News for hackers. Stuff that matters.
Re:Google Gemini: Context Caching by ethbr1 on Thursday May 16, 2024 @05:57PM (#40383778)
If you can pipeline upcoming requests and tie state to a specific request, doesn't that allow you to change how you design physical memory? (at least for inference)

Stupid question, but why wouldn't {extremely large slow-write, fast-read memory} + {smaller, very fast-write memory} be a feasible hardware architecture?

If you know many, many cycles ahead what you'll need to have loaded at a specific time.

Or hell, maybe it's time to go back to memory bank switching.

There are no comments on this comment yet.