Tag: #Kubernetes
Kubernetes, DevOps and MLOps, written from things we ran and measured ourselves · 2 posts
Multi-tenant GPU Scheduling and Capacity Planning
Starting from the limitations of how the default scheduler handles GPUs, this post outlines the design differences between Kueue and Volcano, topology-aware placement, the isolation limits of GPU sharing, and the current
2026-10-08 · 37 min read #Kubernetes#GPU#Kueue#Volcano#스케줄링Hybrid GPU Kubernetes with Cilium and Istio Networking
We summarize the choices, network paths, and role divisions between Cilium and Istio when combining on-premises GPU nodes and cloud nodes into a single cluster or multiple clusters. We focus on how long-lived connections
2026-10-08 · 46 min read #Kubernetes#하이브리드클라우드#GPU#Cilium#Istio