+- 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 on Threadripper box (/showthread.php?tid=714)
Pages:
1
2
Re: vLLM vs SGLang for small teams on Threadripper box - rocmrunner40 - 10-09-2026
Good point. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: vLLM vs SGLang for small teams on Threadripper box - amberrunner - 10-09-2026
Good point. I ended up in about the same place using SGLang. 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: vLLM vs SGLang for small teams on Threadripper box - thetashed24 - 10-10-2026
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: vLLM vs SGLang for small teams on Threadripper box - batchsize - 10-10-2026
I'd approach it in a boring order. On 4090, 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.