7900 XTX local stack

[mintforge]

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.

[sparrowbrook]

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.