+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Miscellaneous Discussion (https://www.datasculpting.ai/inference/forumdisplay.php?fid=24)
+--- Forum: Off Topic (https://www.datasculpting.ai/inference/forumdisplay.php?fid=27)
+--- Thread: non-AI thing you built recently (/showthread.php?tid=54)
Pages:
1
2
non-AI thing you built recently - audiorunner74 - 08-28-2026
Wanted to compare notes with people doing similar things.
I'm mostly working with FLUX in vLLM on A6000. The part I'm trying to understand is reranking.
Would appreciate practical advice rather than theory.
Re: non-AI thing you built recently - bytesupply76 - 08-29-2026
Quote:Wanted to compare notes with people doing similar things.
Interesting, I hadn't tried that. That matches what I saw on dual 3090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: non-AI thing you built recently - pixelcrate82 - 09-01-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.
Re: non-AI thing you built recently - plaingarden18 - 09-01-2026
I tested this tonight. My result was mixed: first run looked bad, second run looked normal.
Re: non-AI thing you built recently - mintstation99 - 09-02-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: non-AI thing you built recently - latentpeak22 - 09-03-2026
Quote:A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy. A lot of th
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
Re: non-AI thing you built recently - edgecoast - 09-04-2026
Quote:[quote]A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy. A lo
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.
Re: non-AI thing you built recently - quantyard - 09-04-2026
What worked for me was pretty simple. On mini PC, 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: non-AI thing you built recently - llm_wren - 09-04-2026
Quote:What worked for me was pretty simple. On mini PC, the easiest win is often to back off the aggressive settings and see whether the problem survives. O
I'd approach it in a boring order. If you're on Ollama, 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. The logs were somehow calmer than I was.
Re: non-AI thing you built recently - kernelghost - 09-04-2026
My first guess would be this: On A6000, 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.