May I ask if there is a difference in priority or the number of GPUs between Pod and serverless? For example, if all the 3090 GPUs are out in POD, will they also be out in serverless?
Or is the difference that serverless is like a service used to manage, auto-scale, and save costs?
#About resources and priority compare with Pod
fossil drum
misty needle
May I ask if there is a difference in priority or the number of GPUs between Pod...
Yess, usually they release on pods first then test for serverless, if it's doing great then they should release it for serverless