News for hackers. Stuff that matters.

A comment on DeepSeek 4 Flash local inference engine for Metal. Parent comment

Re:DeepSeek 4 Flash local inference engine for Metal by nopurpose on Friday May 08, 2026 @09:27AM (#48062816)
Ultra-optimized HW-specific engines is what Mojo lang seems to be targeting, but I rarely hear about it here.
[ Parent | on HN ]
Re:DeepSeek 4 Flash local inference engine for Metal by andsoitis on Friday May 08, 2026 @09:40AM (#48062998)
> Mojo lang seems to be targeting, but I rarely hear about it here

Momentum over at Mojo lang seems very very slow.

According to their roadmap, they're still busy on Phase 1 ("High performance CPU + GPU coding"), and haven't touched Phase 2 ("Systems application programming") and Phase 3 ("Dynamic object-oriented programming").

So perhaps there isn't much to talk about?

[ Parent | on HN ]
Re:DeepSeek 4 Flash local inference engine for Metal by GeekyBear on Friday May 08, 2026 @11:28AM (#48064553)
They've got a lot of work yet to do to be a general purpose language, but for GPU programming they have already demonstrated that they can outperform CUDA on Nvidia GPUs.

That's pretty compelling.

[ Parent | on HN ]