serving on Blackwell for FLUX

[pixelcrate82]

Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimizat

Maybe, but I had the opposite result. I've seen people blame batch size when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup. The logs were somehow calmer than I was.