This is from today apr 5 saying the mmap change loads twice as big models with x100 speed up - is this not a blatant lie?
Wasn’t it discovered last week that loading larger models was an error in measurement and the speed up was from keeping things in memory after the first loading?
Wasn’t it discovered last week that loading larger models was an error in measurement and the speed up was from keeping things in memory after the first loading?
Please do correct me if I’m wrong.