coder.yaml requests 2 V100s and never reaches Ready, so it permanently
occupies half the GPU pool. candle-vllm serves the coder model on the
other two cards; the unmanaged predictor starves clef-serve and blocks
its own rollout on every sync.
ArgoCD has prune:false, so this removes management only. The live object
is deleted manually after the sync, otherwise selfHeal recreates it.
rock