Not able to run Multiple replicas of GPU based application through DOCKER SWARM

HI All,
i configured 2 node DOCKER SWARM cluster(one manger/one worker) where i want to deploy the GPU based Docker application.
it is working fine for 2 No. of replicas but when i am trying to scale more than 2 it show me the following Errors:

no suitable node (insufficient resources on 2 node)

is there any to resolve this

Hi @mukesh.sharma
Please note this forum branch is dedicated to CUDA GDB support. You question might be more suitable for different forums: