Compare commits

..
Author SHA1 Message Date
rock 6d02f59a9b k8s(llm-serving): stop managing the coder InferenceService
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.
2026-11-04 06:07:20 +08:00

Diff Content Not Available