simple router policy ideas

[phasetrack]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4. Not glamorous advice, but repeatable baselines save a lot of time.

[griffinloom66]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[quantsupply]

I don't think that's the whole story. I get why that seems right, but on 4090 the bottleneck felt elsewhere.

[paperport64]

I don't think that's the whole story. I get why that seems right, but on 4090 the bottleneck felt elsewhere.

A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?