vLLM vs SGLang for small teams

[cacheline]

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

Just sharing a setup that ended up working reasonably well: Qwen, MLX, Threadripper box, with a lot of attention on tool calling.

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

[batchsize]

following this because I'm in the same boat.

I'm happy to test one more variant if you want a second data point.