logoalt Hacker News

hedgehogyesterday at 8:58 PM1 replyview on HN

Ok, at 50k context its about 126 prefill, 13 generation.


Replies

cmrdporcupineyesterday at 9:00 PM

Oh, interesting. So beats on prefill and matches at decode. MTP will help you a bit once you have it. I've got a lot of work to do to optimize prefill.

Kinda wish I had a Strix Halo here to play with as well.

show 1 reply