I think it also gets use in the /fast modes the providers sell at higher cost.
They probably use it on all models. Fast is probably just a resource pool with less congestion and therefore faster throughput per user but less efficent.
If it speeds prefill too I guess so.
They probably use it on all models. Fast is probably just a resource pool with less congestion and therefore faster throughput per user but less efficent.
If it speeds prefill too I guess so.