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

Co-authored-by: rock <[email protected]>
This commit was merged in pull request #113.
This commit is contained in:
2026-11-05 02:28:40 +00:00
committed by rock
parent b790f5fb9b
commit a42c73c1fc
+1 -1
View File
@@ -43,7 +43,7 @@ spec:
# Cold start is about four minutes: the pod pip-installs on every boot because the # 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 # torch base image cannot be pushed to the registry (Cloudflare answers 413 above
# 100 MB per layer). startupProbe allows for that. # 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 # 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. # the new pod Pending forever waiting for a card the old pod still holds.
strategy: strategy: