← Back to context Comment by cma 8 hours ago I think it also gets use in the /fast modes the providers sell at higher cost. 3 comments cma Reply gunalx 5 hours ago 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. cma 2 hours ago If it speeds prefill too I guess so.
gunalx 5 hours ago 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. cma 2 hours ago 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.