dual GPU split inference

[batchwire]

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.

[rocmriley]

Need a little more detail here. Is this local-only or are you routing anything externally?

[sanevault]

That matches what I was seeing. That matches what I saw on M3 Max. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[circuitwire58]

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.

[rocmriley]

A couple things I'd check first. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.

[edgequill]

Did a bit of testing and thought I'd post the result here.

After a few runs on GB200, I ended up with decent performance, but the setup only really made sense once I adjusted around tokens/sec.

Happy to post more details if anyone wants them.