Fix slow decodes "poisoning" sleep times when using power throttling

[omnomburp]

When using --power <number>, decode could slow down dramatically after prefill
(~0.11 tok/s observed) even though unthrottled decode was normal.

The throttle used the first decode timing samples immediately to seed its EMA and
sleep duration. If those first samples were cold/outliers, the resulting long
sleeps could keep the GPU cold and reinforce the slow decode loop.

This change skips sleeping for the first few decode evals, uses the fastest
warmup sample to seed the decode average, and caps later outlier samples relative
to the current average.