PCIe lane weirdness with inference loads for Mixtral

[turbogrid11]

I'd start with the simpler stack.

[sanevault]

Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.

[turbogrid11]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tool calling.

[vrambandit]

What worked for me was pretty simple. If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.