> As of very recently, you can also force EC2 instances to stop or terminate without waiting for a clean shutdown or a ridiculous timeout

Not true for GPU instances, they're stuck 5 minutes in a stopping state because they run some GPU health checks.

For our VM solution, we get around this by hot staging VM's. As soon as one customer stops theirs, we reset everything and start it up again. To the end user, our compute seems to be instantly available. Unless of course, we run out.