DeepSeek 4 Flash local inference engine for Metal

Re:DeepSeek 4 Flash local inference engine for Metal by xtracto on Thursday May 07, 2026 @03:37PM (#48053832)

This takes me to the famous FizzBuzz High performance codegolf answer [1]. If we could implement optimizations like that for the inferences, maybe we could increase the speeds 10x or more.

[1] https://codegolf.stackexchange.com/questions/215216/high-thr...

[ Parent | on HN ]

Re:DeepSeek 4 Flash local inference engine for Metal by Juvination on Thursday May 07, 2026 @04:46PM (#48054716)

I love scrolling and reading through this, thinking yeah of course Python is slower than Java, oh wow Rust is pretty on par I wonder what the Java devs did. Then you hit asm and your jaw drops.

[ Parent | on HN ]

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.

[ Parent | on HN ]

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".

[ Parent | on HN ]

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

Hire the laziest programmer :)

[ Parent | on HN ]