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

Maybe useful as a starting point: SGLang on mini PC, keeping INT4 in mind from the start.

Maybe useful as a starting point for newer folks.

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

One thing I keep noticing is that people underestimate batch size until they actually try to run this stuff for more than one afternoon.

Curious whether that lines up with what other people are seeing.

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

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

This isn't revolutionary, but the combination of SGLang and mini PC felt surprisingly usable once I tuned around consumer GPUs.

Maybe useful as a starting point for newer folks.

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

The more I work with local setups, the more it seems like NVFP4 decides everything downstream.

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

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

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

Maybe useful as a starting point: PyTorch on mini PC, keeping structured output in mind from the start.

Feel free to tear it apart if you see something dumb.

Did a bit of testing and thought I'd post the result here.

After a few runs on GB200, I ended up with decent performance, but the setup only really made sense once I adjusted around workstation thermals.

Nothing scientific here, just practical notes from a real setup.

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 long context.

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

Has anyone else run into this?

I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling prefix caching.

Not looking for the perfect answer, mostly what worked in real use.

This is mostly for local work rather than public serving.

Has anyone else run into this?

My current setup is SGLang with Threadripper box, and I keep running into token cost.

If you've tested something similar, what did you keep and what did you stop bothering with?

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.

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

This isn't revolutionary, but the combination of SGLang and GB200 felt surprisingly usable once I tuned around INT4.

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