fix(llm-serving): retire reference clef-serve at replicas 0 (#113 )

Co-authored-by: rock <[email protected]>
fix(llm-serving): run clef-candle from the fixed binary on the models PVC (#112 )
2026-11-05 02:28:40 +00:00 · 2026-11-05 02:19:58 +00:00
1 changed files with 1 additions and 1 deletions
@@ -43,7 +43,7 @@ spec:
  # Cold start is about four minutes: the pod pip-installs on every boot because the
  # torch base image cannot be pushed to the registry (Cloudflare answers 413 above
  # 100 MB per layer). startupProbe allows for that.
-  replicas: 1
+  replicas: 0
  # Recreate, not RollingUpdate. Every GPU card is allocated, so a rolling update leaves
  # the new pod Pending forever waiting for a card the old pod still holds.
  strategy:
Author	SHA1	Message	Date
rock	a42c73c1fc	fix(llm-serving): retire reference clef-serve at replicas 0 (#113 ) Co-authored-by: rock <[email protected]>	2026-11-05 02:28:40 +00:00
rock	b790f5fb9b	fix(llm-serving): run clef-candle from the fixed binary on the models PVC (#112 ) Co-authored-by: rock <[email protected]>	2026-11-05 02:19:58 +00:00