Y
Hacker News
new
|
ask
|
show
|
jobs
by
jboss10
14 days ago
Most of the time, the speed of these models are constrained by memory bandwidth. GPUs normally have much more memory bandwidth.
1 comments
davedx
14 days ago
I'd expect the memory bandwidth to be the same for the CPU and GPU under a unified memory architecture like Apple silicon uses?
link