Hacker News Reader

I have high hopes for optical computing applications in ML, we need 100x efficiency to run LLMs on edge.

Optical switching is about training at scale and replaces classical physical networking systems (people will say things like "electrical", "copper", etc.). Running models at edge devices is almost by definition without networking.

Not my area, just curious.

If I am getting this (still reading the paper... on a phone :/)... Stupid fast latency due to no processing overhead but slow switching speeds due to how it physically switches, this is basically good for any type of reconfigurable cluster of systems that need low latency without a fixed topology, not strictly ML specific or have I misunderstood that?

Correct, google also has a paper on this at the DC level

https://arxiv.org/pdf/2208.10041.pdf

Reply on news.ycombinator.com