Blog

Insights, tutorials, and news from our team

Boardware GPU Virtualization Practice

Community

Beyond GPU Exclusive Access: Unified Training and Inference with HAMi — Boardware's GPU Virtualization in Practice

GPU management in research labs has always been a headache. Boardware spent three years evolving from VM-exclusive access to a Kubernetes + HAMi cloud-native solution, ultimately achieving physical isolation of Agent RL training and inference on a 12-GPU cluster. This is the seventh article in the HAMi Community Meetup Shenzhen recap series.

CMB Heterogeneous Compute Infrastructure on HAMi

Customer Stories

How China Merchants Bank Built a Heterogeneous Compute Infrastructure with HAMi: 100% GPU Pooling Rate, 30% Reduction in Cross-Node Scheduling

China Merchants Bank built a unified heterogeneous compute infrastructure on HAMi, achieving super-node dual-chip module adaptation (100% GPU pooling rate), vNPU-Core software partitioning (1 GB VRAM / 1% compute granularity), and three-tier topology-aware scheduling (30% reduction in cross-node scheduling). The solutions have been contributed back to the HAMi open-source community.

HAMi Shenzhen Meetup Recap

Community

HAMi Community Meetup Shenzhen Recap: Seven Experts Discuss the Cloud-Native Future of AI Compute

On April 25, 2026, the HAMi Community successfully held its third offline Meetup in Shenzhen. Seven technical experts from CNCF, SF Technology, China Merchants Bank, Enflame, Sangfor, BroadWare Technology, and Dynamia AI gathered to discuss AI infrastructure cloud-native evolution, GPU compute pooling, heterogeneous scheduling, and DRA technology outlook.

Subscribe to our blog

Get the latest technical articles, tutorials, and HAMi community updates.

Blog - Dynamia AI | GPU Virtualization & HAMi