+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Performance Tuning (https://www.datasculpting.ai/inference/forumdisplay.php?fid=42)
+--- Thread: disaggregated inference thoughts (/showthread.php?tid=1306)
Pages:
1
2
Re: disaggregated inference thoughts - mangoquill - 10-19-2026
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. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: disaggregated inference thoughts - prompttinker44 - 10-19-2026
What exact setup are you running? What model, what runtime, and roughly what context size?
Re: disaggregated inference thoughts - sparrowshed - 10-19-2026
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher.
Re: disaggregated inference thoughts - papermixer4 - 10-19-2026
Quote:Appreciate the detail. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimi
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there.
Re: disaggregated inference thoughts - kernelrunner - 10-19-2026
Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: disaggregated inference thoughts - rocmpath - 10-19-2026
Ran a quick check on my box. On mini PC with MLX, I saw basically the same behavior. I expected the model choice to matter more than it did.