GP

GPUStack

Manage GPU clusters for running AI models

Self-Hosted AI ★ 5.8k stars Medium setup Apache-2.0

GPUStack is an open-source platform for running and scaling AI models across heterogeneous GPU clusters. It supports LLMs, embeddings, image, and audio models with an OpenAI-compatible API and a management dashboard.

Key features

  • Distributed GPU scheduling
  • OpenAI-compatible API
  • Many model types
  • Cluster dashboard

Strengths

  • Released under the Apache-2.0 license
  • First-class Docker support for quick deployment
  • Kubernetes-ready with Helm charts available
  • Mature project with 5.8k GitHub stars

Is GPUStack secure?

No known vulnerabilities affect GPUStack's latest release (v2.2.3). OSV.dev lists 1 past advisory for the project; none of them applies to this release. No known vulnerabilities is not proof of security: it means none have been publicly catalogued.

  • Most recent fixed advisory CVE-2026-58658, published 2026-07-15 (91 days ago), fixed in 2.2.1

Source: OSV.dev, checked 2026-10-14. How this is measured.

GPUStack replaces

Health badge

Maintain GPUStack? Add its health score to your README. The badge links back to this page.

SelfHostIndex: 92 · excellent

Markdown
[![SelfHostIndex health score for GPUStack](https://selfhostindex.com/badge/gpustack.svg)](https://selfhostindex.com/app/gpustack/)
HTML
<a href="https://selfhostindex.com/app/gpustack/"><img src="https://selfhostindex.com/badge/gpustack.svg" alt="SelfHostIndex health score for GPUStack"></a>
reStructuredText
.. image:: https://selfhostindex.com/badge/gpustack.svg
   :alt: SelfHostIndex health score for GPUStack
   :target: https://selfhostindex.com/app/gpustack/

The score is recomputed on every nightly rebuild from public repository data — see how it is calculated.

Compare GPUStack

10 head-to-head comparisons.

Similar self-hosted ai apps