DynamiaDynamia
Events

HAMi at KubeCon India 2026: From Amsterdam to Mumbai, Taking GPU Sharing Global

DynamiaEvents
HAMi at KubeCon India 2026
Dynamia · Open-source AI infrastructure

After the landmark Keynote Demo at KubeCon EU 2026, the HAMi community is heading to KubeCon India 2026. CNCF Ambassador Saiyam Pathak will deliver a keynote featuring a live GPU sharing demo on NVIDIA DGX Spark.

On this page

Three months ago, Dynamia and the HAMi community made a landmark appearance at KubeCon EU 2026 — from the Maintainer Summit and Lightning Talks to the Project Pavilion, and ultimately taking the KubeCon main stage for a Keynote Demo. HAMi became the first China-originated open source project to present on the KubeCon EU main stage.

Now, that momentum continues. The HAMi community is heading to KubeCon + CloudNativeCon India 2026, June 18–19 in Mumbai.

Why KubeCon India Matters for HAMi

In our KubeCon EU 2026 recap, we made a key observation: Kubernetes is moving from "orchestrating applications" to "orchestrating compute." This trend isn't limited to one regional market — it's global.

India is one of the fastest-growing developer communities in the world and an important force in the Kubernetes ecosystem. During KubeCon EU, Indian community contributors Rudraksh Karpe and Shivay Lamba already presented "Kubernetes as the Universal GPU Control Plane for AI Workloads" in the Poster Session — a clear signal that GPU scheduling and sharing demand is growing rapidly worldwide.

HAMi's presence at KubeCon India means the project is evolving from a regional solution into a truly global community.

HAMi @ KubeCon India 2026 Event Overview

🎤 Keynote: From Platforms to AI Factories

This keynote directly addresses the GPU sharing problem in Kubernetes. HAMi virtualizes one physical GPU into multiple slices, each with its own memory budget. The live demo features a MacBook connected to an NVIDIA DGX Spark, running two open-source LLMs simultaneously on a single Blackwell GPU.

Following the KubeCon EU main stage demo, this marks another appearance of HAMi's GPU sharing capabilities on a major conference keynote stage.

🪧 HAMi Booth

  • Booth T-10 · Project Pavilion · Jasmine Hall 1 (Level 3)
  • Time: June 18, 3:30–7:30 PM IST

Stop by to see GPU sharing demos in person, learn about HAMi's fractional GPU allocation, DRA integration, and pick up HAMi stickers.

👥 Meet the Team

The HAMi booth is staffed by community contributors and CNCF Ambassadors:

  • Satyam Soni: CNCF Ambassador, KCD Delhi Organizer, Kubernetes Release Engineering
  • Rudraksh Karpe: Forward Deployed Engineer, Simplismart, GSoC Mentor
  • Shivay Lamba: GSoC Org Admin (Jenkins), Full Stack & AI
  • Shivam Kumar: HAMi (CNCF) Contributor

From KubeCon EU to KubeCon India: HAMi's Global Expansion

Looking back at Dynamia's participation at KubeCon EU 2026, HAMi achieved several key milestones:

  1. Main Stage Keynote Demo: HAMi became the first China-originated open source project to present on the KubeCon EU main stage, demonstrating the transition of GPUs from "devices" to "schedulable resources"
  2. Featured in Cloud Native Landscape: HAMi was mentioned as a representative project during the Keynote, signaling broader recognition of its positioning
  3. Accelerating Global Community Growth: At the Project Pavilion, contributors from India, Europe, and beyond actively participated — a clear sign that HAMi's community footprint is expanding

KubeCon India is the natural continuation of this trajectory. From Amsterdam to Mumbai, HAMi is bringing GPU sharing and AI infrastructure discussions to more developers through localized community engagement.

Join Us

If you're thinking about resource management for AI workloads on Kubernetes, come talk to us on-site.

📍 HAMi Booth: T-10

You can also join the HAMi community online:

See you in Mumbai! 🇮🇳

KEEP READING

Keep reading

All articles
DynamiaCommunity & updates
HAMi positioning in CNCF x PyTorch baseBuilding together · discussions · event notes
Dynamia · Open-source AI infrastructure

HAMi Meetup Shanghai Deep Dive (1): Where Does HAMi Fit in the CNCF × PyTorch Cloud Native AI Foundation?

The model has been able to run and the operation is slow to go online. Keith Chan, Director General of the China District, gave an opening speech at the HAMMI Meetup Shanghai Station, giving a structured collaborative idea of how to create a base for the development of claud-native AI: Hami is located in Scheduling with resource management, assuming the role of heterogenouscompute resources sharing and managing.

Read article
DynamiaCommunity & updates
HAMi Community Round Table: From Users to Co-ConstructorsBuilding together · discussions · event notes
Dynamia · Open-source AI infrastructure

HAMi Meetup Shanghai Deep Dive (7): From User to Co-Builder — Why Enterprises Need a Sustainable HAMi Community

Once an enterprise uses open source software in its production environment, the concerns will gradually extend beyond code: can it be responded to when problems are encountered? How do new needs enter public routes? The Hami Meetup Shanghai Station round-table discussion revolves around real use, contribution thresholds, AI ' s liability boundary for assistive development and community knowledge deposition, providing a different set of judgement than technology selection.

Read article
DynamiaCommunity & updates
HAMi 2.10: Soolation, Scheduling and ObservationBuilding together · discussions · event notes
Dynamia · Open-source AI infrastructure

HAMi Meetup Shanghai Deep Dive (2): After GPU Sharing — Isolation, Scheduling, and Observability in HAMi 2.10

The distribution of a GPU to multiple tasks is only the beginning of resource sharing. Dynamia co-founder and CTO, HAMi Mainlainer Mengxuan Li, at the HAMi Meetup Shanghai Station, presented the progress of V2.10 capabilities, DRA ecological appliance, and v2.11 planning (Remote GPU, CPU NUMA alignment). The main thread for these changes is to enable shared compute resources to be distributed on demand and to be subject to monitoring, observation and diagnosis during their operation.

Read article
Image viewer