do you even need a vector DB here for Mistral

[vectorshed43]

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at speculative decoding. Once you know the plain path works, then add the faster path back in piece by piece.

[dockember]

I tested this tonight. My result was mixed: first run looked bad, second run looked normal.

[routerunner]

that fixed it for me too.

[southspark]

A couple things I'd check first. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.