<?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>OpenVINO on heihie</title><link>https://heihei0299.github.io/tags/openvino/</link><description>Recent content in OpenVINO on heihie</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Sat, 11 Jul 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://heihei0299.github.io/tags/openvino/index.xml" rel="self" type="application/rss+xml"/><item><title>在 Intel 设备上运行本地 LLM：llama.cpp + OpenVINO Docker 实战</title><link>https://heihei0299.github.io/posts/ops/blog/</link><pubDate>Sat, 11 Jul 2026 00:00:00 +0800</pubDate><guid>https://heihei0299.github.io/posts/ops/blog/</guid><description>无需 NVIDIA 显卡，用 llama.cpp + OpenVINO 的 Docker 镜像在 Intel CPU/GPU 上本地运行 LLM：多阶段构建、GPU 驱动栈配置与踩坑排查</description></item></channel></rss>