diff --git a/Deployment/Kubernetes/TensorRT-LLM_Autoscaling_and_Load_Balancing/chart/templates/deployment.yaml b/Deployment/Kubernetes/TensorRT-LLM_Autoscaling_and_Load_Balancing/chart/templates/deployment.yaml index 61062609..e5d87023 100644 --- a/Deployment/Kubernetes/TensorRT-LLM_Autoscaling_and_Load_Balancing/chart/templates/deployment.yaml +++ b/Deployment/Kubernetes/TensorRT-LLM_Autoscaling_and_Load_Balancing/chart/templates/deployment.yaml @@ -257,7 +257,7 @@ spec: - mountPath: /var/run/models name: model-repository - mountPath: /dev/shm - name: dshm + name: dshm - mountPath: /var/run/engines name: engine-repository readOnly: false @@ -283,7 +283,7 @@ spec: - name: engine-repository hostPath: path: {{ printf "%s/models/%s/%dx%d/engines" $hostRootPath $model_lower (int $model_pp) (int $model_tp) }} - type: DirectoryOrCreate + type: DirectoryOrCreate - name: model-repository persistentVolumeClaim: claimName: efs-claim-autoscaling-2