NHacker Next
- new
- past
- show
- ask
- show
- jobs
- submit
login
Rendered at 02:37:38 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
Would being able to alter voltage levels on the fly (eg, cells x y and z get 1.25 while abc get 1.2) expand the ability here?
"why are we still transferring data to the compute? Why not execute AI inference natively within the memory?"
You already answered that question: 47.5 seconds per token from a tiny 2B 1-bit model model.