="p">:</span>
<span class="n">_build_cache_enabled</span><span class="p">,</span> <span class="n">_build_cache_root</span> <span class="o">=</span> <span class="n">get_build_cache_config_from_env</span><span class="p">(</span>
<span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cache_root</span> <span class="ow">or</span> <span class="n">Path</span><span class="p">(</span><span class="n">_build_cache_root</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span><span class="w"> </span><span class="nf">max_records</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_records</span>
<span class="nd">@property</span>
<span class="k">def</span><span class="w"> </span><span class="nf">max_cache_storage_gb</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_cache_storage_gb</span></div>
<span class="k">class</span><span class="w"> </span><span class="nc">BuildCache</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The BuildCache class is a class that manages the intermediate products from the build steps.</span>
<span class="sd"> NOTE: currently, only engine-building is supported</span>
<span class="sd"> TODO[chunweiy]: add support for other build steps, such as quantization, convert_checkpoint, etc.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># The version of the cache, will be used to determine if the cache is compatible</span>
<span class="n">CACHE_VERSION</span> <span class="o">=</span> <span class="mi">0</span>
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">config</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">BuildCacheConfig</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
<span class="n">_</span><span class="p">,</span> <span class="n">default_cache_root</span> <span class="o">=</span> <span class="n">get_build_cache_config_from_env</span><span class="p">()</span>
<span class="n">config</span> <span class="o">=</span> <span class="n">config</span> <span class="ow">or</span> <span class="n">BuildCacheConfig</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cache_root</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">cache_root</span> <span class="ow">or</span> <span class="n">Path</span><span class="p">(</span><span class="n">default_cache_root</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">max_records</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">max_records</span>
<span class="bp">self</span><span class="o">.</span><span class="n">max_cache_storage_gb</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">max_cache_storage_gb</span>
<span class="k">if</span> <span class="n">config</span><span class="o">.</span><span class="n">max_records</span> <span class="o">&lt;</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;max_records should be greater than 0&quot;</span><span class="p">)</span>
<span class="k">def</span><span class="w"> </span><span class="nf">free_storage_in_gb</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">float</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39; Get the free storage capacity of the cache. &#39;&#39;&#39;</span>
<span class="c1"># measure the root directory</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">cache_root</span><span class="o">.</span><span class="n">parent</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
<span class="n">usage</span> <span class="o">=</span> <span class="n">shutil</span><span class="o">.</span><span class="n">disk_usage</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">cache_root</span><span class="o">.</span><span class="n">parent</span><span class="p">)</span>
<span class="k">return</span> <span class="n">usage</span><span class="o">.</span><span class="n">free</span> <span class="o">/</span> <span class="mi">1024</span><span class="o">**</span><span class="mi">3</span>
<span class="k">return</span> <span class="mi">0</span>
<span class="k">def</span><span class="w"> </span><span class="nf">get_engine_building_cache_stage</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">build_config</span><span class="p">:</span> <span class="n">BuildConfig</span><span class="p">,</span>
<span class="n">model_path</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Path</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">force_rebuild</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s1">&#39;CachedStage&#39;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> Get the build step for engine building.</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="n">build_config_str</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">prune_build_config_for_cache_key</span><span class="p">(</span>
<span class="n">build_config</span><span class="o">.</span><span class="n">to_dict</span><span class="p">()),</span>
<span class="n">sort_keys</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">kwargs_str</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">kwargs</span><span class="p">,</span> <span class="n">sort_keys</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">return</span> <span class="n">CachedStage</span><span class="p">(</span><span class="n">parent</span><span class="o">=</span><span class="bp">self</span><span class="p">,</span>
<span class="n">kind</span><span class="o">=</span><span class="n">CacheRecord</span><span class="o">.</span><span class="n">Kind</span><span class="o">.</span><span class="n">Engine</span><span class="p">,</span>
<span class="n">cache_root</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">cache_root</span><span class="p">,</span>
<span class="n">force_rebuild</span><span class="o">=</span><span class="n">force_rebuild</span><span class="p">,</span>
<span class="n">inputs</span><span class="o">=</span><span class="p">[</span><span class="n">build_config_str</span><span class="p">,</span> <span class="n">model_path</span><span class="p">,</span> <span class="n">kwargs_str</span><span class="p">])</span>
<span class="k">def</span><span class="w"> </span><span class="nf">prune_caches</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">has_incoming_record</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> Clean up the cache records to make sure the cache size is within the limit</span>
<span class="sd"> Args:</span>
<span class="sd"> has_incoming_record (bool): If the cache has incoming record, the existing records will be further pruned to</span>
<span class="sd"> reserve space for the incoming record</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">cache_root</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
<span class="k">return</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_clean_up_cache_dir</span><span class="p">()</span>
<span class="n">records</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="nb">dir</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">cache_root</span><span class="o">.</span><span class="n">iterdir</span><span class="p">():</span>
<span class="n">records</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_load_cache_record</span><span class="p">(</span><span class="nb">dir</span><span class="p">))</span>
<span class="n">records</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">key</span><span class="o">=</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">time</span><span class="p">,</span> <span class="n">reverse</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">max_records</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_records</span> <span class="o">-</span> <span class="mi">1</span> <span class="k">if</span> <span class="n">has_incoming_record</span> <span class="k">else</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_records</span>
<span class="c1"># prune the cache to meet max_records and max_cache_storage_gb limitation</span>
<span class="k">while</span> <span class="nb">len</span><span class="p">(</span><span class="n">records</span><span class="p">)</span> <span class="o">&gt;</span> <span class="n">max_records</span> <span class="ow">or</span> <span class="nb">sum</span><span class="p">(</span>
<span class="n">r</span><span class="o">.</span><span class="n">storage_gb</span> <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">records</span><span class="p">)</span> <span class="o">&gt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_cache_storage_gb</span><span class="p">:</span>
<span class="n">record</span> <span class="o">=</span> <span class="n">records</span><span class="o">.</span><span class="n">pop</span><span class="p">()</span>
<span class="c1"># remove the directory and its content</span>
<span class="n">shutil</span><span class="o">.</span><span class="n">rmtree</span><span class="p">(</span><span class="n">record</span><span class="o">.</span><span class="n">path</span><span class="p">)</span>
<span class="nd">@staticmethod</span>
<span class="k">def</span><span class="w"> </span><span class="nf">prune_build_config_for_cache_key</span><span class="p">(</span><span class="n">build_config</span><span class="p">:</span> <span class="nb">dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">dict</span><span class="p">:</span>
<span class="c1"># The BuildCache will be disabled once auto_pp is enabled, so &#39;auto_parallel_config&#39; should be removed</span>
<span class="n">black_list</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;auto_parallel_config&#39;</span><span class="p">,</span> <span class="s1">&#39;dry_run&#39;</span><span class="p">]</span>
<span class="n">dic</span> <span class="o">=</span> <span class="n">build_config</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">black_list</span><span class="p">:</span>
<span class="k">if</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">dic</span><span class="p">:</span>
<span class="n">dic</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
<span class="k">return</span> <span class="n">dic</span>
<span class="k">def</span><span class="w"> </span><span class="nf">load_cache_records</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="s2">&quot;CacheRecord&quot;</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> Load all the cache records from the cache directory</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="n">records</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">cache_root</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
<span class="k">return</span> <span class="n">records</span>
<span class="k">for</span> <span class="nb">dir</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">cache_root</span><span class="o">.</span><span class="n">iterdir</span><span class="p">():</span>
<span class="n">records</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_load_cache_record</span><span class="p">(</span><span class="nb">dir</span><span class="p">))</span>
<span class="k">return</span> <span class="n">records</span>
<span class="k">def</span><span class="w"> </span><span class="nf">_load_cache_record</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cache_dir</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;CacheRecord&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> Get the cache record from the cache directory</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="n">metadata</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">((</span><span class="n">cache_dir</span> <span class="o">/</span> <span class="s1">&#39;metadata.json&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">read_text</span><span class="p">())</span>
<span class="n">storage_gb</span> <span class="o">=</span> <span class="nb">sum</span><span class="p">(</span><span class="n">f</span><span class="o">.</span><span class="n">stat</span><span class="p">()</span><span class="o">.</span><span class="n">st_size</span> <span class="k">for</span> <span class="n">f</span> <span class="ow">in</span> <span class="n">cache_dir</span><span class="o">.</span><span class="n">glob</span><span class="p">(</span><span class="s1">&#39;**/*&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">f</span><span class="o">.</span><span class="n">is_file</span><span class="p">())</span> <span class="o">/</span> <span class="mi">1024</span><span class="o">**</span><span class="mi">3</span>
<span class="k">return</span> <span class="n">CacheRecord</span><span class="p">(</span><span class="n">kind</span><span class="o">=</span><span class="n">CacheRecord</span><span class="o">.</span><span class="n">Kind</span><span class="o">.</span><span class="n">__members__</span><span class="p">[</span><span class="n">metadata</span><span class="p">[</span><span class="s1">&#39;kind&#39;</span><span class="p">]],</span>
<span class="n">storage_gb</span><span class="o">=</span><span class="n">storage_gb</span><span class="p">,</span>
<span class="n">path</span><span class="o">=</span><span class="n">cache_dir</span><span class="p">,</span>
<span class="n">time</span><span class="o">=</span><span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="o">.</span><span class="n">fromisoformat</span><span class="p">(</span>
<span class="n">metadata</span><span class="p">[</span><span class="s1">&#39;datetime&#39;</span><span class="p">]))</span>
<span class="k">def</span><span class="w"> </span><span class="nf">_clean_up_cache_dir</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> Clean up the files in the cache directory, remove anything that is not in the cache</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="c1"># get all the files and directies in the cache_root</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">cache_root</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
<span class="k">return</span>
<span class="k">for</span> <span class="n">file_or_dir</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">cache_root</span><span class="o">.</span><span class="n">iterdir</span><span class="p">():</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_cache_valid</span><span class="p">(</span><span class="n">file_or_dir</span><span class="p">):</span>
<span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Removing invalid cache directory </span><span class="si">{</span><span class="nb">dir</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">file_or_dir</span><span class="o">.</span><span class="n">is_file</span><span class="p">():</span>
<span class="n">file_or_dir</span><span class="o">.</span><span class="n">unlink</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">shutil</span><span class="o">.</span><span class="n">rmtree</span><span class="p">(</span><span class="n">file_or_dir</span><span class="p">)</span>
<span class="k">def</span><span class="w"> </span><span class="nf">is_cache_valid</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cache_dir</span><span class="p">:</span> <span class="n">Path</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> Check if the cache directory is valid</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">cache_dir</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="n">metadata_path</span> <span class="o">=</span> <span class="n">cache_dir</span> <span class="o">/</span> <span class="s1">&#39;metadata.json&#39;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">metadata_path</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="n">metadata</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">metadata_path</span><span class="o">.</span><span class="n">read_text</span><span class="p">())</span>
<span class="k">if</span> <span class="n">metadata</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;version&#39;</span><span class="p">)</span> <span class="o">!=</span> <span class="n">BuildCache</span><span class="o">.</span><span class="n">CACHE_VERSION</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="n">content</span> <span class="o">=</span> <span class="n">cache_dir</span> <span class="o">/</span> <span class="s1">&#39;content&#39;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">content</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="nd">@dataclass</span>
<span class="k">class</span><span class="w"> </span><span class="nc">CachedStage</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> CachedStage is a class that represents a stage in the build process, it helps to manage the intermediate product.</span>
<span class="sd"> The cache is organized as follows:</span>
<span class="sd"> this_cache_dir/ # name is like &quot;engine-&lt;hash&gt;&quot;</span>
<span class="sd"> metadata.json # the metadata of the cache</span>
<span class="sd"> content/ # the actual product of the build step, such trt-llm engine directory</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="c1"># The parent should be kept alive by CachedStep instance</span>
<span class="n">parent</span><span class="p">:</span> <span class="n">BuildCache</span>
<span class="n">cache_root</span><span class="p">:</span> <span class="n">Path</span>
<span class="c1"># The inputs will be used to determine if the step needs to be re-run, so all the variables should be put here</span>
<span class="n">inputs</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">Any</span><span class="p">]</span>
<span class="n">kind</span><span class="p">:</span> <span class="s2">&quot;CacheRecord.Kind&quot;</span>
<span class="c1"># If force_rebuild is set to True, the cache will be ignored</span>
<span class="n">force_rebuild</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span>
<span class="k">def</span><span class="w"> </span><span class="nf">get_hash_key</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">lib_version</span> <span class="o">=</span> <span class="n">tensorrt_llm</span><span class="o">.</span><span class="n">__version__</span>
<span class="n">input_strs</span> <span class="o">=</span> <span class="p">[</span><span class="nb">str</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">inputs</span><span class="p">]</span>
<span class="k">return</span> <span class="n">hashlib</span><span class="o">.</span><span class="n">md5</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">lib_version</span><span class="si">}</span><span class="s2">-</span><span class="si">{</span><span class="n">input_strs</span><span class="si">}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">encode</span><span class="p">())</span><span class="o">.</span><span class="n">hexdigest</span><span class="p">()</span> <span class="c1"># nosec B324</span>
<span class="k">def</span><span class="w"> </span><span class="nf">get_cache_path</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Path</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> The path to the product of the build step, will be overwritten if the step is re-run</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">cache_root</span> <span class="o">/</span> <span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">kind</span><span class="o">.</span><span class="n">value</span><span class="si">}</span><span class="s2">-</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">get_hash_key</span><span class="p">()</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="k">def</span><span class="w"> </span><span class="nf">get_engine_path</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Path</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_cache_path</span><span class="p">()</span> <span class="o">/</span> <span class="s1">&#39;content&#39;</span>
<span class="k">def</span><span class="w"> </span><span class="nf">get_cache_metadata</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">dict</span><span class="p">:</span>
<span class="n">res</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;version&quot;</span><span class="p">:</span> <span class="n">BuildCache</span><span class="o">.</span><span class="n">CACHE_VERSION</span><span class="p">,</span>
<span class="s2">&quot;datetime&quot;</span><span class="p">:</span> <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span><span class="o">.</span><span class="n">isoformat</span><span class="p">(),</span>
<span class="s2">&quot;kind&quot;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">kind</span><span class="o">.</span><span class="n">name</span><span class="p">,</span>
<span class="p">}</span>
<span class="k">return</span> <span class="n">res</span>
<span class="k">def</span><span class="w"> </span><span class="nf">is_cached</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> Check if the product of the build step is in the cache</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">force_rebuild</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_cache_path</span><span class="p">()</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
<span class="n">metadata</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span>
<span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_cache_path</span><span class="p">()</span> <span class="o">/</span> <span class="s1">&#39;metadata.json&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">read_text</span><span class="p">())</span>
<span class="k">if</span> <span class="n">metadata</span><span class="p">[</span><span class="s2">&quot;version&quot;</span><span class="p">]</span> <span class="o">==</span> <span class="n">BuildCache</span><span class="o">.</span><span class="n">CACHE_VERSION</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">except</span><span class="p">:</span>
<span class="k">pass</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="nd">@contextlib</span><span class="o">.</span><span class="n">contextmanager</span>
<span class="k">def</span><span class="w"> </span><span class="nf">write_guard</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39; Guard the cache writing process.</span>
<span class="sd"> The cache writing process should be atomic, so the filelock is used to protect the cache writing process. And</span>
<span class="sd"> the cache metadata will be written to the cache directory.</span>
<span class="sd"> Args:</span>
<span class="sd"> final_engien_dir: the final engine directory</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">parent</span><span class="o">.</span><span class="n">prune_caches</span><span class="p">(</span><span class="n">has_incoming_record</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">target_dir</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_cache_path</span><span class="p">()</span>
<span class="k">if</span> <span class="n">enable_llm_debug</span><span class="p">():</span>
<span class="n">print_colored</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Writing cache to </span><span class="si">{</span><span class="n">target_dir</span><span class="si">}</span><span class="se">\n</span><span class="s2">&quot;</span><span class="p">,</span> <span class="s2">&quot;yellow&quot;</span><span class="p">)</span>
<span class="c1"># To avoid the cache modification conflict, a dummy directory is used to write the cache, and then rename it to</span>
<span class="c1"># the target directory</span>
<span class="n">dummy_target_dir</span> <span class="o">=</span> <span class="n">Path</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">target_dir</span><span class="o">.</span><span class="n">parent</span><span class="si">}</span><span class="s2">/</span><span class="si">{</span><span class="n">target_dir</span><span class="o">.</span><span class="n">name</span><span class="si">}</span><span class="s2">.dummy&quot;</span><span class="p">)</span>
<span class="n">dummy_target_dir</span><span class="o">.</span><span class="n">mkdir</span><span class="p">(</span><span class="n">parents</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">exist_ok</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="c1"># TODO[chunweiy]: deal with the cache modification conflict</span>
<span class="n">lock</span> <span class="o">=</span> <span class="n">filelock</span><span class="o">.</span><span class="n">FileLock</span><span class="p">(</span><span class="n">dummy_target_dir</span> <span class="o">/</span> <span class="s1">&#39;.filelock&#39;</span><span class="p">,</span> <span class="n">timeout</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">dummy_target_dir</span> <span class="o">/</span> <span class="s1">&#39;metadata.json&#39;</span><span class="p">,</span> <span class="s1">&#39;w&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_cache_metadata</span><span class="p">()))</span>
<span class="k">with</span> <span class="n">lock</span><span class="p">:</span>
<span class="k">yield</span> <span class="n">dummy_target_dir</span> <span class="o">/</span> <span class="s1">&#39;content&#39;</span>
<span class="c1"># If engine building is successful, rename the dummy directory to the target directory</span>
<span class="k">if</span> <span class="n">target_dir</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
<span class="n">shutil</span><span class="o">.</span><span class="n">rmtree</span><span class="p">(</span><span class="n">target_dir</span><span class="p">)</span>
<span class="n">shutil</span><span class="o">.</span><span class="n">move</span><span class="p">(</span><span class="n">dummy_target_dir</span><span class="p">,</span> <span class="n">target_dir</span><span class="p">)</span>
<span class="nd">@dataclass</span><span class="p">(</span><span class="n">unsafe_hash</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">class</span><span class="w"> </span><span class="nc">CacheRecord</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;</span>
<span class="sd"> CacheRecord is a class that represents a record in the cache directory.</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="k">class</span><span class="w"> </span><span class="nc">Kind</span><span class="p">(</span><span class="n">enum</span><span class="o">.</span><span class="n">Enum</span><span class="p">):</span>
<span class="n">Engine</span> <span class="o">=</span> <span class="s1">&#39;engine&#39;</span>
<span class="n">Checkpoint</span> <span class="o">=</span> <span class="s1">&#39;checkpoint&#39;</span>
<span class="n">kind</span><span class="p">:</span> <span class="n">Kind</span>
<span class="n">storage_gb</span><span class="p">:</span> <span class="nb">float</span>
<span class="n">path</span><span class="p">:</span> <span class="n">Path</span>
<span class="n">time</span><span class="p">:</span> <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span>
</pre></div>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
</div>
</footer>
</div>
<div class="bd-sidebar-secondary"></div>
</div>
<footer class="bd-footer-content">
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script defer src="../../../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf"></script>
<script defer src="../../../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf"></script>
<footer class="bd-footer">
<div class="bd-footer__inner bd-page-width">
<div class="footer-items__start">
<div class="footer-item">
<a class="footer-brand logo" href="https://www.nvidia.com">
<img src="../../../_static/nvidia-logo-horiz-rgb-1c-blk-for-screen.svg" class="logo__image only-light" alt="NVIDIA"/>
<img src="../../../_static/nvidia-logo-horiz-rgb-1c-wht-for-screen.svg" class="logo__image only-dark" alt="NVIDIA"/>
</a></div>
<div class="footer-item">
<div class="footer-links">
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/">Privacy Policy</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/privacy-center/">Manage My Privacy</a>
|
<a class="external" href="https://www.nvidia.com/en-us/preferences/start/">Do Not Sell or Share My Data</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/terms-of-service/">Terms of Service</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/accessibility/">Accessibility</a>
|
<a class="external" href="https://www.nvidia.com/en-us/about-nvidia/company-policies/">Corporate Policies</a>
|
<a class="external" href="https://www.nvidia.com/en-us/product-security/">Product Security</a>
|
<a class="external" href="https://www.nvidia.com/en-us/contact/">Contact</a>
</div>
</div>
<div class="footer-item">
<p class="copyright">
Copyright © 2025, NVidia.
<br/>
</p>
</div>
<div class="footer-item">
<div class="extra_footer">
<p>Last updated on August 06, 2025.</p>
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/a16ba64">a16ba64</a>.</p>
</div></div>
</div>
</div>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink