Requirements for Sherpa AI Server#

# Check system resources
df -h          # Disk space
free -h        # RAM
nvidia-smi     # GPU (if installed)

# Update the system and install tools
sudo apt update
sudo apt install -y ca-certificates curl tar

# Add the official Docker GPG key
sudo install -m 0755 -d /etc/apt/keyrings
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
sudo chmod a+r /etc/apt/keyrings/docker.asc

# Add the Docker repository
echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
  $(. /etc/os-release && echo "${UBUNTU_CODENAME:-$VERSION_CODENAME}") stable" | \
  sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

# Install Docker
sudo apt update
sudo apt install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin

# Add user to the docker group (optional)
sudo usermod -aG docker $USER

# Check installation
docker --version
docker compose version

# Remove old drivers and install new ones
sudo apt purge 'nvidia-*'
sudo apt autoremove
sudo apt install -y nvidia-driver-580

# Reboot the server
sudo reboot

# After reboot, check GPU
nvidia-smi

# Add the repository and install the toolkit
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | \
  sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit.gpg

curl -fsSL https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
  sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit.gpg] https://#g' | \
  sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list

sudo apt update
sudo apt install -y nvidia-container-toolkit

# Configure Docker for GPU
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

# Create a directory for packages
mkdir -p nvidia-offline-packages/drivers
cd nvidia-offline-packages/drivers

# Download the driver via apt download (if the repository is available)
# First, add the NVIDIA repository (if not already added)
sudo add-apt-repository ppa:graphics-drivers/ppa
sudo apt update

# Download the driver package
apt download nvidia-driver-580

# Download driver dependencies (execute the command line by line)
# First, find out the list of dependencies:
apt-cache depends nvidia-driver-580 | grep "Depends:" | cut -d: -f2 | tr -d ' ' > /tmp/deps.txt

# Then download each dependency:
while read dep; do
	apt download "$dep" 2>/dev/null || echo "Skipped dependency: $dep"
done < /tmp/deps.txt

# Remove the temporary file
rm /tmp/deps.txt

# Go back to the packages directory
cd nvidia-offline-packages

# Create a directory for the Container Toolkit
mkdir -p toolkit

# Add the NVIDIA Container Toolkit repository (if not already added)
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | \
  sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit.gpg

curl -fsSL https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
  sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit.gpg] https://#g' | \
  sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list

sudo apt update

# Download the Container Toolkit package and all its dependencies
cd toolkit
apt download nvidia-container-toolkit

# Download Container Toolkit dependencies (execute the command line by line)
# First, find out the list of dependencies:
apt-cache depends nvidia-container-toolkit | grep "Depends:" | cut -d: -f2 | tr -d ' ' > /tmp/toolkit-deps.txt

# Then download each dependency:
while read dep; do
  apt download "$dep" 2>/dev/null || echo "Skipped dependency: $dep"
done < /tmp/toolkit-deps.txt

# Remove the temporary file
rm /tmp/toolkit-deps.txt

# Optionally: Download the GPG key and repository file (only needed if you plan to use apt install instead of dpkg)
# For offline installation via dpkg -i, GPG keys ARE NOT REQUIRED
cd ..
mkdir -p keys
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey -o keys/nvidia-container-toolkit.gpg
curl -fsSL https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list -o keys/nvidia-container-toolkit.list

# Go back to the root directory of the packages
cd nvidia-offline-packages

# Ensure all files are in place:
# - drivers/ - contains .deb packages or .run driver file
# - toolkit/ - contains .deb packages of the Container Toolkit
# - keys/ - contains GPG keys and repository files (optionally, if available)

# Create an archive with all packages
# If the keys/ directory is empty or missing, you can create the archive without it:
if [ -d "keys" ] && [ "$(ls -A keys)" ]; then
    tar -czf nvidia-packages-offline.tar.gz drivers/ toolkit/ keys/
else
    tar -czf nvidia-packages-offline.tar.gz drivers/ toolkit/
    echo "Warning: GPG keys are not included in the archive (not required for installation via dpkg)"
fi

# Check the size of the archive
ls -lh nvidia-packages-offline.tar.gz

# Extract the archive
tar -xzf nvidia-packages-offline.tar.gz
cd nvidia-offline-packages

# Check for .deb files in the drivers directory
ls -la drivers/*.deb

# Install NVIDIA drivers
cd drivers
sudo dpkg -i *.deb

# Check the installation result
if [ $? -eq 0 ]; then
    echo "Drivers installed successfully"
else
    echo "Dependency errors detected, fixing..."
    # If there are dependency errors, install them from the cache or fix dependencies
    sudo apt install --fix-broken -y
    
    # If fix-broken did not help, try installing dependencies manually
    # Ensure that all dependencies were downloaded to the drivers directory
    echo "Check that all dependencies are downloaded to the drivers/ directory"
    ls -la *.deb
fi

# Reboot the server to apply the drivers
echo "Rebooting the server in 10 seconds... Press Ctrl+C to cancel"
sleep 10
sudo reboot

# Extract the archive (if the .run file was added to the archive)
tar -xzf nvidia-packages-offline.tar.gz
cd nvidia-offline-packages/drivers

# Find the .run driver file (e.g., NVIDIA-Linux-x86_64-580.XX.XX.run)
ls -la *.run

# Make the file executable
chmod +x NVIDIA-Linux-x86_64-*.run

# Determine which graphical server is used (execute one of the commands):
# Check for GNOME/GDM3:
systemctl status gdm3 > /dev/null 2>&1 && echo "Using gdm3"
# Check for LightDM:
systemctl status lightdm > /dev/null 2>&1 && echo "Using lightdm"
# Check for SDDM (KDE):
systemctl status sddm > /dev/null 2>&1 && echo "Using sddm"

# Stop the graphical server (execute ONLY one command corresponding to your display manager):
# For Ubuntu with GNOME:
sudo systemctl stop gdm3
# OR for Ubuntu with LightDM:
# sudo systemctl stop lightdm
# OR for systems with KDE:
# sudo systemctl stop sddm
# OR if there is no graphical interface, skip this step

# Install the driver (use flags for automatic installation)
sudo ./NVIDIA-Linux-x86_64-*.run \
  --silent \
  --no-nouveau-check \
  --no-opengl-files \
  --disable-nouveau

# Check the installation result (should be a success message)
echo $?

# If the graphical server was stopped, start it back up (use the same command as for stopping):
sudo systemctl start gdm3  # or lightdm/sddm depending on your system

# Reboot the server to apply the drivers
sudo reboot

# Check GPU (this command should show information about the graphics card)
nvidia-smi

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 580.XX       Driver Version: 580.XX       CUDA Version: 12.X  |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  NVIDIA GeForce ...  Off  | 00000000:01:00.0 Off |                  N/A |
| ...                                                                         |
+-----------------------------------------------------------------------------+

# Go back to the packages directory (replace with the actual path where you extracted the archive)
# For example, if the archive was extracted in the home directory:
cd ~/nvidia-offline-packages
# Or if in another location, specify the full path:
# cd /full/path/to/nvidia-offline-packages

# Check that all files are in place
ls -la toolkit/*.deb

# Optionally: Install the GPG key (NOT required for installation via dpkg)
# GPG keys are only needed if:
# 1. You plan to use apt install instead of dpkg -i
# 2. You want to set up the repository for future updates (when internet is available)
# For simple offline installation via dpkg -i, you can skip this step
if [ -f "keys/nvidia-container-toolkit.gpg" ]; then
    echo "Installing GPG key (optional)..."
    sudo mkdir -p /usr/share/keyrings
    sudo cp keys/nvidia-container-toolkit.gpg /tmp/nvidia-container-toolkit.gpg
    sudo gpg --dearmor /tmp/nvidia-container-toolkit.gpg -o /usr/share/keyrings/nvidia-container-toolkit.gpg
    sudo rm /tmp/nvidia-container-toolkit.gpg
    echo "GPG key installed"
else
    echo "GPG key not found - skipping installation (not critical for dpkg -i)"
fi

# Install the Container Toolkit from local packages
cd toolkit
sudo dpkg -i *.deb

# Check the installation result
if [ $? -eq 0 ]; then
    echo "Container Toolkit installed successfully"
else
    echo "Dependency errors detected, fixing..."
    # Fix dependencies if necessary
    sudo apt install --fix-broken -y
    
    # If fix-broken did not help, check that all dependencies are downloaded
    echo "Check for all dependencies in the toolkit/ directory"
    ls -la *.deb
fi

# Configure Docker for GPU
sudo nvidia-ctk runtime configure --runtime=docker

# Restart Docker to apply changes
sudo systemctl restart docker

# Check that Docker is running
sudo systemctl status docker

# Check GPU installation in Docker
nvidia-smi