dual GPU split inference

[vrambandit]

This keeps coming up in conversation so I figured I'd start a thread.

One thing I keep noticing is that people underestimate HBM constraints until they actually try to run this stuff for more than one afternoon.

Curious whether that lines up with what other people are seeing.

[fusedhall]

I'd approach it in a boring order. If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[quietstack]

Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[benchplease]

I'd start with the simpler stack.

[fusedhall]

Appreciate the detail. The pattern around tail latency has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[sanevault]

My first guess would be this: On mini PC, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.