Robertjam954/multimodal_rag_application / .claude/skills/airunway-aks-setup
airunway-aks-setup
VerifiedSet up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: "setup AI Runway", "onboard AKS cluster", "install AI Runway", "airunway setup", "deploy model to AKS", "GPU inference on AKS", "KAITO setup on AKS", "run LLM on AKS", "vLLM on AKS", "set up model serving on AKS", "AI Runway controller".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.0 KB |
| references/gpu-profiles.md | markdown | 2.5 KB |
| references/model-sizing.md | markdown | 1.8 KB |
| references/powershell-notes.md | markdown | 3.1 KB |
| references/steps/step-1-verify.md | markdown | 1.9 KB |
| references/steps/step-2-controller.md | markdown | 1.0 KB |
| references/steps/step-3-gpu.md | markdown | 834 B |
| references/steps/step-4-provider.md | markdown | 2.0 KB |
| references/steps/step-5-deploy.md | markdown | 3.6 KB |
| references/steps/step-6-summary.md | markdown | 1.7 KB |
| references/troubleshooting.md | markdown | 1.5 KB |
references/steps/step-5-deploy.md
View on GitHub# Step 5 — First Model Deployment
**Goal**: Deploy a starter model that fits the cluster's GPU capacity and reach `Ready` status.
**Model recommendations** (based on cluster VRAM from Step 3 — see [gpu-profiles.md](../gpu-profiles.md) for full sizing guide):
| Cluster Capacity | Recommended Model | Provider | Notes |
|-----------------|-------------------|----------|-------|
| CPU-only | `google/gemma-3-1b-it-qat-q8_0-gguf` | KAITO (llama.cpp) | GGUF Q8 quantized; runs on CPU |
| 1× T4 (16 GB) | `microsoft/Phi-3-mini-4k-instruct` | KAITO (vLLM) | Small, fast; fits T4 with headroom |
| 1× A10G or L4 (24 GB) | `meta-llama/Llama-3.1-8B-Instruct` | KAITO (vLLM) | Good general-purpose starter (gated — needs HF token) |
| 1× A100 40 GB | `microsoft/Phi-3-medium-128k-instruct` | KAITO (vLLM) | ~28 GB float16; non-gated; MIT license |
| 1× A100 80 GB / H100 | `meta-llama/Llama-3.1-8B-Instruct` | KAITO (vLLM) | Oversized for 8B; suggest 70B with tensor parallelism if more GPUs available |
| 4× A100 80 GB | `meta-llama/Llama-3.1-70B-Instruct` | KAITO (vLLM, tensor parallel) | Large model; requires tensor parallelism; gated — needs HF token |
Present recommendation. Ask user to confirm or choose their own model.
## Naming Convention
- **`model-name`**: A DNS-safe Kubernetes resource name derived from the model ID (e.g., `meta-llama/Llama-3.1-8B-Instruct` → `llama-3-1-8b-instruct`)
- **`model-id`**: The full HuggingFace model identifier (e.g., `meta-llama/Llama-3.1-8B-Instruct`)
## Gated Models (HuggingFace Token)
Llama-family models are gated on HuggingFace and require an access token. Read the token interactively to avoid exposing it in shell history:
```bash
# Read token without echo, store in a securely permissioned temp file
hf_token_file="$(mktemp)"
trap 'rm -f "$hf_token_file"' EXIT
read -r -s -p "Enter HuggingFace token: " hf_token
printf '\n'
printf '%s' "$hf_token" > "$hf_token_file"
chmod 600 "$hf_token_file"
unset hf_token
kubectl create secret generic hf-token \
--from-file=token="$hf_token_file" \
-n <namespace> \
--dry-run=client -o yaml | kubectl apply -f -
```
> See [powershell-notes.md](../powershell-notes.md) for the PowerShell equivalent.
## Apply the ModelDeployment CR
Use the appropriate manifest based on whether the model is gated.
**For gated models (Llama etc. — requires HuggingFace token):**
```bash
kubectl apply -f - <<EOF
apiVersion: airunway.ai/v1alpha1
kind: ModelDeployment
metadata:
name: <model-name>
namespace: <namespace>
spec:
model:
id: <model-id>
huggingFaceTokenSecretRef:
name: hf-token
key: token
provider:
name: <provider-name>
EOF
```
**For non-gated models (Phi-3, Gemma etc. — no token required):**
```bash
kubectl apply -f - <<EOF
apiVersion: airunway.ai/v1alpha1
kind: ModelDeployment
metadata:
name: <model-name>
namespace: <namespace>
spec:
model:
id: <model-id>
provider:
name: <provider-name>
EOF
```
> See [powershell-notes.md](../powershell-notes.md) for the PowerShell equivalent.
## Monitor Deployment
```bash
kubectl get modeldeployment <model-name> -n <namespace> -w
```
Wait until `STATUS = Ready`. If not ready within 10 minutes:
- `kubectl describe modeldeployment <model-name> -n <namespace>` — check events
- `kubectl get pods -l modeldeployment=<model-name> -n <namespace>` — check pod status
> **Note:** Large models (13B+) may take significantly longer than 10 minutes because weights must be downloaded first. For 70B models, expect 20–40+ minutes depending on network speed. Check pod logs to confirm download progress rather than assuming failure.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |