# Qwen3.8-27B with MTP speculative decoding served by llama.cpp.
# The primary and draft GGUFs are downloaded by an initContainer into the
# shared model PVC before llama-server starts.
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: llamacpp-qwen38-27b
  namespace: llamacpp
  labels:
    app: llamacpp
    model: qwen3.8-27b
spec:
  replicas: 1
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app: llamacpp
      model: qwen3.8-27b
  template:
    metadata:
      labels:
        app: llamacpp
        model: qwen3.8-27b
    spec:
      nodeSelector:
        kubernetes.io/arch: amd64
        hardware: high-memory
      initContainers:
      - name: fetch-models
        image: alpine:3.20
        command: ["/bin/sh", "-c"]
        args:
        - |
          set -eu
          apk add --no-cache curl
          for entry in \
            "https://huggingface.co/ggml-org/Qwen3.8-27B-GGUF/resolve/main/Qwen3.8-27B-Q4_K_M.gguf|Qwen3.8-27B-Q4_K_M.gguf" \
            "https://huggingface.co/ggml-org/Qwen3.8-27B-GGUF/resolve/main/mtp-Qwen3.8-27B-Q4_0.gguf|mtp-Qwen3.8-27B-Q4_0.gguf"; do
            url=${entry%%|*}
            file=${entry##*|}
            if [ -s "/models/$file" ]; then
              echo "$file already present - skipping download."
              continue
            fi
            echo "Downloading $file ..."
            curl -fL --retry 5 --retry-delay 5 -C - \
              -o "/models/$file.partial" "$url"
            mv "/models/$file.partial" "/models/$file"
            echo "Download complete: $(ls -lh "/models/$file")"
          done
        volumeMounts:
        - name: models
          mountPath: /models
      containers:
      - name: llama-server
        image: ghcr.io/ggml-org/llama.cpp:server-vulkan
        imagePullPolicy: IfNotPresent
        args:
        - -m
        - /models/Qwen3.8-27B-Q4_K_M.gguf
        - --model-draft
        - /models/mtp-Qwen3.8-27B-Q4_0.gguf
        - --spec-default
        - --spec-type
        - draft-mtp
        - --ctx-size
        - "196608"
        - --cache-type-k
        - q8_0
        - --cache-type-v
        - q8_0
        - --reasoning-preserve
        - --fit
        - "off"
        - --agent
        - --chat-template-kwargs
        - '{"reasoning_effort":"medium"}'
        - --alias
        - qwen3.8-27b
        - --host
        - 0.0.0.0
        - --port
        - "8080"
        - --jinja
        ports:
        - name: http
          containerPort: 8080
        resources:
          requests:
            cpu: "1000m"
            memory: 2Gi
          limits:
            cpu: "4000m"
            memory: 24Gi
        readinessProbe:
          httpGet:
            path: /health
            port: 8080
          initialDelaySeconds: 30
          periodSeconds: 10
          failureThreshold: 6
        livenessProbe:
          httpGet:
            path: /health
            port: 8080
          initialDelaySeconds: 600
          periodSeconds: 30
          failureThreshold: 5
        securityContext:
          privileged: true
        volumeMounts:
        - name: models
          mountPath: /models
          readOnly: true
        - name: dri
          mountPath: /dev/dri
      volumes:
      - name: models
        persistentVolumeClaim:
          claimName: llamacpp-models
      - name: dri
        hostPath:
          path: /dev/dri
          type: Directory
---
apiVersion: v1
kind: Service
metadata:
  name: llamacpp-qwen38-27b
  namespace: llamacpp
  labels:
    app: llamacpp
    model: qwen3.8-27b
spec:
  type: ClusterIP
  selector:
    app: llamacpp
    model: qwen3.8-27b
  ports:
  - name: http
    port: 80
    targetPort: 8080