Upgrading Layar

Introduction

This guide will go over how to upgrade Layar, the method you use will depend on if the server has access to the internet.

Internet Available

If you are using the Layar Amazon Machine Image (AMI) simply run:

/data/layar/deployLayar.sh upgrade

If you installed Layar manually, run:

helm repo update
kubectl delete deployment --all
kubectl delete statefulset --all
sleep 30

Now run the same helm command that was used during installation but replace the word install with upgrade. For example:

helm upgrade layar vyasa/layar --set APPURL=layar.acme.com --set TRITON_GPU_COUNT=3

Air Gaped

Pre-requisites

Before continuing you will need to have the .tar containing the updated version. If you do not have this, please reach out to support at [email protected].

Ensure the file is placed in a directory on the server that runs Layar.

Install

1. Login to the server as an Admin.
2. Navigate to the location of the .tar file.
3. Run tar xvf <name of file>
4. Once the files have extracted, cdto the newly created directory.
5. Run for i in 'ls vyasa*'; do echo "loading $i": lz4cat $i | docker load : done

🚧 If you are not changing the LLM during the upgrade skip to step 13

6. Run kubectl get pvc
7. Copy the name of the TGI PVC.
8. Run cd /data/vyasa-volumes/<TGI PVC Name>
9. Run Tar xvf <path of the models .tar file>
10. Run vi /data/layar/layar.config
11. Edit the TGI_Modelwith the name of the new model.
    1. Verify that model arguements do not need to be added to the config file. If you are unsure, review the Model Arguements
12. Save the changes.
13. Run kubectl delete deployments --all
14. Run kubectl delete statefulsets --all
15. cd back to the /data/layar
16. Run the helm command that was used to install Layar.