| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133 |
- services:
- mineru-openai-server:
- image: mineru:latest
- container_name: mineru-openai-server
- restart: always
- profiles: ["openai-server"]
- ports:
- - 30000:30000
- environment:
- MINERU_MODEL_SOURCE: local
- entrypoint: mineru-openai-server
- command:
- # ==================== Engine Selection ====================
- # WARNING: Only ONE engine can be enabled at a time!
- # Choose 'vllm' OR 'lmdeploy' (uncomment one line below)
- --engine vllm
- # --engine lmdeploy
-
- # ==================== vLLM Engine Parameters ====================
- # Uncomment if using --engine vllm
- --host 0.0.0.0
- --port 30000
- # Multi-GPU configuration (increase throughput)
- # --data-parallel-size 2
- # Single GPU memory optimization (reduce if VRAM insufficient)
- # --gpu-memory-utilization 0.5 # Try 0.4 or lower if issues persist
- # ==================== LMDeploy Engine Parameters ====================
- # Uncomment if using --engine lmdeploy
- # --server-name 0.0.0.0
- # --server-port 30000
- # Multi-GPU configuration (increase throughput)
- # --dp 2
- # Single GPU memory optimization (reduce if VRAM insufficient)
- # --cache-max-entry-count 0.5 # Try 0.4 or lower if issues persist
- 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"] # Modify for multiple GPUs: ["0", "1"]
- capabilities: [gpu]
- mineru-api:
- image: mineru:latest
- container_name: mineru-api
- restart: always
- profiles: ["api"]
- ports:
- - 8000:8000
- environment:
- MINERU_MODEL_SOURCE: local
- entrypoint: mineru-api
- command:
- # ==================== Server Configuration ====================
- --host 0.0.0.0
- --port 8000
- # ==================== vLLM Engine Parameters ====================
- # Multi-GPU configuration
- # --data-parallel-size 2
- # Single GPU memory optimization
- # --gpu-memory-utilization 0.5 # Try 0.4 or lower if VRAM insufficient
- # ==================== LMDeploy Engine Parameters ====================
- # Multi-GPU configuration
- # --dp 2
- # Single GPU memory optimization
- # --cache-max-entry-count 0.5 # Try 0.4 or lower if VRAM insufficient
- ulimits:
- memlock: -1
- stack: 67108864
- ipc: host
- deploy:
- resources:
- reservations:
- devices:
- - driver: nvidia
- device_ids: ["0"] # Modify for multiple GPUs: ["0", "1"]
- capabilities: [gpu]
- mineru-gradio:
- image: mineru:latest
- container_name: mineru-gradio
- restart: always
- profiles: ["gradio"]
- ports:
- - 7860:7860
- environment:
- MINERU_MODEL_SOURCE: local
- entrypoint: mineru-gradio
- command:
- # ==================== Gradio Server Configuration ====================
- --server-name 0.0.0.0
- --server-port 7860
-
- # ==================== Gradio Feature Settings ====================
- # --enable-api false # Disable API endpoint
- # --max-convert-pages 20 # Limit conversion page count
-
- # ==================== Engine Selection ====================
- # WARNING: Only ONE engine can be enabled at a time!
-
- # Option 1: vLLM Engine (recommended for most users)
- --enable-vllm-engine true
- # Multi-GPU configuration
- # --data-parallel-size 2
- # Single GPU memory optimization
- # --gpu-memory-utilization 0.5 # Try 0.4 or lower if VRAM insufficient
- # Option 2: LMDeploy Engine
- # --enable-lmdeploy-engine true
- # Multi-GPU configuration
- # --dp 2
- # Single GPU memory optimization
- # --cache-max-entry-count 0.5 # Try 0.4 or lower if VRAM insufficient
- ulimits:
- memlock: -1
- stack: 67108864
- ipc: host
- deploy:
- resources:
- reservations:
- devices:
- - driver: nvidia
- device_ids: ["0"] # Modify for multiple GPUs: ["0", "1"]
- capabilities: [gpu]
|