Selfhosted

The amount of absolutely wrong answers in here is astounding.

NO. PCIE is not plug and play. Moreover, having a dead PCIE device that was previously accepting information, and then suddenly stops, is almost guaranteed to cause a kernel panic on any OS because of an overflowing bus of tons of data that can't just sit there waiting. It's a house of cards at that point. It's also going to possibly harm the physical machine when the power comes back on due to a sudden influx of power from an outside PSU powering up a device not meant for such things.

Why wouldn't instead think of maybe NOT running an insane workload on such a machine with insanely power hungry GPUs, and maybe go for an AMD APU instead? Then you'll get all the things you want.

This is a terrible idea, no really.

Any system that shares power and grounds (i.e. on the same bus), keep on the same power supply/domain.

Even, if!!!!, it doesn't fry your computer when one power system goes off but the other stays on - the system will absolutely not be stable, and will behave in unexpected ways.

DO NOT DO THIS.

I think the safe option would be to use a smart UPS and Network UPS Tools to shutdown the LLM virtual machine when it's running on battery. I do something similar with my NAS as it's running on an older dell R510 so when the UPS goes onto battery it'll safely shut down that whole machine to extend how long my networking gear will stay powered.

You could accomplish what you're trying by putting the GPU in a second computer. Further, most UPSes have a data interface, so that you could have the GPU computer plugged into the UPS too, but receive the signal when power is out, so it can save its work and shutdown quickly preserving power in the UPS batteries. The only concern there would be the max current output of the UPS in the event of a power outage being able to power both computers for a short time.

What you want are two servers, one for each purpose. What you are proposing is very janky and will compromise the reliability of your services.

It looks like regular PSUs are isolated from the mains ground with a transformer. That means that two PSUs’ DC grounds will not be connected. That will likely cause problems for you, as they’ll have to back flow current in places that do NOT expect back flow current to account for the voltage differences between the two ground potentials. Hence it might damage the GPU which is going be the mediator between these two PSUs - and maybe the mobo if everything goes to shit.

Now I am not saying this will be safe, but you may avoid that issue by tying the grounds of the two PSUs together. You still have the issue where if, say, PSU1’s 12V voltage plane meets PSU2’s 12V voltage plane and they’re inevitably not the same exact voltage, you’ll have back flowing current again which is bad because again nothing is designed for that situation. Kind of like if you pair lithium batteries in parallel that aren’t matched, the higher voltage one will back charge the other and they’ll explode.

It sounds like a fire hazard. Do not mix power supplies especially if only one is plugged into a UPS

The proper way of doing this is to have two separate systems in a cluster such as proxmox. The system with GPUs runs certain workloads and the non GPU system runs other workloads.

Each system can be connected (or not) to a ups and shut down with a power outage and then boot back up when power is back.

Don't try hot-plugging a gpu, it will never be reliable.

Run a proxmox cluster or kubernetes cluster, it is designed for this type of application but will add a fair amount of complexity.

I imagine this would be up to the application. What you’re describing would been seen by the OS as the device becoming unavailable. That won’t really affect the OS. But, it could cause problems with the drivers and/or applications that are expecting the device to be available. The effect could range from “hm, the GPU isn’t responding, oh well” to a kernel panic.

Nope. I actually did that unintentionally on a PC I built. I only used one power wire when the GPU needed 2 so it couldn't use all the power it needed when running 100%. My understanding was PCI doesn't support disconnecting devices so the system expects all components it starts up with to be available all the time. Lose one and the system goes down.

Acronyms, initialisms, abbreviations, contractions, and other phrases which expand to something larger, that I've seen in this thread:

5 acronyms in this thread; the most compressed thread commented on today has 4 acronyms.

[Thread #806 for this sub, first seen 15th Jun 2024, 14:15] [FAQ] [Full list] [Contact] [Source code]

Most UPS systems of quality will come with software capabilities. You can leverage this and just use a daemon to check the charge status every minute or so. If it's ever off AC or reporting charge levels lowering, you can toss the system into a low power profile. This might accomplish what you're trying to do.