apiVersion: serving.kserve.io/v1beta1
kind: InferenceService
metadata:
  annotations:
    serving.kserve.io/deploymentMode: RawDeployment
  labels:
    app.kubernetes.io/name: llm-reasoning
    app.kubernetes.io/part-of: llm-serving
  name: reasoning
  namespace: llm-serving
spec:
  predictor:
    containers:
    - args:
      # DeepSeek-R1-Distill-32B retired: tool_choice="auto" (what pi sends)
      # hit a documented vLLM/R1-family conflict -- the model narrated fake
      # tool_calls in its <think> block instead of emitting real ones,
      # regardless of parser. Tried swapping to a Kimi-distilled Qwen3.6
      # MoE checkpoint and an AWQ-quantized Qwen3-30B-A3B first -- both
      # failed on real, separate blockers (unrecognized model_type; then
      # marlin INT4 kernels needing compute capability 80+, but worker-1's
      # GPU is sm70/V100). Landed on dense Qwen3-32B instead: native Qwen3
      # tool-call format (no narration bug), bnb-4bit works fine on sm70
      # (proven by the old DeepSeek config already), and no MoE
      # arch/quantization risk this time.
      - --model=unsloth/Qwen3-32B-bnb-4bit
      - --served-model-name=reasoning
      - --quantization=bitsandbytes
      - --dtype=float16
      - --kv-cache-dtype=auto
      - --tensor-parallel-size=1
      - --max-model-len=16384
      - --gpu-memory-utilization=0.90
      - --max-num-seqs=4
      - --enable-chunked-prefill
      - --enable-prefix-caching
      # qwen3 is vLLM's dedicated reasoning parser for this family's <think>
      # blocks.
      - --reasoning-parser=qwen3
      # hermes is the documented tool-call parser for general (non-Coder)
      # Qwen3 models -- native chat template support, not narrated text.
      - --enable-auto-tool-choice
      - --tool-call-parser=hermes
      # vLLM 0.11.0's native OffloadingConnector -- spills KV cache blocks
      # to CPU DRAM instead of discarding them on preemption (max-num-seqs=4
      # + max-model-len=16384 means concurrent long sequences compete for
      # the same GPU KV space). No extra dependency, built into vLLM core.
      # num_cpu_blocks=2000 hung the pod at startup on the old model (2000 x
      # ~32MB/block blew well past the pod's memory limit). num_cpu_blocks=32
      # was the safe-recovery value after that -- only ~1GB of real DRAM
      # (32 blocks x 128 tokens x 256KB/token-across-all-64-layers, fp16),
      # basically a token-count safety valve, not real offload capacity.
      # This model: 64 layers, 8 KV heads x 128 head_dim, fp16 -> ~256KB of
      # KV per token across all layers -> ~32MB per 128-token block.
      # num_cpu_blocks=256 -> ~8GB of actual DRAM offload (32,768 tokens),
      # comfortably under the pod's 36Gi limit alongside the ~20GB bnb-4bit
      # weights. Watch real host memory on boot before raising further --
      # block_size=128 tokens matches vLLM's own example.
      # Note: 0.11.0 ships the original (fragmented, small-transfer-block)
      # version of this connector -- 0.12.0 consolidates KV data into one
      # contiguous block per request and is reported an order of magnitude
      # faster for this specific feature, so this is a real but not yet
      # optimal implementation until the image gets bumped.
      - --kv-transfer-config={"kv_connector":"OffloadingConnector","kv_role":"kv_both","kv_connector_extra_config":{"num_cpu_blocks":256,"block_size":128}}
      - --host=0.0.0.0
      - --port=8080
      env:
      - name: VLLM_USE_FLASHINFER_SAMPLER
        value: '0'
      - name: VLLM_ATTENTION_BACKEND
        value: TRITON_ATTN
      - name: HF_HOME
        value: /mnt/models
      image: vllm/vllm-openai:v0.11.0@sha256:014a95f21c9edf6abe0aea6b07353f96baa4ec291c427bb1176dc7c93a85845c
      name: kserve-container
      ports:
      - containerPort: 8080
        protocol: TCP
      readinessProbe:
        httpGet:
          path: /health
          port: 8080
        periodSeconds: 10
      resources:
        limits:
          cpu: '16'
          memory: 36Gi
          nvidia.com/gpu: '1'
        requests:
          cpu: '8'
          memory: 12Gi
          nvidia.com/gpu: '1'
      startupProbe:
        failureThreshold: 80
        httpGet:
          path: /health
          port: 8080
        periodSeconds: 15
      volumeMounts:
      - mountPath: /mnt/models
        name: models
      - mountPath: /dev/shm
        name: shm
    deploymentStrategy:
      type: Recreate
    maxReplicas: 2
    minReplicas: 2
    nodeSelector:
      kubernetes.io/hostname: worker-1
    runtimeClassName: nvidia
    volumes:
    - name: models
      persistentVolumeClaim:
        claimName: llm-models
    - emptyDir:
        medium: Memory
        sizeLimit: 2Gi
      name: shm