+- 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=487)
Pages:
1
2
dataset format recommendations - audioforge - 09-25-2026
Did a bit of testing and thought I'd post the result here.
I tried this with Kimi using MLX on A6000. The headline result was better than I expected, but batch size still ended up being the limiting factor.
Happy to post more details if anyone wants them.
Re: dataset format recommendations - routecraft - 09-26-2026
A couple things I'd check first. On B200, 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.
Re: dataset format recommendations - deltapoint17 - 09-26-2026
Quote:A couple things I'd check first. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.
Re: dataset format recommendations - cudapoint - 09-27-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: dataset format recommendations - promptpoint - 09-27-2026
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality. The logs were somehow calmer than I was.
Re: dataset format recommendations - embershed99 - 09-27-2026
What exact setup are you running? Are you testing this on B200 or something else?
Re: dataset format recommendations - modbench - 09-27-2026
Maybe, but I had the opposite result. I get why that seems right, but on M3 Max the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: dataset format recommendations - homelabhenry - 09-30-2026
same here on my side.
Re: dataset format recommendations - phasenode - 10-01-2026
Appreciate the detail. That matches what I saw on 7900 XTX.
Re: dataset format recommendations - quantsupply - 10-02-2026
Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?