new here, what's your stack on 5090

[quiettoken]

Good point. I ended up in about the same place using vLLM. Worth rechecking your defaults though, because one bad assumption can make the rest of the

I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Worth testing the simpler explanation before adopting the more interesting one.