+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: vLLM / SGLang (https://www.datasculpting.ai/inference/forumdisplay.php?fid=36)
+--- Thread: router in front of vLLM for Phi (/showthread.php?tid=1256)
Pages:
1
2
Re: router in front of vLLM for Phi - thetashed24 - 10-18-2026
subscribed, curious where this lands.
Re: router in front of vLLM for Phi - llmarch83 - 10-18-2026
Appreciate the detail. That matches what I saw on 5090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
If you post your exact settings, people here can probably narrow it down pretty fast.
Re: router in front of vLLM for Phi - cacheline - 10-19-2026
Quote:subscribed, curious where this lands.
subscribed, curious where this lands. At this point the real bottleneck is my patience.
Re: router in front of vLLM for Phi - promptspark58 - 10-19-2026
My first guess would be this: On M3 Max, 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.
Re: router in front of vLLM for Phi - signalcraft14 - 10-19-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at quant drift. Not glamorous advice, but repeatable baselines save a lot of time. The logs were somehow calmer than I was.