News for hackers. Stuff that matters.
Re:DeepSeek 4 Flash local inference engine for Metal by slaw on Thursday May 07, 2026 @05:04PM (#48054990)
Check out cpp at 208.3 GiB/s, 3x faster than asm.
Re:DeepSeek 4 Flash local inference engine for Metal by akie on Friday May 08, 2026 @03:26AM (#48059833)
Yeah, because (and here's the trick) they are clever and do less work.

Optimizing things usually means "think of a way to do the same thing with less effort".

Re:DeepSeek 4 Flash local inference engine for Metal by andai on Friday May 08, 2026 @09:25AM (#48062793)
Hire the laziest programmer :)