how much orchestration is too much

[llm_wren]

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

Maybe useful as a starting point: MLX on 4090, keeping NVFP4 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.

[llm_wren]

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

Interesting, I hadn't tried that. That matches what I saw on B200. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[vramstream]

I'd approach it in a boring order. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[llm_wren]

A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?

[cudacrate]

A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?

What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?

[bytegarden73]

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[llm_wren]

Maybe, but I had the opposite result. 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.

[ggufvault]

My first guess would be this: 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.

[cudacrate]

That matches what I was seeing. The pattern around tail latency 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.

[llm_wren]

following this because I'm in the same boat.