name: gpu-lab-sglang
services:
  sglang:
    image: lmsysorg/sglang:v0.5.12-cu129-runtime
    container_name: gpu-lab-sglang
    network_mode: host
    ipc: host
    shm_size: "32gb"
    env_file:
      - active/current.env
    volumes:
      - /root/models:/models:ro
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    entrypoint: ["python3", "-m", "sglang.launch_server"]
    command:
      - --model-path
      - ${MODEL_PATH}
      - --served-model-name
      - ${SERVED_NAME}
      - --host
      - "0.0.0.0"
      - --port
      - "8010"
      - --tp-size
      - ${TP_SIZE}
      - --mem-fraction-static
      - ${GPU_MEM_UTIL}
      - --context-length
      - ${MAX_MODEL_LEN}
      - --disable-flashinfer
      - --disable-flashinfer-sampling
    restart: "no"