0.21.0

This release introduces the vLLM container image. It provides Intel GPU software support for vLLM inference and serving.

This image is available on Docker Hub, and you can build it from the Dockerfile.

Requirements

The vLLM container was validated on a host system running Ubuntu 24.04.4 with the following GPUs:

• Intel® Arc™ Pro B50 Graphics

• Intel® Arc™ Pro B60 Graphics

• Intel® Arc™ Pro B65 Graphics

• Intel® Arc™ Pro B70 Graphics

Components

This container is based on Intel® Open Middleware Xe (Intel OMIX) 0.1.0 and includes vLLM 0.21.0. For more information about this version, see the project’s Release Notes.

Security vulnerabilities

vLLM currently depends on diskcache version 5.6.3, which has been reported as affected by CVE-2025-69872. The vulnerability remains unresolved upstream as of the day of this release. According to initial analysis, the vLLM architecture does not expose the vulnerable code path, meaning vLLM is not impacted in practice, despite the dependency being formally flagged.

Legal notices

By downloading and using this container image and the included software, you agree to the terms and conditions of the software license agreements.

In accordance with the terms and conditions of these licenses, particularly those requiring source code availability, such as GPL, the source code for all such open-source components included in this container image can be obtained from here.

This container image is not intended for production use. To receive expanded security maintenance from Canonical on the Ubuntu base layer, you may follow the instructions in how to enable Ubuntu Pro in a Dockerfile, which requires rebuilding the image.