dataset format recommendations

[audioforge]

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.

[routecraft]

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.

[deltapoint17]

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.

[cudapoint]

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.

[promptpoint]

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.

[embershed99]

What exact setup are you running? Are you testing this on B200 or something else?

[modbench]

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.

[homelabhenry]

same here on my side.

[phasenode]

Appreciate the detail. That matches what I saw on 7900 XTX.

[quantsupply]

Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?