Einblicke, Tutorials und Neuigkeiten von unserem Team
HAMi v2.9.0 is officially released! Ascend 910C user-space virtualization (HAMi-core mode) delivers fine-grained memory and compute sharing, HAMi-DRA reaches production readiness based on Kubernetes DRA standards, Vastai device support is added, and security and observability are comprehensively enhanced.
A CNCF case study on how SNOW Corp., a NAVER subsidiary, uses HAMi for GPU sharing and KEDA for proactive autoscaling to handle 700% viral traffic spikes — achieving 91% MTTR reduction, 85% fewer surge errors, and USD 17.4M in estimated cost savings.
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.
Chen Junchao from SF Technology shares the complete evolution from bare-metal to a multi-cloud hybrid architecture, with an in-depth look at HAMi-based GPU pooling, memory oversubscription, and mixed deployment in production.
HAMi Maintainer Li Mengxuan reveals v2.9 core features for the first time at the Shenzhen Meetup, deep-diving into the DRA technology roadmap and the community vision for unified heterogeneous compute management.
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.
In this HAMi Community Meetup Shenzhen recap, CNCF VP of APAC Keith Chan shares global perspectives on cloud-native evolution trends for AI infrastructure and previews the AI session lineup at KubeCon Shanghai this September.
NIO adopted a hybrid GPU sharing strategy combining HAMi, NVIDIA MIG, and time-slicing to significantly improve GPU utilization across CI, simulation, and inference workloads — achieving 4× utilization gains and 30% reduction in GPU hours.
KubeCon EU 2026 has concluded, and one signal was unmistakable: cloud native is rapidly evolving from an application platform into the foundational layer for AI infrastructure. As the initiator and core driver of the HAMi project, Dynamia made a landmark appearance — from Maintainer Summit and Lightning Talks to the KubeCon main stage Keynote Demo.
Get the latest technical articles, tutorials, and HAMi community updates.