quiet dual-GPU build advice for Mixtral

[plainscope50]

worth checking the driver first.

[phasenode]

I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly.

[vectorcrate98]

Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal.

[labnest]

That matches what I was seeing. The pattern around long context has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[kernelhouse70]

subscribed, curious where this lands.