+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: LLM Models (https://www.datasculpting.ai/inference/forumdisplay.php?fid=12)
+--- Forum: Open Weight (https://www.datasculpting.ai/inference/forumdisplay.php?fid=49)
+---- Forum: Recipes & Configurations (https://www.datasculpting.ai/inference/forumdisplay.php?fid=52)
+---- Thread: simple router policy ideas: anyone testing this? (/showthread.php?tid=1436)
Pages:
1
2
Re: simple router policy ideas: anyone testing this? - torchsupply99 - 10-19-2026
worth checking the driver first. The logs were somehow calmer than I was.
Re: simple router policy ideas: anyone testing this? - kernelghost - 10-19-2026
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
Re: simple router policy ideas: anyone testing this? - fusedhall - 10-19-2026
I hit almost the same issue last night.
Re: simple router policy ideas: anyone testing this? - macronest - 10-19-2026
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. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.