mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
803 lines
47 KiB
HTML
803 lines
47 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>Inference Request — 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" />
|
|
|
|
<!-- 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>DOCUMENTATION_OPTIONS.pagename = 'advanced/inference-request';</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="Run gpt-2b + LoRA using GptManager / cpp runtime" href="lora.html" />
|
|
<link rel="prev" title="Graph Rewriting Module" href="graph-rewriting.html" />
|
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
|
<meta name="docsearch:language" content="en"/>
|
|
<meta name="docsearch:version" content="" />
|
|
|
|
|
|
</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="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__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/linux.html">Installing on Linux</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>
|
|
<li class="toctree-l1"><a class="reference internal" href="../installation/grace-hopper.html">Installing on Grace Hopper</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">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">LLM API Examples</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../llm-api-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>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_inference_async.html">Generate Text Asynchronously</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_logits_processor.html">Control generated text using logits post processor</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_quantization.html">Generation with Quantization</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_inference_async_streaming.html">Generate Text in Streaming</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_inference.html">Generate text</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_inference_customize.html">Generate text with customization</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_auto_parallel.html">Automatic Parallelism with LLM</a></li>
|
|
</ul>
|
|
</details></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../llm-api-examples/customization.html">Common Customizations</a></li>
|
|
<li class="toctree-l1 has-children"><a class="reference internal" href="../llm-api-examples/llm_api_examples.html">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="../llm-api-examples/llm_medusa_decoding.html">Generate Text Using Medusa Decoding</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_multilora.html">Generate text with multiple LoRA adapters</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_inference_async.html">Generate Text Asynchronously</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_inference_distributed.html">Distributed LLM Generation</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_logits_processor.html">Control generated text using logits post processor</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_lookahead_decoding.html">Generate Text Using Lookahead Decoding</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_quantization.html">Generation with Quantization</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_inference_async_streaming.html">Generate Text in Streaming</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_guided_decoding.html">Generate text with guided decoding</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_inference.html">Generate text</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_inference_customize.html">Generate text with customization</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="../llm-api-examples/llm_auto_parallel.html">Automatic Parallelism with LLM</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-build.html">trtllm-build</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-serve.html">trtllm-serve</a></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="current nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="gpt-attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="gpt-runtime.html">C++ GPT Runtime</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="executor.html">Executor API</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="graph-rewriting.html">Graph Rewriting Module</a></li>
|
|
<li class="toctree-l1 current active"><a class="current reference internal" href="#">Inference Request</a></li>
|
|
|
|
<li class="toctree-l1"><a class="reference internal" href="lora.html">Run gpt-2b + LoRA using GptManager / cpp runtime</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="expert-parallelism.html">Expert Parallelism in TensorRT-LLM</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="kv-cache-reuse.html">KV cache reuse</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="speculative-decoding.html">Speculative Sampling</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="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>
|
|
</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>
|
|
</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">Inference Request</span></li>
|
|
</ul>
|
|
</nav>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<div id="searchbox"></div>
|
|
<article class="bd-article">
|
|
|
|
<section id="inference-request">
|
|
<span id="id1"></span><h1>Inference Request<a class="headerlink" href="#inference-request" title="Link to this heading">#</a></h1>
|
|
<p>The main class to describe requests to <code class="docutils literal notranslate"><span class="pre">GptManager</span></code> is <code class="docutils literal notranslate"><span class="pre">InferenceRequest</span></code>. This is structured as a map of tensors and a <code class="docutils literal notranslate"><span class="pre">uint64_t</span> <span class="pre">requestId</span></code>.
|
|
The mandatory input tensors to create a valid <code class="docutils literal notranslate"><span class="pre">InferenceRequest</span></code> object are described below. Sampling config params are documented in the <a class="reference internal" href="gpt-runtime.html#gpt-runtime"><span class="std std-ref">C++ GPT Runtime</span></a> section. Descriptions have been omitted in the table.</p>
|
|
<div class="pst-scrollable-table-container"><table class="table">
|
|
<thead>
|
|
<tr class="row-odd"><th class="head text-center"><p>Name</p></th>
|
|
<th class="head text-center"><p>Shape</p></th>
|
|
<th class="head text-center"><p>Type</p></th>
|
|
<th class="head text-center"><p>Description</p></th>
|
|
</tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">request_output_len</span></code></p></td>
|
|
<td class="text-center"><p>[1,1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>Max number of output tokens</p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">input_ids</span></code></p></td>
|
|
<td class="text-center"><p>[1, num_input_tokens]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>Tensor of input tokens</p></td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
</div>
|
|
<p>Optional tensors that can be supplied to <code class="docutils literal notranslate"><span class="pre">InferenceRequest</span></code> are shown below. Default values, where applicable are specified.:</p>
|
|
<div class="pst-scrollable-table-container"><table class="table">
|
|
<thead>
|
|
<tr class="row-odd"><th class="head text-center"><p>Name</p></th>
|
|
<th class="head text-center"><p>Shape</p></th>
|
|
<th class="head text-center"><p>Type</p></th>
|
|
<th class="head text-center"><p>Description</p></th>
|
|
</tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">streaming</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">bool</span></code></p></td>
|
|
<td class="text-center"><p>(Default=<code class="docutils literal notranslate"><span class="pre">false</span></code>). When <code class="docutils literal notranslate"><span class="pre">true</span></code>, stream out tokens as they are generated. When <code class="docutils literal notranslate"><span class="pre">false</span></code> return only when the full generation has completed.</p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">beam_width</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>(Default=1) Beam width for this request; set to 1 for greedy sampling</p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">temperature</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code></p></td>
|
|
<td class="text-center"><p>Sampling Config param: <code class="docutils literal notranslate"><span class="pre">temperature</span></code></p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">runtime_top_k</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>Sampling Config param: <code class="docutils literal notranslate"><span class="pre">topK</span></code></p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">runtime_top_p</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code></p></td>
|
|
<td class="text-center"><p>Sampling Config param: <code class="docutils literal notranslate"><span class="pre">topP</span></code></p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">len_penalty</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code></p></td>
|
|
<td class="text-center"><p>Sampling Config param: <code class="docutils literal notranslate"><span class="pre">lengthPenalty</span></code></p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">early_stopping</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int</span></code></p></td>
|
|
<td class="text-center"><p>Sampling Config param: <code class="docutils literal notranslate"><span class="pre">earlyStopping</span></code></p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">repetition_penalty</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code></p></td>
|
|
<td class="text-center"><p>Sampling Config param: <code class="docutils literal notranslate"><span class="pre">repetitionPenalty</span></code></p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">min_length</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>Sampling Config param: <code class="docutils literal notranslate"><span class="pre">minLength</span></code></p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">presence_penalty</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code></p></td>
|
|
<td class="text-center"><p>Sampling Config param: <code class="docutils literal notranslate"><span class="pre">presencePenalty</span></code></p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">frequency_penalty</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code></p></td>
|
|
<td class="text-center"><p>Sampling Config param: <code class="docutils literal notranslate"><span class="pre">frequencyPenalty</span></code></p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">no_repeat_ngram_size</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>Sampling Config param: <code class="docutils literal notranslate"><span class="pre">noRepeatNgramSize</span></code></p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">random_seed</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">uint64_t</span></code></p></td>
|
|
<td class="text-center"><p>Sampling Config param: <code class="docutils literal notranslate"><span class="pre">randomSeed</span></code></p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">end_id</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>End token Id. If not specified, defaults to -1</p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">pad_id</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>Pad token Id</p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">embedding_bias</span></code></p></td>
|
|
<td class="text-center"><p>[1, vocab_size]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code></p></td>
|
|
<td class="text-center"><p>The bias is added to the logits for each token in the vocabulary before decoding occurs. Positive values in the bias encourage the sampling of tokens, while negative values discourage it. A value of <code class="docutils literal notranslate"><span class="pre">0.f</span></code> leaves the logit value unchanged.</p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">bad_words_list</span></code></p></td>
|
|
<td class="text-center"><p>[1, 2, num_bad_words]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>Bad words list. Consider an example with two bad words, where the first word contains tokens <code class="docutils literal notranslate"><span class="pre">[5,</span> <span class="pre">7,</span> <span class="pre">3]</span></code> and the second one contains tokens <code class="docutils literal notranslate"><span class="pre">[9,</span> <span class="pre">2]</span></code>. In total there are 5 tokens so the tensor shape should be <code class="docutils literal notranslate"><span class="pre">[1,</span> <span class="pre">2,</span> <span class="pre">5]</span></code>. The first row of the tensor must contain the token ids, while the second row must store the include-scan offsets of the word lengths (in number of tokens). Hence, the <code class="docutils literal notranslate"><span class="pre">bad_word_list</span></code> tensor would look like: <code class="docutils literal notranslate"><span class="pre">[[[</span> <span class="pre">5,</span> <span class="pre">7,</span> <span class="pre">3,</span> <span class="pre">9,</span> <span class="pre">2][</span> <span class="pre">3,</span> <span class="pre">5,</span> <span class="pre">-1,</span> <span class="pre">-1,</span> <span class="pre">-1]]]</span></code></p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">stop_words_list</span></code></p></td>
|
|
<td class="text-center"><p>[1, 2, num_stop_words]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>Stop words list. See <code class="docutils literal notranslate"><span class="pre">bad_words_list</span></code> for the description of the expected tensor shape and content</p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">prompt_embedding_table</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float16</span></code></p></td>
|
|
<td class="text-center"><p>P-tuning prompt embedding table</p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">prompt_vocab_size</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>P-tuning prompt vocab size</p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">lora_task_id</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">uint64_t</span></code></p></td>
|
|
<td class="text-center"><p>Task ID for the given lora_weights. This ID is expected to be globally unique. To perform inference with a specific LoRA for the first time <code class="docutils literal notranslate"><span class="pre">lora_task_id</span></code> <code class="docutils literal notranslate"><span class="pre">lora_weights</span></code> and <code class="docutils literal notranslate"><span class="pre">lora_config</span></code> must all be given. The LoRA will be cached, so that subsequent requests for the same task only require <code class="docutils literal notranslate"><span class="pre">lora_task_id</span></code>. If the cache is full the oldest LoRA will be evicted to make space for new ones. An error is returned if <code class="docutils literal notranslate"><span class="pre">lora_task_id</span></code> is not cached</p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">lora_weights</span></code></p></td>
|
|
<td class="text-center"><p>[num_lora_modules_layers, D x Hi + Ho x D]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code> (model data type)</p></td>
|
|
<td class="text-center"><p>weights for a LoRA adapter. Refer to <a class="reference internal" href="lora.html#lora"><span class="std std-ref">Run gpt-2b + LoRA using GptManager / cpp runtime</span></a> for more information.</p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">lora_config</span></code></p></td>
|
|
<td class="text-center"><p>[num_lora_modules_layers, 3]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>LoRA configuration tensor. <code class="docutils literal notranslate"><span class="pre">[</span> <span class="pre">module_id,</span> <span class="pre">layer_idx,</span> <span class="pre">adapter_size</span> <span class="pre">(D</span> <span class="pre">aka</span> <span class="pre">R</span> <span class="pre">value)</span> <span class="pre">]</span></code> Refer to <a class="reference internal" href="lora.html#lora"><span class="std std-ref">Run gpt-2b + LoRA using GptManager / cpp runtime</span></a> for more information.</p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">return_log_probs</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">bool</span></code></p></td>
|
|
<td class="text-center"><p>When <code class="docutils literal notranslate"><span class="pre">true</span></code>, include log probs in the output</p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">return_context_logits</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">bool</span></code></p></td>
|
|
<td class="text-center"><p>When <code class="docutils literal notranslate"><span class="pre">true</span></code>, include context logits in the output</p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">return_generation_logits</span></code></p></td>
|
|
<td class="text-center"><p>[1]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">bool</span></code></p></td>
|
|
<td class="text-center"><p>When <code class="docutils literal notranslate"><span class="pre">true</span></code>, include generation logits in the output</p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">draft_input_ids</span></code></p></td>
|
|
<td class="text-center"><p>[num_draft_tokens]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>Draft tokens to be leveraged in generation phase to potentially generate multiple output tokens in one inflight batching iteration</p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">draft_logits</span></code></p></td>
|
|
<td class="text-center"><p>[num_draft_tokens, vocab_size]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code></p></td>
|
|
<td class="text-center"><p>Draft logits associated with <code class="docutils literal notranslate"><span class="pre">draft_input_ids</span></code> to be leveraged in generation phase to potentially generate multiple output tokens in one inflight batching iteration</p></td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
</div>
|
|
</section>
|
|
<section id="responses">
|
|
<h1>Responses<a class="headerlink" href="#responses" title="Link to this heading">#</a></h1>
|
|
<p>Responses from GptManager are formatted as a list of tensors. The table below shows the set of output tensors returned by <code class="docutils literal notranslate"><span class="pre">GptManager</span></code> (via the <code class="docutils literal notranslate"><span class="pre">SendResponseCallback</span></code>):</p>
|
|
<div class="pst-scrollable-table-container"><table class="table">
|
|
<thead>
|
|
<tr class="row-odd"><th class="head text-center"><p>Name</p></th>
|
|
<th class="head text-center"><p>Shape</p></th>
|
|
<th class="head text-center"><p>Type</p></th>
|
|
<th class="head text-center"><p>Description</p></th>
|
|
</tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">output_ids</span></code></p></td>
|
|
<td class="text-center"><p>[beam_width, num_output_tokens]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>Tensor of output tokens. When <code class="docutils literal notranslate"><span class="pre">streaming</span></code> is enabled, this is a single token.</p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">sequence_length</span></code></p></td>
|
|
<td class="text-center"><p>[beam_width]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">int32_t</span></code></p></td>
|
|
<td class="text-center"><p>Number of output tokens. When <code class="docutils literal notranslate"><span class="pre">streaming</span></code> is set, this will be 1.</p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">output_log_probs</span></code></p></td>
|
|
<td class="text-center"><p>[1, beam_width, num_output_tokens]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code></p></td>
|
|
<td class="text-center"><p>Only if <code class="docutils literal notranslate"><span class="pre">return_log_probs</span></code> is set on input. Tensor of log probabilities of output token logits.</p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">cum_log_probs</span></code></p></td>
|
|
<td class="text-center"><p>[1, beam_width]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code></p></td>
|
|
<td class="text-center"><p>Only if <code class="docutils literal notranslate"><span class="pre">return_log_probs</span></code> is set on input. Cumulative log probability of the sequence generated.</p></td>
|
|
</tr>
|
|
<tr class="row-even"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">context_logits</span></code></p></td>
|
|
<td class="text-center"><p>[1, num_input_tokens, vocab_size]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code></p></td>
|
|
<td class="text-center"><p>Only if <code class="docutils literal notranslate"><span class="pre">return_context_logits</span></code> is set on input. Tensor of input token logits.</p></td>
|
|
</tr>
|
|
<tr class="row-odd"><td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">generation_logits</span></code></p></td>
|
|
<td class="text-center"><p>[1, beam_width, num_output_tokens, vocab_size]</p></td>
|
|
<td class="text-center"><p><code class="docutils literal notranslate"><span class="pre">float</span></code></p></td>
|
|
<td class="text-center"><p>Only if <code class="docutils literal notranslate"><span class="pre">return_generation_logits</span></code> is set on input. Tensor of output token logits.</p></td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
</div>
|
|
</section>
|
|
|
|
|
|
</article>
|
|
|
|
|
|
|
|
|
|
|
|
<footer class="prev-next-footer d-print-none">
|
|
|
|
<div class="prev-next-area">
|
|
<a class="left-prev"
|
|
href="graph-rewriting.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">Graph Rewriting Module</p>
|
|
</div>
|
|
</a>
|
|
<a class="right-next"
|
|
href="lora.html"
|
|
title="next page">
|
|
<div class="prev-next-info">
|
|
<p class="prev-next-subtitle">next</p>
|
|
<p class="prev-next-title">Run gpt-2b + LoRA using GptManager / cpp runtime</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-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#">Inference Request</a></li>
|
|
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#responses">Responses</a></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/">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 © 2024, NVidia.
|
|
<br/>
|
|
|
|
</p>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
</div>
|
|
|
|
</footer>
|
|
</body>
|
|
</html> |