Ubuntu 20 Helm Chart

Prerequisites

Hardware

256 GB RAM
32 CPUs
1TB SSD disk
2x A100 or later generation GPUs (A100 strongly preferred)

Additional Requirements

The system must have an external DNS entry (not relying on /etc/hosts) with the corresponding IP assigned to the host
Internet access from the installation system is a requirement.
Swap must be disabled.
SELinux must be disabled or set to Permissive.

LLM Considerations

Certara AI allows you to utilize various LLMs for your GPT needs. The models available are determined by the version of Layar you are planning to install. Please review the available models and the minimum GPU requirements needs to run those models

Installation

Commands should be run as root or prefixed with sudo.

Ensure you have current Docker installed

dpkg -l docker-ce
docker version

The installed docker should be from the official Docker repository, not from the Ubuntu repositories. If the first command above fails but the second works then you are running the Ubuntu-provided version which is incorrect. In that case, please follow the instructions for installing docker on Ubuntu here before proceeding. Both Client and Server output should show version 24.0.5 or later.

Increase operating system `vm.max_map_count`

echo "vm.max_map_count=262144" > /etc/sysctl.d/99-vyasa.conf 

sysctl -p /etc/sysctl.d/99-vyasa.conf

Configure NetworkManager to ignore Calico interfaces

If using NetworkManager, edit the file /etc/NetworkManager/conf.d/calico.conf and set the following:

[keyfile]
unmanaged-devices=interface-name:cali*;interface-name:tunl*;interface-name:vxlan.calico;interface-name:wireguard.cali

Restart NetworkManager

systemctl restart NetworkManager

Install CUDA 12

Install CUDA per the instructions at NVIDIA. Ensure DKMS is also installed. Version 12.0 or later is required.
https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html

Install NVIDIA Docker toolkit

distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \   
    && curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add - \   
    && curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list
apt update

apt-get install -y nvidia-docker2

Set docker default runtime

Edit the file /etc/docker/daemon.json and replace its contents with:

{
"default-runtime": "nvidia",
 "runtimes": {
        "nvidia": {
            "path": "/usr/bin/nvidia-container-runtime",
            "runtimeArgs": []
        }
    }
}

Restart Docker

systemctl restart docker

Install Kubernetes

curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key 
add -

echo "deb http://apt.kubernetes.io/ kubernetes-xenial main" >> /etc/apt/sources.list  && apt update

apt install -y kubeadm=1.23.15-00 kubelet=1.23.15-00 kubectl=1.23.15-00

/usr/bin/kubeadm init --kubernetes-version=1.23.15 --token-ttl 0 --pod-network-cidr=10.17.0.0/16 -v 5

mkdir -p $HOME/.kube

sudo cp -i /etc/kubernetes/admin.conf $HOME/.kube/config

sudo chown $(id -u):$(id -g) $HOME/.kube/config

Install NGINX Ingress controller

kubectl apply -f https://vyasa-static-assets.s3.amazonaws.com/layar/nginx-ingress.yaml

Install Calico CNI

kubectl create -f https://vyasa-static-assets.s3.amazonaws.com/layar/tigera-operator.yaml

kubectl create -f https://vyasa-static-assets.s3.amazonaws.com/layar/custom-resources.yaml

Let head node run pods

kubectl taint nodes --all node-role.kubernetes.io/master:NoSchedule-

Install local volume provisioner

/usr/bin/kubectl apply -f https://vyasa-static-assets.s3.amazonaws.com/layar/local-storage-provisioner.yml

Set default storage class

kubectl patch storageclass 'local-path' -p '{"metadata":{"annotations":{"storageclass.kubernetes.io/is-default-class":"true"}}}'

Install Helm

wget -P /usr/local/bin/ https://vyasa-static-assets.s3.amazonaws.com/helm/helm

chmod +x /usr/local/bin/helm

Add the Layar helm repository

helm repo add vyasa https://helm.vyasa.com/charts/ --username 
vyasahelm --password "sail#away()"

helm repo update

Install Layar

Replace MY_URL with the IP address or DNS name of the system. Set MY_GPU_COUNT to the number of GPUs available to Layar.

helm install layar vyasa/layar --set APPURL=MY_URL --set TRITON_GPU_COUNT=MY_GPU_COUNT

Uninstall Layar

To uninstall the Layar helm chart, execute the following command:

helm uninstall layar