DALI model not able to run on a Triton Server on a GPU Node

AI & Data Science Deep Learning (Training & Inference) Maxine
,
1

Hello, Whenever I try to deploy my DALI model on a Triton Server which is running on a GPU kubernetes node, I am seeing an error trace as “Assert on “device != “gpu” || device_id_ != CPU_ONLY_DEVICE_ID” failed: Cannot add a GPU operator ExternalSource, device_id should not be equal CPU_ONLY_DEVICE_ID” which is coming from DALI end here

Is there anything I need to add from DALI model code my current DALI pipeline code has device=‘gpu’ and device_id=0 .

Any suggestions on this will be really helpful please