model merge got better or just different

[quiettoken]

Thought I'd post a small recipe because a lot of threads ask similar things.

Maybe useful as a starting point: TensorRT-LLM on 7900 XTX, keeping MoE serving in mind from the start.

If someone wants the exact settings I can clean them up and post them.

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

[pixelspark]

Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[nanopatch]

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tail latency.