Ryan McCormick

@Tabrizian is this still needed or can it be merged?

CC @fpetrini15 just FYI

Hi @w169q169, thanks for the contribution? Have you filled out a [CLA](https://github.com/triton-inference-server/server/blob/main/CONTRIBUTING.md#contributor-license-agreement-cla)? @nv-kmcgill53 @mc-nv could you sanity check it's OK to follow redirects here when you get a chance?

Looks like this is also a duplicate of #5935

@GuanLuo do we still plan to implement this to help unify decoupled/non-decoupled logic in backends like RIVA/TRTLLM etc?

Seems reasonable to me. CC @nealvaidya for comments

> I have also emailed my signed CLA. Hi @okyspace, can you either resend this email or clarify the name and company attached to it?

Thanks for your contribution and patience @okyspace !

Seems fine to me. @szalpal are you able to run a pipeline to confirm this builds and runs OK?

What's the state of this PR @Tabrizian ? Do we intend to finalize it at some point? I think a new backend API like this could enable a cleaner way...