logoalt Hacker News

augment_me • today at 2:39 AM • 1 reply • view on HN

What a non-answer. And there should be perfect latency hiding, and there should always be predictable power-of-2 workloads, and all weights should always be homogenous, etc.


Replies

adgjlsfhk1 • today at 3:26 AM

It's a reasonable answer. Consumer chips are idle 95% of the time, so idle power draw matters. AI datacenters are currently under capacity, so rather than optimizing for idle power draw, just have work to do.

➕ show 1 reply