---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: llama-swap
  namespace: llama
spec:
  replicas: 1
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app: llama-swap
  template:
    metadata:
      labels:
        app: llama-swap
    spec:
      initContainers:
        - name: download-whisper
          image: ghcr.io/mostlygeek/llama-swap:unified-vulkan-2026-05-21
          command:
            - sh
            - -c
            - |
              mkdir -p /root/.cache/whisper
              if [ ! -f /root/.cache/whisper/ggml-small.bin ]; then
                echo "Downloading whisper-small model..."
                curl -L -o /root/.cache/whisper/ggml-small.bin \
                  https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin
              else
                echo "whisper-small model already present, skipping download"
              fi
              if [ ! -f /root/.cache/ffmpeg/ffmpeg ]; then
                echo "Downloading static ffmpeg..."
                mkdir -p /root/.cache/ffmpeg
                curl -L -o /root/.cache/ffmpeg/ffmpeg.tar.gz \
                  https://johnvansickle.com/ffmpeg/releases/ffmpeg-release-amd64-static.tar.gz
                tar -xzf /root/.cache/ffmpeg/ffmpeg.tar.gz -C /root/.cache/ffmpeg --wildcards '*/ffmpeg' --strip-components=1
                rm /root/.cache/ffmpeg/ffmpeg.tar.gz
                chmod +x /root/.cache/ffmpeg/ffmpeg
              else
                echo "ffmpeg already present, skipping download"
              fi
          volumeMounts:
            - name: models
              mountPath: /root/.cache
      containers:
        - name: llama-swap
          image: ghcr.io/mostlygeek/llama-swap:unified-vulkan-2026-05-21
          imagePullPolicy: IfNotPresent
          command:
            - llama-swap
          args:
            - --config=/config/config.yaml
            - --watch-config
          ports:
            - containerPort: 8080
              name: http
              protocol: TCP
          volumeMounts:
            - name: models
              mountPath: /root/.cache
            - name: models
              mountPath: /usr/local/bin/ffmpeg
              subPath: ffmpeg/ffmpeg
            - mountPath: /dev/kfd
              name: kfd
            - mountPath: /dev/dri
              name: dri
            - mountPath: /config
              name: config
          securityContext:
            privileged: true
      volumes:
        - name: models
          persistentVolumeClaim:
            claimName: llama-models-lvmssd
        - name: kfd
          hostPath:
            path: /dev/kfd
            type: CharDevice
        - name: dri
          hostPath:
            path: /dev/dri
            type: Directory
        - name: config
          configMap:
            name: llama-swap
---
apiVersion: v1
kind: Service
metadata:
  name: llama
  namespace: llama
spec:
  type: ClusterIP
  ports:
    - name: http
      port: 11434
      targetPort: 8080
      protocol: TCP
  selector:
    app: llama-swap