alt Hacker NewsYou’re right, but this poses a separate issue as the providers then do FP4 PTQ, which is quite lossy. Reduces the model size and optimizes for Blackwells at the (imo severe) cost of performance.
You’re right, but this poses a separate issue as the providers then do FP4 PTQ, which is quite lossy. Reduces the model size and optimizes for Blackwells at the (imo severe) cost of performance.