Why is the GPU not full?
I made 4 requests, but only 3 workers are running and 1 is waiting, but my worker limit is 5!
5 Replies
1
Its because the other 3 are throttled so they can't accept requests
What does throttling mean?
It means the GPUs are in use by other customers.
If you want dedicated GPUs, you have to use active workers which you pay for because they run constantly.
Thank you