+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Benchmarks (https://www.datasculpting.ai/inference/forumdisplay.php?fid=65)
+--- Thread: comparing models without fooling yourself for Phi (/showthread.php?tid=397)
Pages:
1
2
Re: comparing models without fooling yourself for Phi - batchsize - 10-06-2026
that fixed it for me too.
Re: comparing models without fooling yourself for Phi - benchplease - 10-06-2026
Interesting, I hadn't tried that. I ended up in about the same place using vLLM.
Re: comparing models without fooling yourself for Phi - griffinloom66 - 10-06-2026
Quote:Interesting, I hadn't tried that. I ended up in about the same place using vLLM.
Need a little more detail here. Is this local-only or are you routing anything externally?