Skip to main content

Your submission was sent successfully! Close

Thank you for signing up for our newsletter!
In these regular emails you will find the latest updates from Canonical and upcoming events where you can meet our team.Close

Thank you for contacting us. A member of our team will be in touch shortly. Close

  1. Blog
  2. Article

Benjamin Ryzman
on 11 June 2025

Canonical Kubernetes meets NVIDIA DOCA Platform Framework (DPF): building the future of DPU-driven infrastructure


The combined solutions simplify infrastructure operations and accelerate time-to-value for AI, telecom, and enterprise computing workloads.

Accelerate deployment and operations of BlueField DPUs with Canonical Kubernetes

At GTC Paris today, Canonical announced support for the NVIDIA DOCA Platform Framework (DPF) with Canonical Kubernetes LTS. This milestone strengthens the strategic collaboration between the two companies and brings the benefits of NVIDIA BlueField DPU accelerations to cloud-native environments with end-to-end automation, open-source flexibility, and long-term support.

DPF is NVIDIA’s software framework for managing and orchestrating NVIDIA BlueField DPUs at scale. NVIDIA BlueFieldenables advanced offloading of infrastructure services (such as networking, storage, and security) directly onto the DPU, freeing up host CPU resources and enabling secure, high-performance, zero-trust architectures. With Canonical Kubernetes now officially supporting DPF 25.1, developers and infrastructure teams can easily integrate these capabilities into their AI, telecom and enterprise computing workloads using Canonical’s proven tooling and automation stack.

A joint solution built for scale and simplicity

This integration enables organizations to deploy DPU-accelerated infrastructure across telco, enterprise, and edge use cases, with key benefits including:

  • Simplified provisioning and lifecycle management of BlueField DPUs using Canonical infrastructure products like MAAS, Juju, and Snap-based deployment flows on Ubuntu 24.04 LTS and Kubernetes 1.32.2.
  • Declarative deployment of DPU firmware and services using Kubernetes-native interfaces such as Helm charts and custom resource definitions (CRDs).
  • Out-of-the-box integration with NVIDIA Network Operator, including support for SR-IOV, Multus, and accelerated CNIs like OVN-Kubernetes.
  • Production-grade support with Canonical’s long term support, offering up to 12 years of security updates and enterprise SLAs.

“This milestone marks a significant step forward in our collaboration with NVIDIA,” said Cedric Gegout, VP of Product at Canonical. “Together, we’re enabling a new class of infrastructure that combines the power of NVIDIA BlueField DPUs with the flexibility and automation of Canonical Kubernetes – laying the groundwork for secure, high-performance environments across AI, telecom, and enterprise use cases.”

A platform for developers, operators, and innovators

When combined, the NVIDIA DOCA software framework and Canonical Kubernetes empower cloud architects and platform engineers to design scalable, secure infrastructure while minimizing operational complexity. For DevOps and SRE teams, the integration of BlueField-accelerated  services into CI/CD pipelines becomes streamlined, enabling consistent, automated delivery of infrastructure components. Application developers gain access to offloaded services through the DOCA SDK and APIs, accelerating innovation without compromising performance. Meanwhile, IT decision makers benefit from enhanced efficiency, workload isolation, and built-in compliance as they modernize their infrastructure.

Open source and cloud-native communities now have a powerful foundation to build on with Canonical Kubernetes and NVIDIA DPF. This integration enables contributors, researchers, and ecosystem partners to adopt and extend a truly open DPU architecture – one where offloaded networking, security, and observability services run independently of the host CPU. By leveraging DOCA’s modular approach and Canonical’s fully supported Kubernetes stack, developers can co-create a rich ecosystem of BlueField-accelerated functions that complement and enhance the performance, scalability, and resilience of applications running on the main CPU.

Get started

Canonical is enabling the next generation of composable, DPU-accelerated cloud infrastructure with NVIDIA. Canonical Kubernetes offers a robust, enterprise-grade platform to install, operate, and scale NVIDIA BlueField-accelerated services using NVIDIA DPF with full automation and long-term support. To get started, visit ubuntu.com/kubernetes for product details and support options, and explore the DPF documentation on GitHub for deployment guides and examples.

If you have any questions about running DPF with Canonical Kubernetes, please stop by our booth #E03 at NVIDIA GTC Paris or contact us.

Related posts


Shashank Balashankar
19 March 2024

Canonical collaborates with NVIDIA to simplify enterprise AI deployments with NVIDIA BlueField-3 operating an optimised, Ubuntu-based Linux OS 

Networking Article

The NVIDIA BlueField-3 networking platform – powering the latest data processing units (DPUs) and SuperNICs, and transforming data centre performance and efficiency – runs BlueField OS, an optimised Linux operating system (OS) derived from Ubuntu. With Ubuntu’s signature maintenance and support guarantees, the comprehensive Ubuntu Pro sof ...


Benjamin Ryzman
22 April 2024

Achieving Performant Single-Tenant Cloud Isolation with IBM Cloud Bare Metal Servers, Ubuntu Core, Snaps, and AMD Pensando Elba Data Processing Unit

Networking Article

Discover how IBM Cloud’s bare metal servers offer highly confined and high-performing single-tenant cloud isolation through the use of Ubuntu Core and Snaps, supported by the AMD Pensando Elba DPU (Data Processing Unit). This setup enables the creation of secure and efficient environments for each tenant. Its design ensures the total sepa ...


Shashank Balashankar
13 June 2023

Canonical solutions reduce SmartNIC time-to-market and drive efficiency in enterprise data centres

Networking Article

Data centre efficiency is a central cost factor in enterprise IT environments. So, in the face of rising energy costs and increasingly resource-intensive workloads, it is more important than ever for businesses to seek out greater optimisation. Traditionally, CPUs have been used for the majority of data centre workloads, including network ...