+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: RAG & Knowledge Systems (https://www.datasculpting.ai/inference/forumdisplay.php?fid=14)
+--- Forum: RAG (https://www.datasculpting.ai/inference/forumdisplay.php?fid=58)
+--- Thread: where reranking mattered (/showthread.php?tid=620)
where reranking mattered - homelabhenry - 09-30-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Maybe useful as a starting point: LM Studio on 4090, keeping consumer GPUs in mind from the start.
Maybe useful as a starting point for newer folks.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: where reranking mattered - sanepeak48 - 09-30-2026
Need a little more detail here. What model, what runtime, and roughly what context size?
Re: where reranking mattered - rocmmixer - 10-03-2026
Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: where reranking mattered - kernelghost - 10-05-2026
Good point. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: where reranking mattered - modbench - 10-05-2026
I think the bottleneck is somewhere else. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Could be a workload difference, but I wouldn't generalize too fast from one setup.
If you post your exact settings, people here can probably narrow it down pretty fast.
Re: where reranking mattered - nanopatch - 10-05-2026
Did a small comparison this afternoon. On B200 with PyTorch, I saw basically the same behavior. At this point the real bottleneck is my patience.
Re: where reranking mattered - homelabhenry - 10-06-2026
What worked for me was pretty simple. 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.
Re: where reranking mattered - sparrowbrook - 10-09-2026
Interesting, I hadn't tried that. 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: where reranking mattered - audionode8 - 10-10-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there.
Re: where reranking mattered - modbench - 10-10-2026
Quote:I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there.
I hit almost the same issue last night.