logoalt Hacker News

staredyesterday at 5:09 PM1 replyview on HN

I wrote this blog post myself, with AI for proofreading (typos and grammar, but not style). There were a few singular sentences for which I had a writer's block, but not much besides that.

So, if there are irrelevant remarks, these are mine. :)

Charts are vibe-coded - but it took quite a bit of hand-holding to get something decent. And the logarithmic scale for model size is my conscious choice (against Claude's initial ideas).


Replies

Ey7NFZ3P0nzAetoday at 7:21 AM

Hi,

If you ever get to writing a blog post about kv cache quantisation, i'm interested in quantising K differently than V