{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# PyTtorch 在线推理算子优化实践\n",
    "\n",
    "本章介绍PyTorch 在线推理场景下模型通过算子优化性能的端到端实践。\n",
    "\n",
    "---\n",
    "\n",
    "## 前置知识\n",
    "为了更好学习本实践内容，需要先掌握tutorials/ascendc_operator_development目录中 **Ascend C算子开发系列教程** 的以下内容：\n",
    "- 完成第一章学习，理解算子的核心概念与基本原理。\n",
    "- 完成第二章学习，掌握基于Ascend C进行算子开发的基础方法。\n",
    "- 完成第三章学习，掌握基于Ascend C进行算子工程开发的步骤，以及算子调用代码的编写。\n",
    "- 完成第八章学习，掌握算子性能数据分析方法。\n",
    "\n",
    "在环境配置方面，本实践要求对你的环境满足以下条件：\n",
    "- 系统中已部署昇腾NPU硬件，或已配置昇腾云服务器/仿真环境。\n",
    "- 已按照[CANN下载页面](https://www.hiascend.com/cann/download)完成对应硬件的开发环境部署。\n",
    "\n",
    "---\n",
    "\n",
    "\n",
    "## 章节内容\n",
    "* [1 章节介绍](./01_chapter_intro.ipynb)\n",
    "* [2 Pytorch Profiling工具使用技巧](./02_pytorch_profiling_tool_usage.ipynb)\n",
    "* [3 AddCustomTemplate 泛化算子开发](./03_operator_develop.ipynb)\n",
    "* [4 Pytorch算子插件开发以及模型接入](./04_pytorch_op_extension_develop_and_apply.ipynb)\n",
    "* [5 章节实践](./05_chapter_practice.ipynb)\n",
    "\n",
    "---\n",
    "\n",
    "本实践请从[2 Pytorch Profiling工具使用技巧](./02_pytorch_profiling_tool_usage.ipynb)开始阅读。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "MindSpore",
   "language": "python",
   "name": "mindspore"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}