setup notes worth sharing

[rasterbench]

This keeps coming up in conversation so I figured I'd start a thread.

It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with INT4.

Maybe obvious to some of you, but it clicked for me this week.

[batchshed]

worth checking the driver first.

[cozysmith]

I'd approach it in a boring order. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious.

[relayforge]

Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher.

[vectorport]

A couple things I'd check first. If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.

[rocmhouse90]

A couple things I'd check first. If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamo

Good point. I don't think your conclusion is far off. 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.

[dockbrook21]

I think the bottleneck is somewhere else. I've seen people blame small local stacks when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[torchdesk]

That matches what I was seeing. The pattern around router policy has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.