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

After a few runs on Threadripper box, I ended up with decent performance, but the setup only really made sense once I adjusted around batch size.

Curious if anyone else landed in the same place.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

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.

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

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

I tried this with Phi using PyTorch on GB200. The headline result was better than I expected, but small local stacks still ended up being the limiting factor.

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

This is mostly for local work rather than public serving.

Spent some time on this today and wanted to compare notes.

I've gone back and forth between TensorRT-LLM and llama.cpp for Qwen. The interesting difference for me has been speculative decoding.

What would you pick if you had to live with it for a few months?

This is mostly for local work rather than public serving.

Spent some time on this today and wanted to compare notes.

I'm comparing two approaches here: keep it simple on GB200, or squeeze more out of the stack and deal with the complexity.

Interested in tradeoffs more than fan loyalty.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

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 HBM constraints decides everything downstream.

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

I figured I'd ask here before changing everything.

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

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.

Maybe useful as a starting point: vLLM on dual 3090, keeping INT4 in mind from the start.

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

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

Curious what people here are seeing.

My current setup is SGLang with 7900 XTX, and I keep running into batch size.

Would appreciate practical advice rather than theory. The logs were somehow calmer than I was.

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 VRAM headroom decides everything downstream.

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