mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-24 12:42:54 +08:00
835 lines
48 KiB
HTML
835 lines
48 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>KV Cache Connector — 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 = 'features/kv-cache-connector';</script>
|
||
<script>
|
||
DOCUMENTATION_OPTIONS.theme_version = '0.16.1';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_json_url = './_static/switcher.json';
|
||
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '1.2.0rc5';
|
||
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="Architecture Overview" href="../developer-guide/overview.html" />
|
||
<link rel="prev" title="Helix Parallelism" href="helix.html" />
|
||
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
||
<meta name="docsearch:language" content="en"/>
|
||
<meta name="docsearch:version" content="1.2.0rc5" />
|
||
|
||
|
||
</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/deepseek_r1_reasoning_parser.html">Deepseek R1 Reasoning Parser</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/genai_perf_client.html">Genai Perf Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/genai_perf_client_for_multimodal.html">Genai Perf Client For Multimodal</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_chat_client.html">OpenAI Chat Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_chat_client_for_multimodal.html">OpenAI Chat Client for Multimodal</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_completion_client.html">OpenAI Completion Client</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_completion_client_for_lora.html">Openai Completion Client For Lora</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../examples/openai_completion_client_json_schema.html">OpenAI Completion Client with JSON Schema</a></li>
|
||
</ul>
|
||
</details></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../examples/dynamo_k8s_example.html">Dynamo K8s Example</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../deployment-guide/index.html">Model Recipes</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-deepseek-r1-on-trtllm.html">Deployment Guide for DeepSeek R1 on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-llama3.3-70b-on-trtllm.html">Deployment Guide for Llama3.3 70B on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-llama4-scout-on-trtllm.html">Deployment Guide for Llama4 Scout 17B on TensorRT LLM - Blackwell & Hopper Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-gpt-oss-on-trtllm.html">Deployment Guide for GPT-OSS on TensorRT-LLM - Blackwell Hardware</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../deployment-guide/deployment-guide-for-qwen3-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="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-bench.html">trtllm-bench</a></li>
|
||
|
||
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-eval.html">trtllm-eval</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../commands/trtllm-serve/index.html">trtllm-serve</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../commands/trtllm-serve/trtllm-serve.html">trtllm-serve</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../commands/trtllm-serve/run-benchmark-with-trtllm-serve.html">Run benchmarking with <code class="docutils literal notranslate"><span class="pre">trtllm-serve</span></code></a></li>
|
||
</ul>
|
||
</details></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">API Reference</span></p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="../llm-api/index.html">LLM API Introduction</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../llm-api/reference.html">API Reference</a></li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Features</span></p>
|
||
<ul class="current nav bd-sidenav">
|
||
<li class="toctree-l1"><a class="reference internal" href="feature-combination-matrix.html">Feature Combination Matrix</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="disagg-serving.html">Disaggregated Serving</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="kvcache.html">KV Cache System</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="long-sequence.html">Long Sequences</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="lora.html">LoRA (Low-Rank Adaptation)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="multi-modality.html">Multimodal Support in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="overlap-scheduler.html">Overlap Scheduler</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="paged-attention-ifb-scheduler.html">Paged Attention, IFB, and Request Scheduling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="parallel-strategy.html">Parallelism in TensorRT LLM</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="quantization.html">Quantization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="sampling.html">Sampling</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="additional-outputs.html">Additional Outputs</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="guided-decoding.html">Guided Decoding</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="speculative-decoding.html">Speculative Decoding</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="checkpoint-loading.html">Checkpoint Loading</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="auto_deploy/auto-deploy.html">AutoDeploy (Prototype)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="ray-orchestrator.html">Ray Orchestrator (Prototype)</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="torch_compile_and_piecewise_cuda_graph.html">Torch Compile & Piecewise CUDA Graph</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="helix.html">Helix Parallelism</a></li>
|
||
<li class="toctree-l1 current active"><a class="current reference internal" href="#">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">KV Cache Connector</span></li>
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<div id="searchbox"></div>
|
||
<article class="bd-article">
|
||
|
||
<section class="tex2jax_ignore mathjax_ignore" id="kv-cache-connector">
|
||
<h1>KV Cache Connector<a class="headerlink" href="#kv-cache-connector" title="Link to this heading">#</a></h1>
|
||
<p>The KV Cache Connector is a flexible interface in TensorRT-LLM that enables remote or external access to the Key-Value (KV) cache. It allows developers to implement custom logic for loading, saving, and managing KV cache blocks, extending the capabilities of the standard KV cache manager.</p>
|
||
<p>This document explains the KV Cache Connector architecture, common use cases, and provides a detailed walkthrough of the included example.</p>
|
||
<section id="use-cases">
|
||
<h2>Use Cases<a class="headerlink" href="#use-cases" title="Link to this heading">#</a></h2>
|
||
<p>The KV Cache Connector is designed to support a variety of advanced serving scenarios:</p>
|
||
<ol class="arabic simple">
|
||
<li><p><strong>KV Cache Offloading</strong>: Move KV cache blocks from GPU memory to cheaper/larger storage (CPU RAM, NVMe SSD, or network storage) when they are not immediately needed, and reload them when required.</p></li>
|
||
<li><p><strong>Custom Disaggregated Serving</strong>: Separate the prefill (context processing) and decode (token generation) phases onto different instances or machines. The connector can be used to transmit the KV cache generated during prefill to the decode instances.</p></li>
|
||
<li><p><strong>KV Cache Sharing / P2P Transfer</strong>: Share KV cache states between different model instances or across peer-to-peer connections.</p></li>
|
||
</ol>
|
||
</section>
|
||
<section id="architecture">
|
||
<h2>Architecture<a class="headerlink" href="#architecture" title="Link to this heading">#</a></h2>
|
||
<p>The connector architecture is split into two main components:</p>
|
||
<ul class="simple">
|
||
<li><p><strong>Scheduler (Leader)</strong>: Responsible for orchestration. It decides <em>what</em> needs to be loaded or saved and builds metadata instructions. It runs only on the leader rank (rank 0).</p></li>
|
||
<li><p><strong>Worker</strong>: Responsible for execution. It receives metadata from the scheduler and performs the actual data transfers (loading/saving) on the KV cache tensors. It runs on all ranks.</p></li>
|
||
</ul>
|
||
<section id="api-reference">
|
||
<h3>API Reference<a class="headerlink" href="#api-reference" title="Link to this heading">#</a></h3>
|
||
<p>To implement a custom connector, you must subclass <code class="docutils literal notranslate"><span class="pre">KvCacheConnectorScheduler</span></code> and <code class="docutils literal notranslate"><span class="pre">KvCacheConnectorWorker</span></code>.</p>
|
||
<section id="scheduler-leader-interface-kvcacheconnectorscheduler">
|
||
<h4>1. Scheduler (Leader) Interface (<code class="docutils literal notranslate"><span class="pre">KvCacheConnectorScheduler</span></code>)<a class="headerlink" href="#scheduler-leader-interface-kvcacheconnectorscheduler" title="Link to this heading">#</a></h4>
|
||
<p>These methods run on the leader process and drive the connector’s behavior.</p>
|
||
<ul class="simple">
|
||
<li><p><strong><code class="docutils literal notranslate"><span class="pre">build_connector_meta(self,</span> <span class="pre">scheduler_output:</span> <span class="pre">SchedulerOutput)</span> <span class="pre">-></span> <span class="pre">object</span></code></strong></p>
|
||
<ul>
|
||
<li><p><strong>Description</strong>: The core orchestration method. Called during the scheduling phase. It examines the current requests and decides which blocks need to be loaded from or saved to the external store.</p></li>
|
||
<li><p><strong>Arguments</strong>: <code class="docutils literal notranslate"><span class="pre">scheduler_output</span></code> contains information about new requests, blocks allocated, and current request states.</p></li>
|
||
<li><p><strong>Returns</strong>: An arbitrary metadata object (picklable) that describes the tasks for the workers. This object is broadcasted to all workers.</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p><strong><code class="docutils literal notranslate"><span class="pre">get_num_new_matched_tokens(self,</span> <span class="pre">request:</span> <span class="pre">LlmRequest,</span> <span class="pre">num_computed_tokens:</span> <span class="pre">int)</span> <span class="pre">-></span> <span class="pre">tuple[int,</span> <span class="pre">bool]</span></code></strong></p>
|
||
<ul>
|
||
<li><p><strong>Description</strong>: Called when a new request arrives. It checks to see if any KV cache can be loaded from an external KV store.</p></li>
|
||
<li><p><strong>Returns</strong>: A tuple <code class="docutils literal notranslate"><span class="pre">(num_tokens,</span> <span class="pre">is_async)</span></code>. <code class="docutils literal notranslate"><span class="pre">num_tokens</span></code> is the number of tokens found in the external cache. <code class="docutils literal notranslate"><span class="pre">is_async</span></code> indicates if the loading will happen asynchronously (background) or requires blocking.</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p><strong><code class="docutils literal notranslate"><span class="pre">request_finished(self,</span> <span class="pre">request:</span> <span class="pre">LlmRequest,</span> <span class="pre">cache_block_ids:</span> <span class="pre">list[int])</span> <span class="pre">-></span> <span class="pre">bool</span></code></strong></p>
|
||
<ul>
|
||
<li><p><strong>Description</strong>: Called when a request completes generation.</p></li>
|
||
<li><p><strong>Returns</strong>: A boolean indicating if an asynchronous save operation is underway. If <code class="docutils literal notranslate"><span class="pre">True</span></code>, the system waits for the operation to complete before releasing the KV cache blocks.</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p><strong><code class="docutils literal notranslate"><span class="pre">update_state_after_alloc(self,</span> <span class="pre">request:</span> <span class="pre">LlmRequest,</span> <span class="pre">block_ids:</span> <span class="pre">list[int])</span></code></strong></p>
|
||
<ul>
|
||
<li><p><strong>Description</strong>: a callback to update internal state after KV cache blocks have been allocated for the prefill.</p></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</section>
|
||
<section id="worker-interface-kvcacheconnectorworker">
|
||
<h4>2. Worker Interface (<code class="docutils literal notranslate"><span class="pre">KvCacheConnectorWorker</span></code>)<a class="headerlink" href="#worker-interface-kvcacheconnectorworker" title="Link to this heading">#</a></h4>
|
||
<p>These methods run on all workers (GPU processes) and interact with the actual GPU data.</p>
|
||
<ul class="simple">
|
||
<li><p><strong><code class="docutils literal notranslate"><span class="pre">register_kv_caches(self,</span> <span class="pre">kv_cache_tensor:</span> <span class="pre">torch.Tensor)</span></code></strong></p>
|
||
<ul>
|
||
<li><p><strong>Description</strong>: Called at initialization. Provides the worker with the GPU KV cache tensors.</p></li>
|
||
<li><p><strong>Arguments</strong>: <code class="docutils literal notranslate"><span class="pre">kv_cache_tensor</span></code> is the underlying storage tensor for the KV cache.</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p><strong><code class="docutils literal notranslate"><span class="pre">start_load_kv(self,</span> <span class="pre">stream:</span> <span class="pre">torch.cuda.Stream)</span></code></strong></p>
|
||
<ul>
|
||
<li><p><strong>Description</strong>: Initiates the loading of KV blocks from the external source into the GPU memory.</p></li>
|
||
<li><p><strong>Arguments</strong>: <code class="docutils literal notranslate"><span class="pre">stream</span></code> is the CUDA stream where the forward pass is executed in.</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p><strong><code class="docutils literal notranslate"><span class="pre">wait_for_layer_load(self,</span> <span class="pre">layer_idx:</span> <span class="pre">int,</span> <span class="pre">stream:</span> <span class="pre">torch.cuda.Stream)</span></code></strong></p>
|
||
<ul>
|
||
<li><p><strong>Description</strong>: A synchronization point. Ensures that the KV cache for a specific layer is fully loaded before the model attempts to perform the forward pass on that layer.</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p><strong><code class="docutils literal notranslate"><span class="pre">save_kv_layer(self,</span> <span class="pre">layer_idx:</span> <span class="pre">int,</span> <span class="pre">stream:</span> <span class="pre">torch.cuda.Stream)</span></code></strong></p>
|
||
<ul>
|
||
<li><p><strong>Description</strong>: Triggers the saving of a specific layer’s KV cache.</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p><strong><code class="docutils literal notranslate"><span class="pre">wait_for_save(self,</span> <span class="pre">stream:</span> <span class="pre">torch.cuda.Stream)</span></code></strong></p>
|
||
<ul>
|
||
<li><p><strong>Description</strong>: A synchronization point to ensure all save operations are enqueued or completed.</p></li>
|
||
</ul>
|
||
</li>
|
||
<li><p><strong><code class="docutils literal notranslate"><span class="pre">get_finished(self,</span> <span class="pre">finished_gen_req_ids,</span> <span class="pre">started_loading_req_ids)</span> <span class="pre">-></span> <span class="pre">tuple[list[int],</span> <span class="pre">list[int]]</span></code></strong></p>
|
||
<ul>
|
||
<li><p><strong>Description</strong>: Polled by the runtime to check the status of asynchronous operations.</p></li>
|
||
<li><p><strong>Returns</strong>: Two lists of request IDs: those that have finished saving, and those that have finished loading.</p></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</section>
|
||
</section>
|
||
</section>
|
||
<section id="example-implementation">
|
||
<h2>Example Implementation<a class="headerlink" href="#example-implementation" title="Link to this heading">#</a></h2>
|
||
<p>The file <code class="docutils literal notranslate"><span class="pre">examples/llm-api/llm_kv_cache_connector.py</span></code> provides a reference implementation of a <strong>Persistent KV Cache</strong>.</p>
|
||
<section id="overview">
|
||
<h3>Overview<a class="headerlink" href="#overview" title="Link to this heading">#</a></h3>
|
||
<p>This example implements a file-system based KV cache.
|
||
1.<strong>Save</strong>: When a request finishes or needs to be swapped out, its KV blocks are saved to disk as <code class="docutils literal notranslate"><span class="pre">.pt</span></code> files.
|
||
2.<strong>Load</strong>: When a new request arrives with the same prompt prefix, the connector identifies the cached files and loads them back into GPU memory, skipping re-computation.</p>
|
||
</section>
|
||
<section id="implementation-details">
|
||
<h3>Implementation Details<a class="headerlink" href="#implementation-details" title="Link to this heading">#</a></h3>
|
||
<ul class="simple">
|
||
<li><p><strong>Metadata</strong>: The example defines a <code class="docutils literal notranslate"><span class="pre">PersistentKvCacheConnectorMetadata</span></code> dataclass containing lists of <code class="docutils literal notranslate"><span class="pre">(file_path,</span> <span class="pre">block_id)</span></code> tuples for both loading and saving. This simple structure allows the Scheduler to tell the Worker exactly which file corresponds to which GPU block index.</p></li>
|
||
<li><p><strong>Hashing Strategy</strong>: The <code class="docutils literal notranslate"><span class="pre">PersistentKvCacheConnectorLeader</span></code> hashes the token sequence of a block to generate a unique filename (e.g., <code class="docutils literal notranslate"><span class="pre">hash_value.pt</span></code>). This acts as the lookup key.</p></li>
|
||
<li><p><strong>Worker Logic</strong>:</p>
|
||
<ul>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">start_load_kv</span></code>: Iterates through the load list provided in the metadata, loads the <code class="docutils literal notranslate"><span class="pre">.pt</span></code> file to CPU, and copies it to the specific <code class="docutils literal notranslate"><span class="pre">block_id</span></code> in the GPU tensor.</p></li>
|
||
<li><p><code class="docutils literal notranslate"><span class="pre">wait_for_save</span></code>: Performs the reverse. It copies data from the GPU <code class="docutils literal notranslate"><span class="pre">block_id</span></code> to CPU and saves it to disk using <code class="docutils literal notranslate"><span class="pre">torch.save</span></code>.</p></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</section>
|
||
<section id="limitations-patterns">
|
||
<h3>Limitations & Patterns<a class="headerlink" href="#limitations-patterns" title="Link to this heading">#</a></h3>
|
||
<p>This example illustrates the API mechanics but has several limitations that make it unsuitable for high-performance production use without modification:</p>
|
||
<ol class="arabic simple">
|
||
<li><p><strong>Blocking I/O</strong>: The example uses <code class="docutils literal notranslate"><span class="pre">torch.load</span></code> and <code class="docutils literal notranslate"><span class="pre">torch.save</span></code> synchronously. In a real implementation, these should be offloaded to a background thread or asynchronous I/O handler to avoid stalling the GPU.</p></li>
|
||
<li><p><strong>Simplified Block Matching</strong>: The <code class="docutils literal notranslate"><span class="pre">get_num_new_matched_tokens</span></code> implementation in the example only matches full blocks. It does not handle partial cache hits.</p></li>
|
||
<li><p><strong>FileSystem Latency</strong>: Storing one file per block can create high filesystem overhead.</p></li>
|
||
</ol>
|
||
</section>
|
||
<section id="usage">
|
||
<h3>Usage<a class="headerlink" href="#usage" title="Link to this heading">#</a></h3>
|
||
<p>To run the example:</p>
|
||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>python<span class="w"> </span>examples/llm-api/llm_kv_cache_connector.py<span class="w"> </span><model_path>
|
||
</pre></div>
|
||
</div>
|
||
<p>The script demonstrates:</p>
|
||
<ol class="arabic simple">
|
||
<li><p>Generating text for a prompt (First run).</p></li>
|
||
<li><p>Destroying the LLM instance.</p></li>
|
||
<li><p>Creating a new LLM instance with the same connector config.</p></li>
|
||
<li><p>Generating text for the same prompt (Second run).</p></li>
|
||
<li><p>Asserting that the outputs match, proving the state was correctly restored from the disk cache.</p></li>
|
||
</ol>
|
||
</section>
|
||
</section>
|
||
</section>
|
||
|
||
|
||
</article>
|
||
|
||
|
||
|
||
|
||
|
||
<footer class="prev-next-footer d-print-none">
|
||
|
||
<div class="prev-next-area">
|
||
<a class="left-prev"
|
||
href="helix.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">Helix Parallelism</p>
|
||
</div>
|
||
</a>
|
||
<a class="right-next"
|
||
href="../developer-guide/overview.html"
|
||
title="next page">
|
||
<div class="prev-next-info">
|
||
<p class="prev-next-subtitle">next</p>
|
||
<p class="prev-next-title">Architecture Overview</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="#use-cases">Use Cases</a></li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#architecture">Architecture</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#api-reference">API Reference</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#scheduler-leader-interface-kvcacheconnectorscheduler">1. Scheduler (Leader) Interface (<code class="docutils literal notranslate"><span class="pre">KvCacheConnectorScheduler</span></code>)</a></li>
|
||
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#worker-interface-kvcacheconnectorworker">2. Worker Interface (<code class="docutils literal notranslate"><span class="pre">KvCacheConnectorWorker</span></code>)</a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#example-implementation">Example Implementation</a><ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#overview">Overview</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#implementation-details">Implementation Details</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#limitations-patterns">Limitations & Patterns</a></li>
|
||
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#usage">Usage</a></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 07, 2025.</p>
|
||
|
||
<p>This page is generated by TensorRT-LLM commit <a href="https://github.com/NVIDIA/TensorRT-LLM/tree/e4c7078">e4c7078</a>.</p>
|
||
|
||
</div></div>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
</div>
|
||
|
||
</footer>
|
||
</body>
|
||
</html> |