I agree. The very term “goodput” implies delivering genuinely useful value, not just raw speed. Measuring it is far from simple, and inference companies will compete fiercely to prove it. With inference chips and racks only now reaching the market, we should soon see their real utility.
@PhotonCap ""Which chip is fastest?" toward "Does that speed actually reduce the customer's total cost?""
Only a comment about that; premium services almost must be considered. In speed or whatever reason, regardless the cost