Dynamia Team to Represent HAMi at KubeCon EU 2026

This weekend, the Dynamia team will head to Amsterdam to attend the upcoming KubeCon + CloudNativeCon Europe 2026. As one of the most influential conferences in the global cloud native space, this year's KubeCon is expected to attract over 13,000 developers, architects, and infrastructure practitioners to discuss Kubernetes, AI, and next-generation infrastructure.

As the initiator and leading contributor of the CNCF Sandbox project HAMi, Dynamia will represent the HAMi community in multiple core activities during the conference, including Project Pavilion booth, official technical sessions, main stage Live Demo, and the post-conference AI Native Summit. This represents not only a concentrated project showcase but also a comprehensive presentation of HAMi in the global cloud native and AI infrastructure ecosystem.

HAMi's Global Impact

HAMi is not a fledgling project; it is gradually becoming an important component of GPU virtualization and scheduling in the Kubernetes ecosystem.

Currently, HAMi has established preliminary influence globally:

• Continuously growing GitHub Stars, with increasing developer attention

• Global user and contributor base, covering 17 countries and regions including China, Europe, and North America, with over 500 contributors

• Production deployments across multiple enterprise scenarios, improving GPU utilization and multi-tenant resource management capabilities, including SF Technology, Beike, PREP EDU, DaoCloud, and others

• Accepted into CNCF Sandbox and incubating, becoming part of the cloud native AI infrastructure ecosystem

• Gradual integration with Kubernetes ecosystem projects, including scheduling and AI components like Volcano, Kueue, vLLM, and others

Starting from "solving GPU utilization problems," HAMi is evolving into a key infrastructure layer for AI workloads on Kubernetes.

Why This KubeCon Matters

Viewing overall trends, a significant change this year is that AI is gradually moving from the application layer to the core position of the cloud native system. In past years, KubeCon discussions focused more on containers, microservices, and platform engineering. This year, whether in keynotes, AI-related sessions, or Project Pavilion project distribution, a clearer signal is being conveyed: AI is becoming one of the main themes in the Kubernetes ecosystem.

Meanwhile, the role of GPUs is also changing. It's no longer just an "acceleration device" on a single node, but is being redefined as a foundational resource that needs scheduling, sharing, and fine-grained management. GPU virtualization, resource utilization, multi-tenant isolation, and scheduling strategies are becoming key issues in AI infrastructure—and these are exactly what HAMi focuses on.

Dynamia's Role at the Conference

At KubeCon Europe 2026, Dynamia will participate as the HAMi community representative and project lead.

In open source scenarios like Project Pavilion, we'll center on HAMi as a CNCF project, discussing GPU virtualization, sharing, and scheduling issues with developers and community members. In deeper exchanges, Dynamia as HAMi's initiator and long-term builder will also share practices and insights from enterprise scenarios. This dual identity of "community + company" is an important characteristic of HAMi's current development stage.

Finding Us at KubeCon

If you're heading to Amsterdam for the conference, you can find us at Project Pavilion.

HAMi Booth: P-13B

Times:

• March 24 (Tuesday) 15:10–19:00

• March 26 (Thursday) 12:30–14:00

At the HAMi booth, we'll focus on GPU virtualization and sharing in Kubernetes, AI workload scheduling, multi-tenant resource management, and utilization optimization. We'll also discuss HAMi's relationships with ecosystem components like Volcano, Kueue, and vLLM.

HAMi @ KubeCon Europe 2026 Event Overview

During KubeCon, core activities around HAMi and Dynamia include:

🎤 Opening Keynote (HAMi Project Spotlight)

• Time: March 24, 09:00–09:35

• Location: Hall 12

• Speakers: Jonathan Bryce (Linux Foundation Executive Director) & Chris Aniszczyk (CNCF CTO)

Topic:

Welcome and Opening Remarks

Highlights:

This opening keynote will revolve around development trends in cloud native and AI infrastructure.

Given current session directions, it's expected to cover GPU resource management, AI workloads, and related content. The problem areas HAMi focuses on may also be mentioned.

⚡ HAMi Technical Sessions (Lightning Talks)

1️⃣ GPU Sharing in Kubernetes (Xiao Zhang)

• Time: March 23, 17:15–17:25

• Location: Hall 7 · Room B

• Speaker: Xiao Zhang (Dynamia CEO / HAMi Maintainer)

Topic:

K8s Issue #52757: Sharing GPUs Among Multiple Containers

Key Content:

• Kubernetes' long-unresolved GPU sharing problem

• Mechanisms and challenges of multi-container GPU sharing

• HAMi's design approach and technical path

2️⃣ HAMi Project Technical Overview (Mengxuan Li)

• Time: March 23, 14:43–14:48

• Location: Elicium 2

• Speaker: Mengxuan Li (Dynamia CTO / HAMi Maintainer)

Topic:

Dynamic, Smart, Stable GPU-Sharing Middleware in Kubernetes

Key Content:

• HAMi's core architecture and capabilities

• GPU virtualization and scheduling implementation mechanisms

• Stability and production availability design

🪧 Poster Session (Ecosystem Perspective)

• Time: March 25, 13:15–14:15

• Location: Hall 1–5 · Gouda Zone · Poster Pavilion

• Speakers: Satyam Soni (Devtron) & Rudraksh Karpe (ZS Associates)

Topic:

Kubernetes as the Universal GPU Control Plane for AI Workloads

Key Content:

• Trends in Kubernetes as a GPU control plane

• Unified abstraction for AI workload scheduling

• High alignment with HAMi's direction

🚀 Main Stage Demo (Core Highlight)

• Time: March 26, 10:03–10:18

• Location: Hall 12

• Speakers: Mengxuan Li & Reza Jelveh (Head of Global Market & Solution Engineer at Dynamia)

Topic:

Keynote Demo Showcase

Content Highlights:

• Live system demonstration

• Real-world GPU sharing and scheduling deployment

• Direct showcase from "concept" to "production system"

👉 This is the most noteworthy HAMi session at the conference

🧠 AI Native Summit (In-depth Sharing)

• Time: March 27, 09:00–16:00

• Location: Van der Valk Hotel Amsterdam – Zuidas

• Speaker: Xiao Zhang

Topic:

HAMi: Heterogeneous GPU Virtualization and Scheduling for AI-Native Infrastructure

Key Content:

• Resource layer vs. control layer in AI infrastructure

• Heterogeneous GPU virtualization and scheduling architecture

• Kubernetes' evolution path as an AI control plane

Beyond HAMi: What Else to Watch

If you're attending KubeCon this year, we recommend focusing on sessions related to GPU, device management, and AI workloads, including Device Management, DRA, AI workload scheduling, and GPU observability. While distributed across different venues, these topics all point to a core question: How can Kubernetes achieve stronger resource abstraction and scheduling capabilities in the AI era?

Additionally, Project Pavilion and Cloud Native Theater are worth your time. These areas often provide a more intuitive reflection of the technical directions and ecosystem changes currently focused on by the community.

What Content Will We Bring On-site?

Beyond participating in the conference itself, Dynamia will continuously record and produce content during KubeCon, including on-site sessions, main stage demos, booth exchanges, and observations and summaries of AI infrastructure trends.

This content will be continuously published through Dynamia's official website, WeChat Official Account, and Video Channel. If you can't make it to the venue, you can also stay updated on key conference developments and technical trends through these channels.

👉 Welcome to follow Dynamia's Video Channel and WeChat Official Account. We'll provide continuous updates and in-depth analysis during the conference.

Conclusion

Kubernetes is gradually evolving from a container orchestration platform to the control plane of AI infrastructure, and GPUs are becoming core resources in this system. In this process, achieving GPU sharing, virtualization, and efficient scheduling will directly impact the cost and efficiency of AI systems.

If you're also thinking about these issues, welcome to connect with us during KubeCon Europe 2026.

📍 HAMi Booth: P-13B

Dynamia will be on-site representing the HAMi community to meet you all.