KV cache compression worth it: worth it?

[dockridge]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.

[marbletrack]

What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?

[localpatch78]

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4. Once you know the plain path works, then add the faster path back in piece by piece.

[deltagrid]

Appreciate the detail. I ended up in about the same place using SGLang. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[marbletrack]

Thanks, that helps. The pattern around consumer GPUs has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.

[fastfield4]

Thanks, that helps. The pattern around consumer GPUs has been pretty similar for me. The biggest change for me was simplifying the stack instead of ad

Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.

If you post your exact settings, people here can probably narrow it down pretty fast.