From a42c73c1fc2a6fe356e7a064fe7c2d45bf6175f5 Mon Sep 17 00:00:00 2001 From: rock Date: Thu, 5 Nov 2026 02:28:40 +0000 Subject: [PATCH] fix(llm-serving): retire reference clef-serve at replicas 0 (#113) Co-authored-by: rock --- k8s/apps/llm-serving/clef-serve.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/k8s/apps/llm-serving/clef-serve.yaml b/k8s/apps/llm-serving/clef-serve.yaml index a8b820f..bd37506 100644 --- a/k8s/apps/llm-serving/clef-serve.yaml +++ b/k8s/apps/llm-serving/clef-serve.yaml @@ -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: