OpenStack Epoxy Release Boosts AI and VMware Migration Capabilities

Apr 2, 2025
OpenInfra Foundation has announced the release of OpenStack 2025.1 Epoxy, enhancing AI workload support and VMware migration capabilities.

The OpenInfra Foundation has announced the release of OpenStack 2025.1 Epoxy, marking the 31st release of the widely used open-source cloud infrastructure software. In a press release, the foundation highlighted the new version's enhanced support for AI workloads and improved capabilities for VMware migration.

OpenStack Epoxy introduces several key features aimed at strengthening its position as a VMware alternative. Notably, the integration of Prometheus into OpenStack via Watcher allows for efficient monitoring of VMware infrastructure during migration. This release also includes updates to Cinder storage drivers, facilitating smoother transitions for workloads reliant on specific storage solutions.

Security enhancements in Epoxy include new features for Manila users, such as the ability to modify access levels of share access rules and set share server characteristics. These improvements aim to provide better control over shared resources and enhance network isolation.

Additionally, the release supports AI workloads with updates like Nova's PCI pass-through feature, which now accommodates new kernel vfio-PCI variant drivers, including Nvidia GRID on Ubuntu 24.04. This allows operators to create instances using specific PCI devices and live-migrate them, enhancing OpenStack's AI capabilities.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

AI Chips & Datacenters AI Brief AI Brief (X)
Free newsletter

Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.