+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Hardware (https://www.datasculpting.ai/inference/forumdisplay.php?fid=4)
+--- Forum: CPUs / NPUs / Accelerators (https://www.datasculpting.ai/inference/forumdisplay.php?fid=30)
+--- Thread: CPU-only fallback performance on 7900 XTX (/showthread.php?tid=407)
CPU-only fallback performance on 7900 XTX - benchplease - 09-21-2026
I figured I'd ask here before changing everything.
I'm mostly working with FLUX in Ollama on A6000. The part I'm trying to understand is prefix caching.
If you've tested something similar, what did you keep and what did you stop bothering with?
Re: CPU-only fallback performance on 7900 XTX - kernelrunner - 09-22-2026
Quote:I figured I'd ask here before changing everything.
Maybe, but I had the opposite result. I get why that seems right, but on B200 the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: CPU-only fallback performance on 7900 XTX - cacheplane98 - 09-24-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal.