Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

i'm not willing to trade any more quality for performance. no draft, no cache for kv either. i'll take the performance cost, it just makes me think carefully about my prompt. i rarely every need more than one prompt to get my answers. :D


Speculative decoding doesn't change output tokens.


Draft model doesn’t degrade quality!


I beg to differ, especially when it comes to code.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: