+- 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 (/showthread.php?tid=408)
vLLM vs SGLang for small teams - signalcraft14 - 09-21-2026
Maybe I'm missing something obvious.
I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling tokens/sec.
If you've tested something similar, what did you keep and what did you stop bothering with?
I care more about stability than squeezing the last possible tokens/sec out of it.
Re: vLLM vs SGLang for small teams - rocmrunner40 - 09-21-2026
Thanks, that helps. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: vLLM vs SGLang for small teams - promptpoint - 09-21-2026
My first guess would be this: If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
Re: vLLM vs SGLang for small teams - vramport - 09-22-2026
Thanks, that helps. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: vLLM vs SGLang for small teams - promptpoint - 09-22-2026
Quote:Thanks, that helps. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of t
Can you fill in a bit more context? Is this local-only or are you routing anything externally?
Re: vLLM vs SGLang for small teams - batchsize - 09-22-2026
A couple things I'd check first. On dual 3090, 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: vLLM vs SGLang for small teams - mangofield33 - 09-22-2026
Quote:A couple things I'd check first. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lo
subscribed, curious where this lands.
Re: vLLM vs SGLang for small teams - rocmrunner40 - 09-22-2026
I'd approach it in a boring order. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: vLLM vs SGLang for small teams - routearch - 09-23-2026
Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?