+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Prompting & Context Engineering (https://www.datasculpting.ai/inference/forumdisplay.php?fid=15)
+--- Forum: Prompts / System Prompts (https://www.datasculpting.ai/inference/forumdisplay.php?fid=62)
+--- Thread: prompt length getting silly (/showthread.php?tid=1020)
Pages:
1
2
prompt length getting silly - localpatch - 10-10-2026
Posting this in case it saves someone else a little time.
If you were starting from scratch today for this use case, what would you choose first and what would you ignore?
Would rather learn from your scars than collect my own all at once.
Re: prompt length getting silly - nanopatch - 10-12-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there.
Re: prompt length getting silly - thetaarch43 - 10-13-2026
Thanks, that helps. I don't think your conclusion is far off.
Re: prompt length getting silly - paperport64 - 10-13-2026
What worked for me was pretty simple. If you're on TensorRT-LLM, 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: prompt length getting silly - thetafield - 10-14-2026
A couple things I'd check first. On Threadripper box, 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: prompt length getting silly - quiettoken - 10-15-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at continuous batching. Not glamorous advice, but repeatable baselines save a lot of time.
Re: prompt length getting silly - northgarden37 - 10-16-2026
worth checking the driver first.
Re: prompt length getting silly - fusedhall56 - 10-18-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: prompt length getting silly - thetaarch43 - 10-18-2026
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher.
Re: prompt length getting silly - thetafield - 10-19-2026
Quote:My first guess would be this: On mini PC, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of
worth checking the driver first.