+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: RAG & Knowledge Systems (https://www.datasculpting.ai/inference/forumdisplay.php?fid=14)
+--- Forum: Vector Databases (https://www.datasculpting.ai/inference/forumdisplay.php?fid=60)
+--- Thread: Help with Vector Databases with vLLM (/showthread.php?tid=819)
Help with Vector Databases with vLLM - tinycontext - 10-06-2026
Did a bit of testing and thought I'd post the result here.
After a few runs on Threadripper box, I ended up with decent performance, but the setup only really made sense once I adjusted around long context.
Nothing scientific here, just practical notes from a real setup.
The part that surprised me was how much the boring details mattered more than the model choice.
Re: Help with Vector Databases with vLLM - fastfield4 - 10-06-2026
Appreciate the detail. I ended up in about the same place using LM Studio. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: Help with Vector Databases with vLLM - emberquill - 10-06-2026
I tested this tonight. My result was mixed: first run looked bad, second run looked normal.
Re: Help with Vector Databases with vLLM - minthall - 10-07-2026
Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
Re: Help with Vector Databases with vLLM - signaltrack44 - 10-07-2026
Thanks, that helps. That matches what I saw on dual 3090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: Help with Vector Databases with vLLM - amberhall - 10-08-2026
I'd approach it in a boring order. On M3 Max, 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: Help with Vector Databases with vLLM - tinycontext - 10-08-2026
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.
Re: Help with Vector Databases with vLLM - fastfield4 - 10-09-2026
Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
I'm happy to test one more variant if you want a second data point.