4 个 · 按相关度排序
Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use recipe-runner/router-starter before this for normal bring-up.
中文简介正在准备中。当前显示原文说明。
Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load OOM, DCGM/VRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugin).
中文简介正在准备中。当前显示原文说明。
Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load OOM, DCGM/VRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugin).
中文简介正在准备中。当前显示原文说明。
Kolla-Ansible day-2 operations skill for post-deployment infrastructure lifecycle management. Covers service reconfiguration (globals.yml changes, config overrides, prechecks, targeted reconfigure with --tags), minor and major OpenStack upgrades (image pull, upgrade procedure, rollback), container management (restart, logs, health inspection), maintenance mode (compute disable, instance drain, host maintenance), password rotation, certificate renewal, and rolling updates. This skill is for operations after initial deployment -- the kolla-ansible deployment skill covers initial bootstrap and deploy.
中文简介正在准备中。当前显示原文说明。