<?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>Vllm on scriptable.com</title><link>https://scriptable.com/categories/vllm/</link><description>Recent content in Vllm on scriptable.com</description><generator>Hugo</generator><language>en</language><lastBuildDate>Thu, 17 Sep 2026 07:20:37 -0400</lastBuildDate><atom:link href="https://scriptable.com/categories/vllm/index.xml" rel="self" type="application/rss+xml"/><item><title>Run vLLM on Apple Silicon with the Metal Plugin</title><link>https://scriptable.com/posts/vllm/vllm-metal-macos/</link><pubDate>Thu, 17 Sep 2026 07:20:37 -0400</pubDate><guid>https://scriptable.com/posts/vllm/vllm-metal-macos/</guid><description>vLLM is the inference server many production LLM deployments sit behind, and until recently it had no answer on a Mac beyond a source build of its CPU backend. The vllm-metal plugin changed that: it…</description></item></channel></rss>