106 lines
3.2 KiB
YAML
106 lines
3.2 KiB
YAML
x-defaults: &defaults
|
|
restart: unless-stopped
|
|
logging:
|
|
driver: json-file
|
|
options:
|
|
max-size: 100m
|
|
max-file: "3"
|
|
|
|
x-mineru-sglang: &mineru-sglang
|
|
<<: *defaults
|
|
image: ${MINERU_DOCKER_IMAGE:-alexsuntop/mineru-sglang:2.2.2}
|
|
environment:
|
|
TZ: ${TZ:-UTC}
|
|
MINERU_MODEL_SOURCE: local
|
|
ulimits:
|
|
memlock: -1
|
|
stack: 67108864
|
|
ipc: host
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
cpus: ${MINERU_SGLANG_CPU_LIMIT:-8.0}
|
|
memory: ${MINERU_SGLANG_MEMORY_LIMIT:-4G}
|
|
reservations:
|
|
cpus: ${MINERU_SGLANG_CPU_RESERVATION:-1.0}
|
|
memory: ${MINERU_SGLANG_MEMORY_RESERVATION:-2G}
|
|
devices:
|
|
- driver: nvidia
|
|
device_ids: [ '0' ]
|
|
capabilities: [ gpu ]
|
|
|
|
services:
|
|
mineru-sglang-server:
|
|
<<: *mineru-sglang
|
|
profiles: ["sglang-server"]
|
|
ports:
|
|
- ${MINERU_PORT_OVERRIDE_SGLANG:-30000}:30000
|
|
entrypoint: mineru-sglang-server
|
|
command:
|
|
- --host 0.0.0.0
|
|
- --port 30000
|
|
|
|
# If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode.
|
|
# - --data-parallel-size 2
|
|
# If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter,
|
|
# if VRAM issues persist, try lowering it further to `0.4` or below.
|
|
# - --gpu-memory-utilization 0.5
|
|
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 60s
|
|
|
|
mineru-api:
|
|
<<: *mineru-sglang
|
|
profiles: ["api"]
|
|
ports:
|
|
- ${MINERU_PORT_OVERRIDE_API:-8000}:8000
|
|
entrypoint: mineru-api
|
|
command:
|
|
- --host 0.0.0.0
|
|
- --port 8000
|
|
|
|
# If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode.
|
|
# - --data-parallel-size 2
|
|
# If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter,
|
|
# if VRAM issues persist, try lowering it further to `0.4` or below.
|
|
# - --gpu-memory-utilization 0.5
|
|
healthcheck:
|
|
test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8000/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 60s
|
|
|
|
mineru-gradio:
|
|
<<: *mineru-sglang
|
|
profiles: ["gradio"]
|
|
ports:
|
|
- ${MINERU_PORT_OVERRIDE_GRADIO:-7860}:7860
|
|
entrypoint: mineru-gradio
|
|
command:
|
|
- --server-name 0.0.0.0
|
|
- --server-port 7860
|
|
|
|
# Enable the vllm engine for Gradio
|
|
- --enable-vllm-engine true
|
|
# If you want to disable the API, set this to false
|
|
# - --enable-api false
|
|
# If you want to limit the number of pages for conversion, set this to a specific number
|
|
# - --max-convert-pages 20
|
|
|
|
# If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode.
|
|
# - --data-parallel-size 2
|
|
# If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter,
|
|
# if VRAM issues persist, try lowering it further to `0.4` or below.
|
|
# - --gpu-memory-utilization 0.5
|
|
healthcheck:
|
|
test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:7860/"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 60s
|