realizar 0.2.2

Pure Rust ML inference engine built from scratch - model serving for GGUF and safetensors
Documentation 
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

version: '3.8'

services:
  # CPU-only deployment
  realizar-cpu:
    build:
      context: .
      dockerfile: Dockerfile
    ports:
      - "3000:3000"
    environment:
      - RUST_LOG=info
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3000/health"]
      interval: 30s
      timeout: 3s
      retries: 3
      start_period: 5s
    restart: unless-stopped
    # Optional: mount models directory
    # volumes:
    #   - ./models:/app/models:ro

  # GPU-enabled deployment (requires nvidia-docker)
  realizar-gpu:
    build:
      context: .
      dockerfile: Dockerfile.gpu
    ports:
      - "3001:3000"
    environment:
      - RUST_LOG=info
      - CUDA_VISIBLE_DEVICES=0
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3000/health"]
      interval: 30s
      timeout: 3s
      retries: 3
      start_period: 5s
    restart: unless-stopped
    # Optional: mount models directory
    # volumes:
    #   - ./models:/app/models:ro

  # Prometheus for metrics collection (optional)
  prometheus:
    image: prom/prometheus:latest
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
    restart: unless-stopped
    profiles:
      - monitoring

  # Grafana for metrics visualization (optional)
  grafana:
    image: grafana/grafana:latest
    ports:
      - "3030:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin
    volumes:
      - grafana_data:/var/lib/grafana
    restart: unless-stopped
    profiles:
      - monitoring

volumes:
  prometheus_data:
  grafana_data: