一键导入
install-maas
Install MaaS (Models as a Service) on a connected RHOAI cluster using this guide's Kustomize manifests and automation scripts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Install MaaS (Models as a Service) on a connected RHOAI cluster using this guide's Kustomize manifests and automation scripts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | install-maas |
| description | Install MaaS (Models as a Service) on a connected RHOAI cluster using this guide's Kustomize manifests and automation scripts. |
| argument-hint | [--model simulator|granite-tiny-gpu|gpt-oss-20b|auto] [--from-phase N] [--skip-models] [--skip-verify] [--with-observability] |
| allowed-tools | Bash(oc *), Bash(./*), Bash(envsubst *), Bash(curl *), Bash(jq *), Bash(grep *), Bash(ls *), Bash(cat *), Bash(date *), Bash(mkdir *), Bash(echo *), Bash(bash *), AskUserQuestion |
Install Models as a Service on an OpenShift cluster with RHOAI using this guide's all-in-one script. No ArgoCD required.
./scripts/setup-maas.sh is the single orchestrator that handles the entire lifecycle - from operator installation through model deployment and verification. Each phase is idempotent; re-running skips what's already done.
./scripts/setup-maas.sh [OPTIONS]
--model <name> -- Model to deploy: simulator (CPU), granite-tiny-gpu (small GPU), gpt-oss-20b (large GPU), auto (auto-detect). Default: auto.--from-phase <N> -- Start from phase N (0-7). Default: 0.--skip-models -- Skip Phase 5 (model deployment).--skip-verify -- Skip Phase 6 (verification).--with-observability -- Also run Phase 7 (COO + telemetry).--dry-run -- Preview without applying.| Phase | What it does | Time |
|---|---|---|
| 0 | Preflight - detect cluster state, decide which phases to run | instant |
| 1 | Operators - oc apply -k manifests/01-prerequisites/operators/, wait for CSVs | 2-5 min |
| 2 | Platform - Kuadrant, UWM, GatewayClass, envsubst Gateway | 2-5 min |
| 3 | RHOAI - DSC with modelsAsService: Managed, Dashboard flags | 3-5 min |
| 4 | MaaS - PostgreSQL secrets/deployment, Authorino TLS, wait for maas-api | 3-5 min |
| 5 | Model - auto-detect GPU, apply Kustomize, wait for Ready | 0.5-15 min |
| 6 | Verify - 6-phase E2E (API, auth, rate limits, cleanup) | 3-5 min |
| 7 | Observability - COO subscription + Gateway TelemetryPolicy | 2-3 min |
Run from the guide repo root (rhoai-maas-guide/).
For a fresh cluster with no MaaS components:
./scripts/setup-maas.sh
This runs Phases 0-6 automatically. The script detects what's already installed and skips completed phases.
./scripts/setup-maas.sh --with-observability
If a previous run failed at Phase 4:
./scripts/setup-maas.sh --from-phase 4
If the platform is already installed and you just want to deploy a model:
./scripts/setup-maas.sh --from-phase 5
Or use the standalone model script for more control:
./scripts/deploy-model.sh --model simulator
./scripts/setup-maas.sh --from-phase 6
Or directly:
./manifests/06-verification/verify.sh
These wrap individual phases for standalone use:
| Script | What it does |
|---|---|
scripts/deploy-model.sh | Phase 5 only - deploy model with GPU auto-detection |
scripts/verify-maas.sh | Phase 6 only - wrapper for manifests/06-verification/verify.sh |
Phase 0 inspects the cluster and reports what's installed. The script uses this to skip phases:
Override with --from-phase N to force re-running from a specific phase.
If a phase fails, the script reports what went wrong. Common fixes:
oc get csv -A --no-headers | grep -v Succeededoc get gateway -n openshift-ingress -o yamloc get datasciencecluster default-dsc -o jsonpath='{.status.conditions}'oc describe pod -n llmThe script ends with a summary: RHOAI version, MaaS API URL, Gateway status, health check, deployed models, and suggested next steps.