<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>C++ on LeventureTecTips</title><link>https://leventureqys.github.io/tags/c++/</link><description>Recent content in C++ on LeventureTecTips</description><generator>Hugo -- 0.163.2</generator><language>en-us</language><lastBuildDate>Wed, 02 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://leventureqys.github.io/tags/c++/index.xml" rel="self" type="application/rss+xml"/><item><title>一个基本问题：当我们谈论移植的时候，我们聊的是 ONNX 还是自定义算子？</title><link>https://leventureqys.github.io/posts/onnx-or-custom-operator-porting/</link><pubDate>Wed, 02 Sep 2026 00:00:00 +0000</pubDate><guid>https://leventureqys.github.io/posts/onnx-or-custom-operator-porting/</guid><description>模型部署时，如何在 ONNX Runtime 与原生 C++ 自定义算子之间做选型。</description></item></channel></rss>