+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Performance Tuning (https://www.datasculpting.ai/inference/forumdisplay.php?fid=42)
+--- Thread: disaggregated inference thoughts: anyone testing this? (/showthread.php?tid=1017)
disaggregated inference thoughts: anyone testing this? - cudapeak - 10-11-2026
I'm trying to sanity-check my setup.
I'm mostly working with FLUX in MLX on 7900 XTX. The part I'm trying to understand is quant drift.
If you've tested something similar, what did you keep and what did you stop bothering with?