dual GPU split inference

[turbogrid11]

Posting this in case it saves someone else a little time.

If you were starting from scratch today for this use case, what would you choose first and what would you ignore?

Would rather learn from your scars than collect my own all at once.

[rocmriley]

Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.

[quantyard]

A couple things I'd check first. On 5090, 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.

[circuitwire58]

worth checking the driver first.

[paperrunner]

I'd approach it in a boring order. If you're on TensorRT-LLM, 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.

[amberhall]

that fixed it for me too.

[mintquill]

I don't think that's the whole story. 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.

[paperrunner]

Can you fill in a bit more context? Is this local-only or are you routing anything externally?

[turbogrid11]

Can you fill in a bit more context? Is this local-only or are you routing anything externally?

My first guess would be this: On Threadripper box, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[signaltrack44]

A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?