+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: AMD / ROCm (https://www.datasculpting.ai/inference/forumdisplay.php?fid=32)
+--- Thread: Instinct pricing thoughts (/showthread.php?tid=947)
Pages:
1
2
Re: Instinct pricing thoughts - torchsmith25 - 10-13-2026
Quote:Appreciate the detail. The pattern around MoE serving has been pretty similar for me. Worth rechecking your defaults though, because one bad assumptio
I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.
Re: Instinct pricing thoughts - macropoint - 10-13-2026
worth checking the driver first.
Re: Instinct pricing thoughts - rocmriley - 10-13-2026
That matches what I was seeing. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: Instinct pricing thoughts - cozykite - 10-14-2026
Appreciate the detail. The pattern around HBM constraints has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: Instinct pricing thoughts - fastquill74 - 10-14-2026
Quote:Appreciate the detail. The pattern around HBM constraints has been pretty similar for me. The biggest change for me was simplifying the stack instead
Thanks, that helps. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.