services:
  sglang:
    image: uhub.service.ucloud.cn/umirror/sglang:dev-dsv41
    shm_size: "32gb"
    ipc: host
    privileged: true

    ports:
      - "30000:30000"

    volumes:
      - /data:/data

    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

    command: >-
      sglang serve
      --trust-remote-code
      --model-path /data/models/DeepSeek-V4.1-Flash
      --tp 4
      --ep-size 4
      --mem-fraction-static 0.75
      --attention-backend dsv4
      --moe-runner-backend flashinfer_mxfp4
      --enable-decoder-swa-bounded-replay
      --cuda-graph-max-bs-decode 64
      --reasoning-parser auto
      --tool-call-parser auto
      --max-running-requests 64
      --host 0.0.0.0
      --port 30000
      --enable-cache-report
      --enable-metrics
      --enable-prefill-cp 
      --cp-strategy interleave
      --json-model-override-args '{"vision_n_layers": 0}'