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.

Sign up for GitHub

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

improve caching docs #295

Merged
merged 1 commit into from
Oct 29, 2024
Merged

improve caching docs #295

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion docs/how-to/cache-models-with-aws-efs.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,7 +118,7 @@ Make sure to set `file_system_id` match the EFS file system ID created in the fi

## 3. Configure KubeAI with the EFS cache profile

You can skip this step if you've already installed KubeAI using the [EKS Helm values file: values-eks.yaml](https://github.com/substratusai/kubeai/blob/main/charts/kubeai/values-eks.yaml) file.
You can skip this step if you've already installed KubeAI using the [EKS Helm values file: values-eks.yaml](https://github.com/substratusai/kubeai/blob/main/charts/kubeai/values-eks.yaml).

Configure KubeAI with the `efs-dynamic` cache profile.
```bash
Expand All @@ -133,6 +133,8 @@ cacheProfiles:
persistentVolumeName: "efs-pv"
EOF
```
You can also manually provision a PersistentVolume using EFS static mode.
The efs-static profile is used for this purpose.

## 4. Configure a model to use the EFS cache

Expand Down
19 changes: 19 additions & 0 deletions docs/how-to/cache-models-with-gcp-filestore.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,25 @@ Ensure that the Filestore API is enabled.
gcloud services enable file.googleapis.com
```

## 1. Configure KubeAI with Caching Profile

You can skip this step if you've already installed KubeAI using the [GKE Helm values file: values-gke.yaml](https://github.com/substratusai/kubeai/blob/main/charts/kubeai/values-gke.yaml).

Configure KubeAI with the Filestore cache profiles.
```bash
helm upgrade --install kubeai kubeai/kubeai \
--reuse-values -f - <<EOF
cacheProfiles:
standard-filestore:
sharedFilesystem:
storageClassName: "standard-rwx"
premium-filestore:
sharedFilesystem:
storageClassName: "premium-rwx"
EOF
```

## 2. Deploy a model that uses the Filestore Caching Profile
Apply a Model with the cache profile set to `standard-filestore` (defined in the reference [GKE Helm values file](https://github.com/substratusai/kubeai/blob/main/charts/kubeai/values-gke.yaml)).

<details markdown="1">
Expand Down
Loading