2026
- January 20 - HAMi v2.8.0 Release: Full DRA Support and High Availability Scheduling - Towards Standardized GPU Resource Management
- March 19 - HAMi at KubeCon Europe 2026: Building the GPU Resource Layer in Kubernetes
- March 23 - From Device Plugin to DRA: GPU Scheduling Paradigm Upgrade and HAMi-DRA Practice Review
- March 31 - KubeCon EU 2026 Recap: HAMi From Project Pavilion to Main Stage Keynote Demo
- April 13 - Introducing HAMi WebUI: GPU Monitoring Dashboard for Kubernetes
- May 11 - HAMi v2.9.0 Release: Ascend User-Space Partitioning, DRA Generally Available, and Scheduler Ecosystem Expansion
- May 28 - Validating AI Agent-Driven GPU Management on Kubernetes with HAMi and kagent
- June 10 - HAMi at KubeCon + CloudNativeCon India 2026
- June 20 - HAMi-core Adopted by NVIDIA KAI Scheduler: GPU Sharing Enters the Hard-Isolation Era
- June 29 - HAMi at KubeCon + CloudNativeCon India 2026: Bringing GPU Sharing to the Community
- July 2 - HAMi Moves to CNCF Incubating Stage
- July 16 - Are You Making Good Use of Your Compute? Three Stages of vLLM Inference Cluster Optimization
- August 1 - HAMi at KubeCon + CloudNativeCon Japan 2026
- August 3 - LFX Mentorship 2026 Term 3: Four Open-Source GPU Sharing Projects Open for Applications
- August 11 - GPU Memory Hard Isolation with KAI Scheduler and HAMi: How It Works and How to Verify It
- August 17 - Soft-Slicing Ascend vNPU with Volcano and HAMi-core: How It Works and How We Verified It
- August 20 - Does Kubernetes DRA Replace HAMi?
- August 21 - HAMi v2.10.0 Release: Flexible MIG, Composable Scheduling, and an Expanded Accelerator Ecosystem
- August 25 - HAMi at KubeCon China 2026: A Keynote, Two Talks, and a Booth in Shanghai
- August 26 - Composable GPU Scheduling Policies: How mutex, binpack, spread, and numa Work Together
