Problem with using mp.Queue with CUDA Tensors on AGX ORIN

[AastaLLL]

Hi,

This is not supported.

The feature is implemented with CUDA IPC which is not available on the Jetson platform.
For more details, please check the below topic:

Jetson AGX Orin CUDA IPC Support

Hello, Our team recently got its hands on AGX Orin, which is very powerful. To take full advantage of what Orin can offer, we decided to virtualize our workload into multiple docker containers, which communicate with each other via Unix Socket. And to keep performance, we found that we can share a reference to the CUDA allocated memory instead of transferring the entire array, which takes way too long. Most of our code base and logic are written in Pytorch, which has built-in support for IPC C…

Thanks.