Comment by vineyardmike
15 days ago
I wonder if that’s more to price in the cost of keeping old models around on expensive inference hardware. It’s not like old models get cheaper to run, and a more heterogeneous fleet is less efficient to manage.
15 days ago
I wonder if that’s more to price in the cost of keeping old models around on expensive inference hardware. It’s not like old models get cheaper to run, and a more heterogeneous fleet is less efficient to manage.
[dead]