apiVersion: apps/v1
kind: Deployment
metadata:
  name: clef-candle
  namespace: llm-serving
  labels:
    app.kubernetes.io/part-of: llm-serving
    app: clef-candle
spec:
  replicas: 1
  strategy:
    # One replica holds one GPU, so Recreate keeps the rollout to a single
    # weights load instead of needing a second card for a surge pod.
    type: Recreate
  selector:
    matchLabels:
      app: clef-candle
  template:
    metadata:
      labels:
        app.kubernetes.io/part-of: llm-serving
        # The clef-serve Service now selects this label (see clef-serve.yaml),
        # so clients keep addressing clef-serve:80 unchanged. The reference
        # pytorch Deployment must stay at replicas 0 while this runs, or the
        # Service splits traffic across two different implementations.
        app: clef-candle
    spec:
      # Required. Without the nvidia runtime class libcuda.so is never injected
      # and candle-vllm panics in cudarc at startup.
      runtimeClassName: nvidia
      containers:
        - name: candle
          # :sm70 is built by .gitea/workflows/candle-vllm-sm70.yaml on every
          # merge to main. It MUST be a build that contains the GDN conv fix
          # (candle-vllm PR: feat/clef-systemone). Older :sm70 images zero the
          # key channel band in causal_conv1d_fwd, which starves the delta rule
          # and makes every linear-attention layer return zero. The symptom is
          # a well-formed /v1/systemone response with wrong answers, not an error.
          image: forgejo.riotpiao.com/riotpiao-poimen/candle-vllm:sm70
          # :sm70 is a moving tag. Default IfNotPresent keeps a cached copy and a
          # rebuilt image never reaches the pod, so a merged fix looks like it did
          # not land. Always forces the pull on every pod start.
          imagePullPolicy: Always
          command: ["/usr/local/bin/candle-vllm"]
          # clef-flash is a hybrid Qwen3_5 model: 8 full-attention layers plus 24
          # GDN layers that carry per-sequence recurrent state. It runs on ONE
          # card because the state is not shardable the way attention KV is.
          args:
            - --w
            - /mnt/models/clef-flash
            - --d
            - "0"
            - --dtype
            - f16
            - --p
            - "8080"
            - --max-num-seqs
            - "4"
            # About 66.8K KV tokens. Clef is a single-shot classifier-style
            # endpoint, so it does not need the coder's pool.
            - --kv-fraction
            - "0.30"
            # Prefix caching stays on: clef requests repeat the schema block.
            - --prefill-chunk-size
            - "1024"
          ports:
            - containerPort: 8080
          resources:
            limits:
              cpu: "8"
              memory: 32Gi
              nvidia.com/gpu: "1"
            requests:
              cpu: "4"
              memory: 16Gi
              nvidia.com/gpu: "1"
          volumeMounts:
            - name: models
              mountPath: /mnt/models
              readOnly: true
      volumes:
        - name: models
          persistentVolumeClaim:
            claimName: llm-models