Skill UI

This skill provides comprehensive guidance for deploying and managing GPU-accelerated AI inference services on CoreWeave Kubernetes (CKS). It covers best practices including containerization using NVIDIA CUDA base images, configuring specific GPU resource limits (A100/H100), setting up robust health checks, and executing controlled rolling updates. Ideal for managing multi-model inference and scaling demanding AI workloads in a cloud environment.

This runbook provides structured steps for responding to critical production incidents on the CoreWeave platform. Use it when dealing with GPU workload failures, inference service outages, or general Kubernetes resource issues. It guides users through checking pod status, node health, and diagnosing common model loading errors to ensure rapid service recovery.

A comprehensive solution for monitoring CoreWeave cluster events and GPU workload status using webhooks. It tracks critical lifecycle events such as pod readiness, job completion, volume attachment, and node health. Essential for building automated scaling, alerting, and recovery pipelines for large-scale GPU-accelerated inference and training workloads.