Add instance type support for ml.p6e-gb200.36xlarge (#204)

* Add instance type support for ml.p6e-gb200.36xlarge

Updated support for ml.p6-b200.48xlarge as well

* Add ml.p6e-gb200.36xlarge to efa plugin

Author: zhaoqizqwang

helm_chart/HyperPodHelmChart/charts/health-monitoring-agent/templates/health-monitoring-agent.yaml

@@ -111,6 +111,7 @@ spec:
                       - ml.g6e.48xlarge
                       - ml.trn2.48xlarge
                       - ml.p6-b200.48xlarge
+                      - ml.p6e-gb200.36xlarge
       containers:
         - name: health-monitoring-agent
           args:

helm_chart/HyperPodHelmChart/values.yaml

@@ -180,6 +180,8 @@ nvidia-device-plugin:
               - ml.p5.48xlarge
               - ml.p5e.48xlarge
               - ml.p5en.48xlarge
+              - ml.p6-b200.48xlarge
+              - ml.p6e-gb200.36xlarge
   tolerations:
     - key: nvidia.com/gpu
       operator: Exists
@@ -197,6 +199,7 @@ aws-efa-k8s-device-plugin:
   devicePlugin:
     enabled: true
   supportedInstanceLabels:
+    # https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/efa.html#efa-instance-types
     values:
       - ml.c5n.9xlarge
       - ml.c5n.18xlarge
@@ -237,6 +240,8 @@ aws-efa-k8s-device-plugin:
       - ml.p5.48xlarge
       - ml.p5e.48xlarge
       - ml.p5en.48xlarge
+      - ml.p6-b200.48xlarge
+      - ml.p6e-gb200.36xlarge
       - ml.r7i.large
       - ml.r7i.xlarge
       - ml.r7i.2xlarge