+- 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: vLLM vs SGLang for small teams with PyTorch (/showthread.php?tid=352)
vLLM vs SGLang for small teams with PyTorch - phasestream53 - 09-18-2026
I figured I'd ask here before changing everything.
My current setup is LM Studio with A6000, and I keep running into NVFP4.
If you've tested something similar, what did you keep and what did you stop bothering with?
Re: vLLM vs SGLang for small teams with PyTorch - signalpeak - 09-19-2026
Good point. That matches what I saw on dual 3090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.