Skip to content

Update Kubernetes version boundaries in deployment docs (#318) #332

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

Merged
ckadner merged 4 commits into from
May 25, 2022
Merged

Update Kubernetes version boundaries in deployment docs (#318) #332

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3fac14d
Signed-off-by: Kiran Patel 104844270+kiranp2396@users.noreply.github.com
May 20, 2022
db239f1
Update mlx-setup.md
ckadner May 25, 2022
431c582
Limit K8s version for KIND cluster
ckadner May 25, 2022
de08771
Update Troubleshooting section
ckadner May 25, 2022
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
8 changes: 4 additions & 4 deletions docs/install-mlx-on-kind.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,9 +40,9 @@ you could download the `kustomize` `v3.2.0` binary as described

Increase the default resources for Docker:

- CPUs: 8 Cores
- Memory: 16 GB RAM
- Disk: 32+ GB
- **CPUs**: 8 Cores
- **Memory**: 16 GB RAM
- **Disk**: 32+ GB

**Note**: We found that on older laptops, like a 2016 MacBook Pro (2.7 GHz i7, 16 GB RAM) the MLX
deployment on KIND may require to give all available resources to the Docker daemon in order to be
Expand All @@ -54,7 +54,7 @@ other application to crash.
## Create KIND Cluster

```Bash
kind create cluster --name mlx
kind create cluster --name mlx --image kindest/node:v1.21.12
kubectl cluster-info --context kind-mlx
kubectl get pods --all-namespaces
```
Expand Down
28 changes: 26 additions & 2 deletions docs/mlx-setup.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,13 @@
# Deploy MLX on an existing Kubernetes cluster

## Prerequisites
* An existing Kubernetes cluster. Version 1.17+
* The minimum recommended capacity requirement for MLX is 8 vCPUs and 16GB RAM
* An existing Kubernetes cluster:
- **Min version: 1.17**
- **Max version: 1.21**
* The recommended minimum capacity requirement for MLX are:
- **CPUs**: 8 Cores
- **Memory**: 16 GB RAM
- **Disk**: 32+ GB
* If you are using IBM Cloud, follow the appropriate instructions for standing up your Kubernetes cluster using the [IBM Cloud Kubernetes Service](https://cloud.ibm.com/docs/containers?topic=containers-cs_cluster_tutorial#cs_cluster_tutorial)
* If you are using OpenShift on IBM Cloud, please follow the instructions for standing up your [IBM Cloud Red Hat OpenShift cluster](https://cloud.ibm.com/docs/openshift?topic=openshift-openshift_tutorial)
* [`kustomize v3.2.0`](https://github.com/kubernetes-sigs/kustomize/releases/tag/v3.2.0) is installed
Expand Down Expand Up @@ -48,3 +53,22 @@ To delete this MLX deployment, run the following commands in the same manifests
```
kustomize build example | kubectl delete -f -
```

## Troubleshooting

- If you see errors like these during the deployment, it may be because of a unsupported Kubernetes version.
Check the [Prerequisites](#prerequisites) for the supported Kubernetes versions.

```
# while ! kustomize build example | kubectl apply -f -; do echo "Retrying to apply resources"; sleep 10; done
...
unable to recognize "STDIN": no matches for kind "CustomResourceDefinition" in version "apiextensions.k8s.io/v1beta1"
unable to recognize "STDIN": no matches for kind "RoleBinding" in version "rbac.authorization.k8s.io/v1beta1"
unable to recognize "STDIN": no matches for kind "ClusterRoleBinding" in version "rbac.authorization.k8s.io/v1beta1"
unable to recognize "STDIN": no matches for kind "EnvoyFilter" in version "networking.istio.io/v1alpha3"
...
```
To find your Kubernetes server version, run `kubectl version | grep Server`:
```
Server Version: version.Info{Major:"1", Minor:"21", GitVersion:"v1.21.12", ...
```