File size: 3,438 Bytes
ed61a86 |
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 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 |
version: '3.8'
services:
helion-inference:
build:
context: .
dockerfile: Dockerfile
args:
- CUDA_VERSION=12.1.1
image: helion:2.5-rnd
container_name: helion-inference-server
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
environment:
- MODEL_PATH=/models/helion
- MODEL_NAME=DeepXR/Helion-2.5-Rnd
- PORT=8000
- HOST=0.0.0.0
- TENSOR_PARALLEL_SIZE=2
- MAX_MODEL_LEN=131072
- GPU_MEMORY_UTILIZATION=0.95
- CUDA_VISIBLE_DEVICES=0,1
- WORKERS=1
# Optional: HuggingFace token for private models
# - HF_TOKEN=your_token_here
# Logging
- LOG_LEVEL=info
- LOG_FILE=/app/logs/helion.log
volumes:
- ./models:/models:ro
- ./logs:/app/logs
- ./cache:/app/cache
- ./inference:/app/inference:ro
- ./model_config.yaml:/app/model_config.yaml:ro
ports:
- "8000:8000"
- "8001:8001" # Metrics
- "8002:8002" # Admin
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
interval: 30s
timeout: 10s
retries: 3
start_period: 120s
restart: unless-stopped
networks:
- helion-network
logging:
driver: "json-file"
options:
max-size: "100m"
max-file: "10"
prometheus:
image: prom/prometheus:latest
container_name: helion-prometheus
volumes:
- ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
- prometheus-data:/prometheus
ports:
- "9090:9090"
command:
- '--config.file=/etc/prometheus/prometheus.yml'
- '--storage.tsdb.path=/prometheus'
- '--web.console.libraries=/usr/share/prometheus/console_libraries'
- '--web.console.templates=/usr/share/prometheus/consoles'
networks:
- helion-network
restart: unless-stopped
grafana:
image: grafana/grafana:latest
container_name: helion-grafana
environment:
- GF_SECURITY_ADMIN_PASSWORD=admin
- GF_USERS_ALLOW_SIGN_UP=false
volumes:
- grafana-data:/var/lib/grafana
- ./monitoring/grafana/dashboards:/etc/grafana/provisioning/dashboards:ro
- ./monitoring/grafana/datasources:/etc/grafana/provisioning/datasources:ro
ports:
- "3000:3000"
networks:
- helion-network
depends_on:
- prometheus
restart: unless-stopped
nginx:
image: nginx:alpine
container_name: helion-nginx
volumes:
- ./nginx/nginx.conf:/etc/nginx/nginx.conf:ro
- ./nginx/ssl:/etc/nginx/ssl:ro
ports:
- "80:80"
- "443:443"
networks:
- helion-network
depends_on:
- helion-inference
restart: unless-stopped
redis:
image: redis:7-alpine
container_name: helion-redis
command: redis-server --appendonly yes
volumes:
- redis-data:/data
ports:
- "6379:6379"
networks:
- helion-network
restart: unless-stopped
networks:
helion-network:
driver: bridge
ipam:
config:
- subnet: 172.28.0.0/16
volumes:
prometheus-data:
driver: local
grafana-data:
driver: local
redis-data:
driver: local |