30A new GPU generation is arriving. Plan the migration of a live 2,048-GPU cluster.▼expert★ EssentialNewMetaMicrosoftCoreWeave4 replies◆ premiumAlmost nothing about a generation change is the GPU. The facility usually cannot take the new part in the old positions, the fabric generation may not match, and the two fleets have to coexist for months. The sequencing that avoids a capacity trough, and the decision people get wrong.Open full answer →
40You must serve a frontier open-weights model on non-NVIDIA accelerators. Plan it.▼expert★ EssentialNewAMDGoogleAmazon Web Services4 replies◆ premiumThe weights are portable and almost nothing else is. Four layers have to exist before the model runs at all, the quantization format is the one most likely to be missing, and the honest plan states what will not work in the first quarter rather than promising parity.Open full answer →