This message was deleted.
# announcements
w
This message was deleted.
b
basically there are GPU servers spinning up and down in the background and we don't want to overload them.
Right now we stare at the deploy logs and update the % traffic to the experiment manually every 30 mins over the interval of T hours (and stop increasing if the deploy goes bad)
f
Right now, we don’t have an automatic way to do ramping through the UI. We do have an API that would allow you to script it if you would like
b
Yeah that would be super cool!
Can you link relevant api docs?
f
ah, the new API endpoints are not yet available
148 Views