+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Hardware (https://www.datasculpting.ai/inference/forumdisplay.php?fid=4)
+--- Forum: GPUs (https://www.datasculpting.ai/inference/forumdisplay.php?fid=28)
+--- Thread: dual GPU split inference (/showthread.php?tid=872)
Pages:
1
2
dual GPU split inference - turbogrid11 - 10-07-2026
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.
Re: dual GPU split inference - rocmriley - 10-09-2026
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.
Re: dual GPU split inference - quantyard - 10-09-2026
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.
Re: dual GPU split inference - circuitwire58 - 10-09-2026
worth checking the driver first.
Re: dual GPU split inference - paperrunner - 10-10-2026
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.
Re: dual GPU split inference - amberhall - 10-10-2026
that fixed it for me too.
Re: dual GPU split inference - mintquill - 10-13-2026
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.
Re: dual GPU split inference - paperrunner - 10-16-2026
Can you fill in a bit more context? Is this local-only or are you routing anything externally?
Re: dual GPU split inference - turbogrid11 - 10-16-2026
Quote: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.
Re: dual GPU split inference - signaltrack44 - 10-16-2026
A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?