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:
      # Swapped off DeepSeek-R1-Distill-Qwen-32B: tool_choice="auto" (what pi
      # sends) hit a documented vLLM architecture conflict for R1-family
      # models -- the model narrated fake tool-call completions in its
      # <think> block instead of emitting real tool_calls, regardless of
      # parser combo tried (deepseek_v3 400s outright, hermes parsed but the
      # model itself never called out to the real tool-call path). Root
      # cause is upstream in the R1 distillation, not this config -- Qwen3's
      # own tool-call format is natively supported instead.
      #
      # First attempt was a Kimi-K2.6-distilled Qwen3.6-35B-A3B checkpoint
      # (lordx64/Qwen3.6-35B-A3B-Kimi-K2.6-Reasoning-Distilled) -- crashed on
      # boot: `model type qwen3_5_moe` unrecognized by transformers/vLLM
      # 0.11.0, not a config problem, a genuinely unsupported/obscure
      # architecture.
      #
      # Second attempt was cpatonn's pre-quantized "AWQ-4bit" build of the
      # official Qwen3-30B-A3B-Thinking-2507 -- also crashed, on two
      # different real issues in sequence: (1) it's actually compressed-tensors
      # format despite the repo name, and (2) once that was fixed, vLLM raised
      # `RuntimeError: Quantization scheme is not supported for the current
      # GPU. Min capability: 80. Current capability: 70.` -- worker-1's GPU is
      # compute capability 7.0 (V100), and AWQ/GPTQ/compressed-tensors marlin
      # INT4 kernels all require sm80+ (Ampere or newer). This node cannot run
      # any of those quant formats, full stop -- only bitsandbytes or full
      # precision work here (which is exactly why the old DeepSeek config used
      # bitsandbytes to begin with).
      #
      # Using the official full-precision Qwen/Qwen3-30B-A3B-Thinking-2507
      # checkpoint with on-the-fly bitsandbytes quantization instead --
      # architecture itself already confirmed good (Qwen3MoeForCausalLM
      # resolved cleanly in both prior attempts).
      - --model=Qwen/Qwen3-30B-A3B-Thinking-2507
      - --served-model-name=reasoning
      - --quantization=bitsandbytes
      - --dtype=bfloat16
      - --kv-cache-dtype=auto
      - --tensor-parallel-size=1
      - --max-model-len=16384
      - --gpu-memory-utilization=0.90
      # 30B total MoE at pre-quantized AWQ-4bit is ~15-16GB weights on a
      # 32GB card at 0.90 util (~29.5GB budget) -- meaningfully more KV-cache
      # headroom than the old DeepSeek-32B config had, so restoring the
      # original max-num-seqs=4 rather than starting conservative again.
      - --max-num-seqs=4
      - --enable-chunked-prefill
      - --enable-prefix-caching
      # qwen3 is vLLM's dedicated reasoning parser for this family's <think>
      # blocks -- official pairing per Qwen3-Thinking's own deployment docs.
      - --reasoning-parser=qwen3
      # hermes is the documented tool-call parser for general Qwen3 models
      # (qwen3_coder/qwen3_xml are Coder-variant-only).
      - --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 (one
      # pinned host tensor per layer, sized per CPU block -- oversized enough
      # to stall pinning that much host memory). 32 is a small, known-safe
      # starting point independent of this model's own layer count --
      # confirm it comes up healthy, then watch real host memory usage and
      # raise it deliberately rather than guessing a round number again.
      # 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":32,"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'
          # Bumped from 36Gi -- on-the-fly bnb quantization stages full
          # bf16 shards (~60GB total model) transiently in host RAM during
          # load before discarding them, unlike loading an already-quantized
          # checkpoint. Request left unchanged (node is already at 84% memory
          # request allocation) -- only the OOM ceiling moves.
          memory: 48Gi
          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