when TensorRT-LLM clearly wins

[mintquill]

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

This isn't revolutionary, but the combination of MLX and B200 felt surprisingly usable once I tuned around prefix caching.

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

[kernelmike]

Thanks, that helps. 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.