Can't select 2x GPU for my old pod, while I could start a new pod with the same GPU setup
Might be a stupid question, but I had a pod running yesterday with 2 H100 PCIe and I can start my pod only with 0 or 1 GPU, which looks like an availability issue. But If I want to deploy a new pod, I can choose 2 H100 PCIe and the availability is medium.
1 Reply
yes, imagine theres a datacenter. your data is in one of the computers there, but there is other computers available for rent too
you can't magically move your date into another computer that's available for rent
the current computer that has your data is rented by other people too// so thats why the gpu is limited in specific time too