Immich – Full GPU Deployment Guide (Docker + NVIDIA)
Docker NVIDIA GPU TensorRT Production 2025
This guide walks you from a clean Ubuntu install to a fully GPU‑accelerated Immich deployment using Docker, NVIDIA Container Toolkit, Redis, and pgvector‑enabled Postgres. This is the exact architecture used on Johannes and validated on Signal Raider.
1. Install Docker
sudo apt update
sudo apt install -y ca-certificates curl gnupg
sudo install -m 0755 -d /etc/apt/keyrings
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | \
sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg
echo \
"deb [arch=$(dpkg --print-architecture) \
signed-by=/etc/apt/keyrings/docker.gpg] \
https://download.docker.com/linux/ubuntu \
$(lsb_release -cs) stable" | \
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
sudo apt update
sudo apt install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
2. Install NVIDIA GPU Drivers
sudo apt install -y nvidia-driver-535
sudo reboot
3. Install NVIDIA Container Toolkit
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | \
sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
curl -s -L https://nvidia.github.io/libnvidia-container/ubuntu$(lsb_release -rs)/libnvidia-container.list | \
sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt update
sudo apt install -y nvidia-container-toolkit
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker
4. Verify GPU passthrough
docker run --rm --gpus all nvidia/cuda:12.2.0-base nvidia-smi
5. Create Immich directory
mkdir -p /opt/immich
cd /opt/immich
6. Create .env
IMMICH_VERSION=release
DB_USERNAME=immich
DB_PASSWORD=immich
DB_DATABASE_NAME=immich
7. Create docker-compose.yml
services:
immich-server:
container_name: immich_server
image: ghcr.io/immich-app/immich-server:${IMMICH_VERSION:-release}
depends_on:
- redis
- database
env_file:
- .env
volumes:
- immich_upload:/usr/src/app/upload
restart: always
immich-machine-learning:
container_name: immich_machine_learning
image: ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}-cuda
env_file:
- .env
volumes:
- model-cache:/cache
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
restart: always
redis:
container_name: immich_redis
image: redis:7
restart: always
database:
container_name: immich_postgres
image: tensorchord/pgvecto-rs:pg14-v0.2.0
environment:
POSTGRES_USER: ${DB_USERNAME}
POSTGRES_PASSWORD: ${DB_PASSWORD}
POSTGRES_DB: ${DB_DATABASE_NAME}
volumes:
- pgdata:/var/lib/postgresql/data
restart: always
volumes:
immich_upload:
pgdata:
model-cache:
8. Start Immich
docker compose up -d
9. Access Immich
- Signal Raider / MSI: http://localhost:2283
- Johannes: via HAProxy backend
10. GPU verification inside Immich
Inside the Immich UI:- Settings → Machine Learning
- You should see CUDA available
- Indexing photos should spike GPU usage to 80–95%
Production Notes (Johannes)
- Remove
ports:from the server container - Let HAProxy handle TLS + routing
- Use bind mounts for long‑term storage
- Snapshot
pgdataregularly
কোন মন্তব্য পাওয়া যায়নি