Project-HAMi

A comprehensive analysis skill for summarizing HAMi vGPU metrics from Prometheus-style `/metrics` output. It organizes GPU allocation by node, device, pod, and namespace, and produces clear reports covering vGPU core allocation, memory allocation, allocation-based utilization, sharing density, and namespace-level usage patterns.

Use when pods are stuck in Pending, CrashLoopBackOff, or ImagePullBackOff state. Performs event-driven triage to quickly identify root cause, then deep-dives into scheduling failures, resource exhaustion, image pull errors, and crash loops.

Use when testing the HAMi-Core DRA Driver on a kind cluster — covers cluster setup, Helm-based driver install, ResourceClaim configuration, pod scheduling, HAMi-Core memory limit verification via nvidia-smi, and teardown.