←back to thread

AI engineers claim new algorithm reduces AI power consumption by 95%

(www.tomshardware.com)
352 points ferriswil | 2 comments | 19 Oct 24 18:03 UTC | HN request time: 0.52s | source
Show context
kayo_20211030 ◴[19 Oct 24 19:34 UTC] No.41890110[source]▶
Extraordinary claims require extraordinary evidence. Maybe it's possible, but consider that some really smart people, in many different groups, have been working diligently in this space for quite a while; so claims of 95% savings on energy costs _with equivalent performance_ is in the extraordinary category. Of course, we'll see when the tide goes out.
replies(6): >>41890280 #>>41890322 #>>41890352 #>>41890379 #>>41890428 #>>41890702 #
Randor ◴[19 Oct 24 20:05 UTC] No.41890352[source]▶
The energy claims up to ~70% can be verified. The inference implementation is here:

https://github.com/microsoft/BitNet

replies(2): >>41890548 #>>41891150 #
1. littlestymaar ◴[19 Oct 24 22:08 UTC] No.41891150[source]▶
How does the liked article relate to BitNet at all? It's about the “addition is all you need” paper which AFAIK is unrelated.
replies(1): >>41892383 #
2. Randor ◴[20 Oct 24 02:12 UTC] No.41892383[source]▶
Yeah, I get what you're saying but both are challenging the current MatMul methods. The L-Mul paper claims "a power savings of 95%" and that is the thread topic. Bitnet proves that at least 70% is possible by getting rid of MatMul.