k8s(llm-serving): client-facing Service for candle-vllm coder

Creates coder-predictor selecting app=candle-vllm on ports 80 and 8080, so clients keep one stable host name across the vLLM -> candle-vllm handoff and only this selector changes from now on. The retired KTML predictor requested two V100s and never reached Ready.
2026-11-04 18:59:56 +08:00
parent c5099e3a8f
commit 67760720fc
2 changed files with 41 additions and 0 deletions
@@ -16,6 +16,7 @@ resources:
  - clef-serve.yaml
  # Stable client-facing name for the chat model. poimen-memory points at this Service,
  # so the vLLM -> candle-vllm handoff is a selector edit here and no client change.
+  - coder-service.yaml
  - reasoning-long-service.yaml
  # ornith is retired: its InferenceService still reports Ready=True while running zero
  # replicas, because desired equals available at 0. Its manifest was never committed,