# Documentation: # https://docs.sglang.ai/backend/server_arguments.html#common-launch-commands services: mineru-sglang: image: mineru-sglang:latest container_name: mineru-sglang restart: always ports: - 30000:30000 environment: MINERU_MODEL_SOURCE: local entrypoint: mineru-sglang-server command: --host 0.0.0.0 --port 30000 # --enable-torch-compile # You can also enable torch.compile to accelerate inference speed by approximately 15% # --dp 2 # If you have more than two GPUs with 24GB VRAM or above, you can use sglang's multi-GPU parallel mode to increase throughput # --tp 2 # If you have two GPUs with 12GB or 16GB VRAM, you can use the Tensor Parallel (TP) mode # --mem-fraction-static 0.7 # If you have two GPUs with 11GB VRAM, in addition to Tensor Parallel mode, you need to reduce the KV cache size ulimits: memlock: -1 stack: 67108864 ipc: host healthcheck: test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"] deploy: resources: reservations: devices: - driver: nvidia device_ids: ["0"] capabilities: [gpu]