+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Quality / Reliability Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=68)
+--- Thread: when video is still not worth the wait (/showthread.php?tid=1158)
Pages:
1
2
Re: when video is still not worth the wait - turbosupply83 - 10-18-2026
Appreciate the detail. The pattern around prefill/decode split has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: when video is still not worth the wait - plainember52 - 10-18-2026
Good point. The pattern around batch size has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: when video is still not worth the wait - visionforge - 10-18-2026
Quote:Good point. The pattern around batch size has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at wh
subscribed, curious where this lands.
Re: when video is still not worth the wait - cobalttinker - 10-18-2026
Maybe, but I had the opposite result. I get why that seems right, but on Threadripper box the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.