torchServce async handling

Hey there,

I’m trying to deploy a torchServe microservice that would handle asynchronously some embedding working then give result back to my api.

I can’t find if there is already an intern queue in torchServe and if I can query it 500 times and let it handle it, or if I have to build my own queue on front of it and have another service give work to it ?

Thank you for your help, I’m quite stuck on this!