clef-serve was parked at 0 while candle-vllm took a card. worker-1 holds
four V100s, so the coder takes one and clef takes one, leaving two free
for a TP=2 candle run.
The gateway already routes the clef-flash model to clef-serve:80 on
/v1/systemone, so this single replica count is what turns that route on.