Dynamia AI on AWS
Integration
Deploy Dynamia AI Platform on AWS with EKS
Follow this battle-tested checklist to prepare IAM, install cluster add-ons, and roll out the Dynamia AI Platform on Amazon EKS in about an hour.
Blog
Einblicke, Tutorials und Neuigkeiten von unserem Team
Device-Aware GPU Scheduling
Technischer Deep Dive
Two Axes, Four Patterns: Device-Aware GPU Binpack/Spread on K8s with HAMi
Explore a practical 2×2 framework for GPU scheduling in Kubernetes: combining node and GPU-level binpack/spread strategies. Learn how HAMi enables device-aware scheduling beyond native K8s capabilities, with hands-on examples of four distinct patterns that balance cost efficiency, GPU availability, and performance for AI workloads.
AWS Trainium Integration
Integration
Virtualizing Any GPU on AWS with HAMi: Free Memory Isolation
This article takes the PR as an entry point, combined with community Issues and mailing records, to fully restore a 'HAMi × vLLM' landing path from deployment to verification, helping you quickly achieve multi-model deployment and resource reuse in Kubernetes.
vLLM Integration
Integration
Global Co-building: vLLM Community Natively Supports HAMi, Inference Efficiency Leap — Contribution from a Spanish Developer
This article takes the PR as an entry point, combined with community Issues and mailing records, to fully restore a 'HAMi × vLLM' landing path from deployment to verification, helping you quickly achieve multi-model deployment and resource reuse in Kubernetes.
Autonomous Driving Case Study
Customer Stories
【HAMi Project Team | User Case】A Leading Autonomous Driving Company Achieves Fine-Grained GPU Management and Maximizes Resource Utilization with HAMi
In its core model training scenarios, a leading autonomous driving company utilizes multi-machine distributed training with scheduling frameworks like Ray and Volcano.
Prep Education × HAMi
Customer Stories
【PREP EDU | HAMi Project Team】Southeast Asia's Potential AI Education Unicorn Builds an Efficient GPU Inference Platform with HAMi
In the fast-growing field of AI education, PREP EDU (prepedu.com) is emerging as a focal point in Southeast Asia's EdTech sector.
Understanding Reservation Pod
Technischer Deep Dive
【Run:ai KAI-Scheduler Deep Dive】Supplement: Demystifying How the Reservation Pod Discovers GPU Allocation Details
Yesterday, we took a deep dive into how KAI-Scheduler achieves fractional GPU sharing. Thank you all for your attention and lively discussion! A reader pointed out a key technical detail that needed further clarification, and today we're going to break down that very issue.
Run:AI KAI vs HAMi
Technischer Deep Dive
Nvidia's Open-Sourced KAI-Scheduler vs. HAMi: An Analysis of Technical Paths to GPU Sharing and a Look at Future Synergy
Today, we're doing a technical deep dive to compare the implementation methods of KAI-Scheduler and HAMi, and to look ahead at the possibilities for future collaboration.
HAMi × Koordinator v1.6
Produktversion
Open-source Synergy, Koordinator v1.6 Released: Teaming Up with the HAMi Community to Redefine AI/ML Heterogeneous Resource Scheduling
Koordinator v1.6 has been released, featuring deep collaboration with the CNCF Sandbox project HAMi to introduce strong GPU sharing isolation capabilities, providing a more efficient resource scheduling and isolation solution for AI training and inference scenarios.
Subscribe to our blog
Get the latest technical articles, tutorials, and HAMi community updates.