Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

NIM on GKE Tutorial #737

Merged
merged 16 commits into from
Jul 29, 2024
Prev Previous commit
Next Next commit
cleanup pvc + explaination
  • Loading branch information
brandonroyal committed Jul 23, 2024
commit d081f4bd99b3d1cdd9e160535695f0c6a49231aa
8 changes: 4 additions & 4 deletions tutorials-and-examples/nvidia-nim/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -88,9 +88,7 @@ kubectl create namespace nim
```

## Deploy a PVC to persist the model
1. Clone this repository

2. Create a PVC to persist the model weights - recommended for deployments with more than one (1) replica. Save the following yaml as `pvc.yaml` or use existing file in this repository
1. Create a PVC to persist the model weights - recommended for deployments with more than one (1) replica. Save the following yaml as `pvc.yaml` or use existing file in this repository
```yaml
apiVersion: v1
kind: PersistentVolumeClaim
Expand All @@ -106,10 +104,12 @@ spec:
storageClassName: standard-rwx
```

3. Apply PVC
2. Apply PVC
```bash
kubectl apply -f pvc.yaml
```
> [!NOTE]
> This PVC will [dynamically provision a PV](https://cloud.google.com/kubernetes-engine/docs/concepts/persistent-volumes#dynamic_provisioning) with the necessary storage to persist model weights across replicas of your pods.

## Deploy the NIM with the generated engine using a Helm chart

Expand Down