you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 11 hours ago

I am not sure it would not help commercial solutions, if all experts are used all the time, sure, but if for example the usage is biased for some experts it would enable one machine to serve more users in parallel or save on VRAM or DRAM without compromising response time, hence cutting costs.

  • source
  • parent