You'll need your own wiring to run your PC soon :-)
I am not a physicist or biologist or anything like that so my intuition is probably completely wrong but it seems to me that for more basic inference operations (lets say add two numbers) power consumption from a processor and a brain is not that different. It’s like seeing how expensive it is for computers to infer for any NLP model, humans should be continuously eating carbs just to talk.
Sure it is - it is too hard to figure it out based on 2 numbers number, but lets multiply that by a billion - how much energy does it take a computer to add two billion numbers? Far less than the energy it would take a human brain to add them.
[It's been quite a while since I studied this stuff, so I can't recall whether 60 mV/decade is a constant for silicon specifically or all semiconductors.]
175 GB aggregate on both RAM and nvme is in the realm of home deep learning workstation.
As long as you aren’t too fussy about inference speed of course.
>but is able to work with different configurations with ≈200GB of GPU memory in total which divide weight dimensions correctly (e.g. 16, 64, 128).
In theory you could probably assign a powerful enough iGPU a few hundred gigabytes of memory already, but just like Apple Silicon the integrated GPU isn't exactly very powerful. The difference between the M1 iGPU and the AMD 5700G is less than 10% and a loaded out system should theoretically be tweakable to dedicate hundreds of gigabytes of VRAM to it.
It's just a waste of space. An RTX3090 is 6 to 7 times faster than even the M1, and the promised performance increase of about 35% for the M2 will means nothing when the 4090 will be released this year.
I think there are better solutions for this. Leveraging the high throughput of PCIe 5 and resizable BAR support might be used to quickly swap out banks of GPU memory, for example, at a performance decrease.
One big problem with this is that GPU manufacturers have incentive to not implement ways for consumers GPUs to compete with their datacenter products. If a 3080 with some memory tricks can approach an A800 well enough, Nvidia might let a lot of profit slip through their hands and they can't have that.
Maybe Apple's tensor chip will be able to provide a performance boost here, but it's stuck on working with macOS and the implementations all seem proprietary so I don't think cross platform researchers will really care about using it. You're restricted by Apple's memory limitations anyway, it's not like you can upgrade their hardware.
The Mac Studio maxes out at 128GB currently for around $5K, so 256GB isn't that far out and might work with the ~200GB Yandex says is required.