Back to articles
AI & Cloud

Guide to Deploy Immich with Hardware Acceleration on VPS GPU for Optimized Face Recognition

Detailed guide to deploy Immich on a VPS GPU with hardware acceleration for optimized face recognition, covering configuration, installation, performance tuning, and verification.

DPTCloud Engineering4 min read
Guide to Deploy Immich with Hardware Acceleration on VPS GPU for Optimized Face Recognition

Image credit: geralt · Pixabay Content License

Introduction to Immich and Benefits of Hardware Acceleration

Immich is a self-hosted image storage and management application, similar to Google Photos, with AI-powered features like face recognition, content-based image search, and automatic categorization. When deployed on a VPS with GPU support, hardware acceleration significantly speeds up AI tasks such as face detection, image analysis, and data processing. By leveraging the GPU for compute-intensive workloads instead of relying solely on the CPU, Immich delivers faster processing, lower latency, and improved overall system efficiency. This is especially valuable for face recognition, where real-time or near-real-time performance is key.

System Requirements and Preparations

System Requirements

  • VPS with GPU support for CUDA (e.g., NVIDIA T4, A10G, or compatible GPUs)
  • Minimum 16GB RAM
  • SSD storage with at least 100GB free space
  • Operating System: Ubuntu 22.04 LTS or Debian 12
  • Docker and Docker Compose installed

Preparation Steps

Before deployment, ensure the following:

  • Access the VPS via SSH
  • Verify the GPU is detected by the system
  • Install NVIDIA drivers and CUDA Toolkit (compatible with Docker)

Deploying Immich with Hardware Acceleration on VPS GPU

Install NVIDIA Container Toolkit

To enable GPU access for Docker containers, install the NVIDIA Container Toolkit:

# Add NVIDIA repository
curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
curl -s -L https://nvidia.github.io/nvidia-docker/ubuntu22.04/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list

# Update and install
sudo apt update
sudo apt install -y nvidia-container-toolkit

# Restart Docker
sudo systemctl restart docker

Configure docker-compose.yml

Create a docker-compose.yml file with the following configuration:

version: '3.8'

services:
  immich-server:
    image: immich/immich-server:latest
    container_name: immich-server
    restart: unless-stopped
    ports:
      - "2283:2283"
    environment:
      - NODE_ENV=production
      - IMMICH_SERVER_PORT=2283
      - IMMICH_SERVER_HOST=0.0.0.0
      - IMMICH_DB_HOST=immich-db
      - IMMICH_DB_PORT=5432
      - IMMICH_DB_USER=immich
      - IMMICH_DB_PASSWORD=immichpassword
      - IMMICH_DB_NAME=immich
      - IMMICH_STORAGE_TYPE=local
      - IMMICH_STORAGE_LOCAL_PATH=/immich/data
    volumes:
      - ./data:/immich/data
    devices:
      - /dev/dri:/dev/dri
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]

  immich-worker:
    image: immich/immich-worker:latest
    container_name: immich-worker
    restart: unless-stopped
    environment:
      - NODE_ENV=production
      - IMMICH_SERVER_URL=http://immich-server:2283
      - IMMICH_DB_HOST=immich-db
      - IMMICH_DB_PORT=5432
      - IMMICH_DB_USER=immich
      - IMMICH_DB_PASSWORD=immichpassword
      - IMMICH_DB_NAME=immich
    depends_on:
      - immich-server
    volumes:
      - ./data:/immich/data
    devices:
      - /dev/dri:/dev/dri
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]

  immich-db:
    image: postgres:15
    container_name: immich-db
    restart: unless-stopped
    environment:
      POSTGRES_DB: immich
      POSTGRES_USER: immich
      POSTGRES_PASSWORD: immichpassword
    volumes:
      - ./db-data:/var/lib/postgresql/data
    ports:
      - "5432:5432"

Start Immich

Run the following command to launch the services:

docker-compose up -d

Performance Optimization and Activity Verification

Verify GPU Usage

Ensure the GPU is being utilized by Immich:

# Check GPU status
nvidia-smi

# Check container status
docker ps

# View Immich server logs
docker logs immich-server

Optimize Performance

  • Ensure containers are allocated sufficient GPU resources
  • Offload CPU-intensive AI tasks to the GPU
  • Adjust image processing schedules based on usage patterns
  • Monitor performance using nvidia-smi or docker stats

Troubleshooting Common Issues

  • GPU not detected: Verify NVIDIA drivers and CUDA Toolkit are correctly installed and compatible.
  • Immich fails to start: Check container logs and ensure the database is running.
  • Low performance: Review GPU, RAM, and CPU allocation; ensure no other containers are consuming excessive resources.

References

DPTCloud Tier III Infrastructure

High-RAM Cloud VPS Plans Optimized for AI, Databases & Cache

Enterprise RAID 10 NVMe SSDs, CMC & FPT District 9 uplinks with Anycast Anti-DDoS and 99.99% SLA.

View 22 VPS Plans
ECO · vn-02Recommended

VPS-4E

297.000 ₫ / mo

10% VAT included

  • CPU: 4 vCPU
  • RAM: 8 GB
  • SSD: 50 GB NVMe
ECO · vn-02

VPS-5E

614.900 ₫ / mo

10% VAT included

  • CPU: 8 vCPU
  • RAM: 16 GB
  • SSD: 100 GB NVMe
ADVANCED · vn-03Recommended

VPS-4T

548.900 ₫ / mo

10% VAT included

  • CPU: 4 vCPU
  • RAM: 8 GB
  • SSD: 50 GB NVMe

Related Articles

View all
ZaloZalo SupportDiscord0384 753 478