+- 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=1375)
7900 XTX local stack - mintforge - 10-16-2026
I'm trying to sanity-check my setup.
My current setup is TensorRT-LLM with B200, and I keep running into prefix caching.
Would appreciate practical advice rather than theory.
Re: 7900 XTX local stack - sparrowbrook - 10-17-2026
That matches what I was seeing. The pattern around NVFP4 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.