% kubectl port-forward svc/llama-3-2-3b 8080:8080
error: cannot attach to *v1.Service: invalid service 'llama-3-2-3b': Service is defined without a selector

% go run cmd/cli/main.go deploy llama-3.2-3b --accelerator metal
📚 Using catalog model: Llama 3.2 3B Instruct

🚀 Deploying LLM inference service
═══════════════════════════════════════════════
Name:        llama-3.2-3b
Namespace:   default
Accelerator: metal
Replicas:    1
Context:     8192 tokens
Image:       ghcr.io/ggml-org/llama.cpp:server
═══════════════════════════════════════════════

📦 Creating Model 'llama-3.2-3b'...
   ✅ Model created

⚙️  Creating InferenceService 'llama-3.2-3b'...
   ✅ InferenceService created

Waiting for deployment to be ready (timeout: 10m0s)...


[2s] Model: Ready, Service: Ready (1/1 replicas)

✅ Deployment ready!
═══════════════════════════════════════════════
Model:       llama-3.2-3b
Size:        2.2 GiB
Path:        /tmp/llmkube-models/086521cd8ae5819e/model.gguf
Endpoint:    http://llama-3-2-3b.default.svc.cluster.local:8080/v1/chat/completions
Replicas:    1/1
═══════════════════════════════════════════════

🧪 To test the inference endpoint:

  # Port forward the service
  kubectl port-forward -n default svc/llama-3-2-3b 8080:8080

  # Send a test request
  curl http://localhost:8080/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{"messages":[{"role":"user","content":"What is 2+2?"}]}'

% kubectl port-forward svc/llama-3-2-3b 8080:8080
error: cannot attach to *v1.Service: invalid service 'llama-3-2-3b': Service is defined without a selector