+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: RAG & Knowledge Systems (https://www.datasculpting.ai/inference/forumdisplay.php?fid=14)
+--- Forum: Search / Retrieval / Reranking (https://www.datasculpting.ai/inference/forumdisplay.php?fid=61)
+--- Thread: Help with Search / Retrieval / Reranking (/showthread.php?tid=531)
Pages:
1
2
Help with Search / Retrieval / Reranking - promptfield - 09-28-2026
Spent some time on this today and wanted to compare notes.
I've gone back and forth between Ollama and vLLM for FLUX. The interesting difference for me has been INT4.
What would you pick if you had to live with it for a few months?
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: Help with Search / Retrieval / Reranking - northgrid33 - 09-28-2026
What worked for me was pretty simple. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: Help with Search / Retrieval / Reranking - quietsupply11 - 09-28-2026
I'd start with the simpler stack.
Re: Help with Search / Retrieval / Reranking - cobalttinker - 09-28-2026
Appreciate the detail. I ended up in about the same place using llama.cpp. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: Help with Search / Retrieval / Reranking - sparrowhall - 10-01-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at workstation thermals.
Re: Help with Search / Retrieval / Reranking - audioforge - 10-04-2026
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
Re: Help with Search / Retrieval / Reranking - mangofield33 - 10-07-2026
Quote:Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, no
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at quant drift. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: Help with Search / Retrieval / Reranking - cacheplane98 - 10-07-2026
following this because I'm in the same boat.
Re: Help with Search / Retrieval / Reranking - audiopoint18 - 10-08-2026
I'd start with the simpler stack.
Re: Help with Search / Retrieval / Reranking - southtinker - 10-09-2026
Quote:I'd start with the simpler stack.
A couple things I'd check first. On 7900 XTX, 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.