compose.yaml
2.94 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
services:
mineru-vllm-server:
image: mineru-vllm:latest
container_name: mineru-vllm-server
restart: always
profiles: ["vllm-server"]
ports:
- 30000:30000
environment:
MINERU_MODEL_SOURCE: local
entrypoint: mineru-vllm-server
command:
--host 0.0.0.0
--port 30000
# --data-parallel-size 2 # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode
# --gpu-memory-utilization 0.5 # 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.
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]
mineru-api:
image: mineru-vllm:latest
container_name: mineru-api
restart: always
profiles: ["api"]
ports:
- 8000:8000
environment:
MINERU_MODEL_SOURCE: local
entrypoint: mineru-api
command:
--host 0.0.0.0
--port 8000
# parameters for vllm-engine
# --data-parallel-size 2 # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode
# --gpu-memory-utilization 0.5 # 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.
ulimits:
memlock: -1
stack: 67108864
ipc: host
deploy:
resources:
reservations:
devices:
- driver: nvidia
device_ids: [ "0" ]
capabilities: [ gpu ]
mineru-gradio:
image: mineru-vllm:latest
container_name: mineru-gradio
restart: always
profiles: ["gradio"]
ports:
- 7860:7860
environment:
MINERU_MODEL_SOURCE: local
entrypoint: mineru-gradio
command:
--server-name 0.0.0.0
--server-port 7860
--enable-vllm-engine true # Enable the vllm engine for Gradio
# --enable-api false # If you want to disable the API, set this to false
# --max-convert-pages 20 # If you want to limit the number of pages for conversion, set this to a specific number
# parameters for vllm-engine
# --data-parallel-size 2 # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode
# --gpu-memory-utilization 0.5 # 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.
ulimits:
memlock: -1
stack: 67108864
ipc: host
deploy:
resources:
reservations:
devices:
- driver: nvidia
device_ids: [ "0" ]
capabilities: [ gpu ]