<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Vllm on Ogenki</title><link>https://blog.ogenki.io/tags/vllm/</link><description>Recent content in Vllm on Ogenki</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>Copyright © 2021–2023, Smana https://github.io/Smana</copyright><lastBuildDate>Wed, 13 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.ogenki.io/tags/vllm/index.xml" rel="self" type="application/rss+xml"/><item><title>Self-hosted LLM stack: a solid foundation for an open-weight platform built to evolve</title><link>https://blog.ogenki.io/post/series/agentic_ai/llm-self-hosted-stack/</link><pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate><guid>https://blog.ogenki.io/post/series/agentic_ai/llm-self-hosted-stack/</guid><description>
A self-hosted platform to run open-weight models on Kubernetes: declarative `InferenceService`, autoscaling on GPU signals, end-to-end GitOps. A foundation designed to evolve with the ecosystem.</description></item></channel></rss>