[Feature]: Stop serving a model

[superm1]

Suggestion Description

After serving a model, the process keeps running when I exit rocm. I don't see any obvious way to stop the model serving service.

Operating System

No response

GPU

No response

ROCm Component

No response

[mikeroySoft]

It's currently done through the dash's Serving tab. There's a 'running instances' modal where you can (s)top one.

[superm1]

Ah, I didn't think to look there. Could you prompt when quiting too?

You left model xxx running, want to close it before quitting?