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:
@@ -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:
|
||||||
|
|||||||
Reference in New Issue
Block a user