+- 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 for Phi (/showthread.php?tid=215)
Pages:
1
2
simple router policy ideas for Phi - emberquill - 09-10-2026
This keeps coming up in conversation so I figured I'd start a thread.
It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with HBM constraints.
Wondering if this is just where the whole space is heading now.
Re: simple router policy ideas for Phi - deltastation - 09-12-2026
I'd start with the simpler stack.
Re: simple router policy ideas for Phi - circuitworks90 - 09-12-2026
A couple things I'd check first. On Threadripper box, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: simple router policy ideas for Phi - phasenode - 09-13-2026
that fixed it for me too. The logs were somehow calmer than I was.
Re: simple router policy ideas for Phi - audioriver - 09-14-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at batch size. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: simple router policy ideas for Phi - routearch - 09-14-2026
What exact setup are you running? Is this local-only or are you routing anything externally?
Re: simple router policy ideas for Phi - mangohouse - 09-14-2026
subscribed, curious where this lands.
Re: simple router policy ideas for Phi - homelabhenry - 09-17-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: simple router policy ideas for Phi - bytelab - 09-17-2026
Quote:A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there. Not glamorous advice, but re
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
Re: simple router policy ideas for Phi - mangofield33 - 09-17-2026
Quote:[quote]A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there. Not glamorous advice,
Good point. I ended up in about the same place using LM Studio. The biggest change for me was simplifying the stack instead of adding one more optimization layer.