simple router policy ideas on GB200

[turboscope5]

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: Kimi, TensorRT-LLM, M3 Max, with a lot of attention on tail latency.

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

This is mostly for local work rather than public serving.

[tensorport]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Phi and compare from there.

[amberkite]

Thanks, that helps. The pattern around tool calling 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.