Merge pull request #10 from OguzPastirmaci/main

Update NCCL manifests

Author: OguzPastirmaci

manifests/a100-nccl-test.yaml

@@ -43,6 +43,9 @@ spec:
               name: wait-for-workers
           serviceAccount: mpi-worker-view
           terminationGracePeriodSeconds: 2
+          tolerations:
+            - key: nvidia.com/gpu
+              operator: Exists          
           containers:
             - command:
                 - /bin/bash

manifests/h100-nccl-test.yaml

@@ -43,6 +43,9 @@ spec:
               name: wait-for-workers
           serviceAccount: mpi-worker-view
           terminationGracePeriodSeconds: 2
+          tolerations:
+            - key: nvidia.com/gpu
+              operator: Exists
           containers:
             - command:
                 - /bin/bash