HAMi - GPU Virtualization & Unified Scheduling for K8s

HAMi is an open-source Kubernetes middleware providing GPU compute and memory isolation, flexible GPU slicing, and topology-aware scheduling maximizing utilization for AI inference and training workloads across NVIDIA GPUs and AWS Neuron devices; part of the CNCF ecosystem. Works with NVIDIA GPU Operator, vLLM Production Stack, and Xinference.