Add p5e (#516)

Signed-off-by: Sean Smith <[email protected]>

1.architectures/4.amazon-eks/README.md

@@ -171,7 +171,7 @@ kubectl get nodes
 5. Apply [K8 Nvidia CNI Plugin](https://github.com/NVIDIA/k8s-device-plugin):
 
 ```bash
-kubectl create -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v0.15.0/deployments/static/nvidia-device-plugin.yml
+kubectl create -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v0.17.0/deployments/static/nvidia-device-plugin.yml
 ```
 
 6. If using EFA, make sure to install the [EFA CNI Plugin](https://docs.aws.amazon.com/eks/latest/userguide/node-efa.html).

1.architectures/4.amazon-eks/amazon-eks-nodegroup.yaml

@@ -1,6 +1,6 @@
 AWSTemplateFormatVersion: "2010-09-09"
 
-Description: Amazon EKS - Create an unmanaged P4d/P5 node group for Capacity Blocks for ML.
+Description: Amazon EKS - Create an unmanaged P4d/P5/P5e node group for Capacity Blocks for ML.
 
 Metadata:
   "AWS::CloudFormation::Interface":
@@ -75,7 +75,7 @@ Parameters:
 
   NodeImageIdSSMParam:
     Type: "AWS::SSM::Parameter::Value<AWS::EC2::Image::Id>"
-    Default: /aws/service/eks/optimized-ami/1.29/amazon-linux-2-gpu/recommended/image_id
+    Default: /aws/service/eks/optimized-ami/1.31/amazon-linux-2-gpu/recommended/image_id
     Description: AWS Systems Manager Parameter Store parameter of the AMI ID for the worker node instances. Change this value to match the version of Kubernetes you are using.
 
   DisableIMDSv1:
@@ -89,6 +89,7 @@ Parameters:
     Type: String
     Default: p5.48xlarge
     AllowedValues:
+      - p5e.48xlarge
       - p5.48xlarge
       - p4d.24xlarge
     Description: EC2 instance type for the node instances
@@ -134,12 +135,16 @@ Conditions:
     - "Fn::Equals":
       - !Ref NodeImageId
       - ""
-  isP5: !Equals
-      - !Ref NodeInstanceType
-      - "p5.48xlarge"
   isP4d: !Equals
       - !Ref NodeInstanceType
       - "p4d.24xlarge"
+  isP5Family: !Or
+    - !Equals
+      - !Ref NodeInstanceType
+      - "p5.48xlarge"
+    - !Equals
+      - !Ref NodeInstanceType
+      - "p5e.48xlarge"
 
   IMDSv1Disabled:
     "Fn::Equals":
@@ -280,7 +285,7 @@ Resources:
 
   NodeLaunchTemplateP5:
     Type: "AWS::EC2::LaunchTemplate"
-    Condition: isP5
+    Condition: isP5Family
     Properties:
       LaunchTemplateData:
         InstanceMarketOptions:
@@ -659,11 +664,11 @@ Resources:
       DesiredCapacity: !Ref NodeAutoScalingGroupDesiredCapacity
       LaunchTemplate:
         LaunchTemplateId: !If
-          - isP5
+          - isP5Family
           - !Ref NodeLaunchTemplateP5
           - !Ref NodeLaunchTemplateP4
         Version: !If
-          - isP5
+          - isP5Family
           - !GetAtt NodeLaunchTemplateP5.LatestVersionNumber
           - !GetAtt NodeLaunchTemplateP4.LatestVersionNumber
       MaxSize: !Ref NodeAutoScalingGroupMaxSize