distillation that keeps useful behavior

[sanevault]

Did a bit of testing and thought I'd post the result here.

After a few runs on mini PC, I ended up with decent performance, but the setup only really made sense once I adjusted around router policy.

Happy to post more details if anyone wants them.

I care more about stability than squeezing the last possible tokens/sec out of it.

[fusedriver]

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

[plainworks]

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

A couple things I'd check first. On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives.