NVIDIA AI Enterprise 2.0 or later
Scaling of GPU worker nodes can be done via combining the use of the OpenShift Console and VMware vCenter. In this example we will have deployed a cluster via the IPI method and already attached a virtual GPU to our OpenShift worker VMs.
![openshift-appendix1.png](https://docscontent.nvidia.com/dims4/default/0987157/2147483647/strip/true/crop/1156x552+0+0/resize/1156x552!/quality/90/?url=https%3A%2F%2Fk3-prod-nvidia-docs.s3.us-west-2.amazonaws.com%2Fbrightspot%2Fsphinx%2F0000018e-a48d-d6f5-a5bf-b69d44f90000%2Fai-enterprise%2Fdeployment-guide-openshift-vmware%2F0.1.0%2F_images%2Fopenshift-appendix1.png)
To scale navigate to Compute and MachineSets.
Select the MachineSet for your GPU Accelerated cluster
![openshift-appendix2.png](https://docscontent.nvidia.com/dims4/default/915fb5d/2147483647/strip/true/crop/1460x778+0+0/resize/1440x767!/quality/90/?url=https%3A%2F%2Fk3-prod-nvidia-docs.s3.us-west-2.amazonaws.com%2Fbrightspot%2Fsphinx%2F0000018e-a48d-d6f5-a5bf-b69d44f90000%2Fai-enterprise%2Fdeployment-guide-openshift-vmware%2F0.1.0%2F_images%2Fopenshift-appendix2.png)
Select the number of machines under Desired Count
![openshift-appendix3.png](https://docscontent.nvidia.com/dims4/default/7e584a9/2147483647/strip/true/crop/1095x782+0+0/resize/1095x782!/quality/90/?url=https%3A%2F%2Fk3-prod-nvidia-docs.s3.us-west-2.amazonaws.com%2Fbrightspot%2Fsphinx%2F0000018e-a48d-d6f5-a5bf-b69d44f90000%2Fai-enterprise%2Fdeployment-guide-openshift-vmware%2F0.1.0%2F_images%2Fopenshift-appendix3.png)
Increase the number of machines for your cluster
![openshift-appendix4.png](https://docscontent.nvidia.com/dims4/default/ae18c61/2147483647/strip/true/crop/535x241+0+0/resize/535x241!/quality/90/?url=https%3A%2F%2Fk3-prod-nvidia-docs.s3.us-west-2.amazonaws.com%2Fbrightspot%2Fsphinx%2F0000018e-a48d-d6f5-a5bf-b69d44f90000%2Fai-enterprise%2Fdeployment-guide-openshift-vmware%2F0.1.0%2F_images%2Fopenshift-appendix4.png)
Wait until the Desired, Current, Ready, and Available, counts are all equal
![openshift-appendix5.png](https://docscontent.nvidia.com/dims4/default/46257fd/2147483647/strip/true/crop/1093x777+0+0/resize/1093x777!/quality/90/?url=https%3A%2F%2Fk3-prod-nvidia-docs.s3.us-west-2.amazonaws.com%2Fbrightspot%2Fsphinx%2F0000018e-a48d-d6f5-a5bf-b69d44f90000%2Fai-enterprise%2Fdeployment-guide-openshift-vmware%2F0.1.0%2F_images%2Fopenshift-appendix5.png)
Navigate to VMware vCenter and select the newly created worker VM in you inventory.
For each new worker VM perform the follow steps:
Power down the VM and edit the settings
![openshift-appendix6.png](https://docscontent.nvidia.com/dims4/default/647218c/2147483647/strip/true/crop/1150x541+0+0/resize/1150x541!/quality/90/?url=https%3A%2F%2Fk3-prod-nvidia-docs.s3.us-west-2.amazonaws.com%2Fbrightspot%2Fsphinx%2F0000018e-a48d-d6f5-a5bf-b69d44f90000%2Fai-enterprise%2Fdeployment-guide-openshift-vmware%2F0.1.0%2F_images%2Fopenshift-appendix6.png)
Add a new device and click PCI Device
![openshift-appendix7.png](https://docscontent.nvidia.com/dims4/default/f20c041/2147483647/strip/true/crop/847x725+0+0/resize/847x725!/quality/90/?url=https%3A%2F%2Fk3-prod-nvidia-docs.s3.us-west-2.amazonaws.com%2Fbrightspot%2Fsphinx%2F0000018e-a48d-d6f5-a5bf-b69d44f90000%2Fai-enterprise%2Fdeployment-guide-openshift-vmware%2F0.1.0%2F_images%2Fopenshift-appendix7.png)
Attach the appropriate vGPU profile or pass-through GPU
![openshift-appendix8.png](https://docscontent.nvidia.com/dims4/default/bd91125/2147483647/strip/true/crop/846x728+0+0/resize/846x728!/quality/90/?url=https%3A%2F%2Fk3-prod-nvidia-docs.s3.us-west-2.amazonaws.com%2Fbrightspot%2Fsphinx%2F0000018e-a48d-d6f5-a5bf-b69d44f90000%2Fai-enterprise%2Fdeployment-guide-openshift-vmware%2F0.1.0%2F_images%2Fopenshift-appendix8.png)
Power on the VM.