Inference
7900 XTX local stack - Printable Version

+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: AMD / ROCm (https://www.datasculpting.ai/inference/forumdisplay.php?fid=32)
+--- Thread: 7900 XTX local stack (/showthread.php?tid=140)

Pages: 1 2


Re: 7900 XTX local stack - cudapoint - 09-13-2026

Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.