←back to thread

LLM Visualization

(bbycroft.net)
638 points gmays | 1 comments | 04 Sep 25 18:06 UTC | HN request time: 0.284s | source
Show context
southp ◴[05 Sep 25 08:20 UTC] No.45136237[source]▶
It's fascinating, even though my knowledge to LLM is so limited that I don't really understand what's happening. I'm curious how the examples are plotted and how much resemblance they are to the real models, though. If one day we could reliably plot a LLM into modules like this using an algorithm, does that mean we would be able to turn LLMs into chips, rather than data centers?
replies(5): >>45136340 #>>45136985 #>>45136988 #>>45137239 #>>45166151 #
1. nl ◴[05 Sep 25 11:07 UTC] No.45137239[source]▶
LLMs already run on chips. You can run one on your phone.

Having said it's interesting to point out that the modules are what allow CPU offload. It's fairly common to run some parts on the CPU and others on the GPU/NPU/TPU depending on your configuration. This has some performance costs but allows more flexibility.