+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Harnesses, Agents & Orchestration (https://www.datasculpting.ai/inference/forumdisplay.php?fid=11)
+--- Forum: Routers (https://www.datasculpting.ai/inference/forumdisplay.php?fid=45)
+--- Thread: dataset format recommendations (/showthread.php?tid=665)
dataset format recommendations - phasenode - 10-03-2026
Spent some time on this today and wanted to compare notes.
I've gone back and forth between PyTorch and Ollama for FLUX. The interesting difference for me has been KV cache pressure.
Interested in tradeoffs more than fan loyalty.
Re: dataset format recommendations - plainworks - 10-03-2026
Interesting, I hadn't tried that. I don't think your conclusion is far off.
Re: dataset format recommendations - quantghost - 10-03-2026
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.
Re: dataset format recommendations - quiettoken - 10-03-2026
following this because I'm in the same boat.
Re: dataset format recommendations - thetapath - 10-03-2026
I'd approach it in a boring order. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: dataset format recommendations - phasetrack - 10-03-2026
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: dataset format recommendations - plainline - 10-04-2026
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
Re: dataset format recommendations - batchember - 10-04-2026
worth checking the driver first.