GPU Sharing Strategies for Multi-Tenant Kubernetes: MIG, Time-Slicing, and MPS
NVIDIA's GPU sharing mechanisms — MIG, time-slicing, and MPS — are gaining traction as teams run multiple inference workloads per GPU.
cost-optimization
3 posts
Production Cost Optimization Patterns with Karpenter
Spot-to-Spot consolidation, instance diversification, right-sizing pod requests, and the real-world strategies that cut Kubernetes compute costs by 20-40%.
KEDA and Karpenter Together — Pod and Node Scaling Synergy
Combining KEDA's event-driven pod scaling with Karpenter's just-in-time node provisioning for a fully reactive, cost-efficient Kubernetes autoscaling stack.