From 53fde83544fdc3591ab4662b05f6b791736c29c8 Mon Sep 17 00:00:00 2001 From: sirius0xdev Date: Wed, 29 Apr 2026 11:20:45 +0000 Subject: [PATCH] fix(rtx6000-scaling): set minReplicas to 1 to prevent transient scale-up/down thrashing from periodic health checks Prevents the watcher cron (every 5m) from causing unnecessary spot pod churn. Keeps 1 ready pod always (KEDA overrides deployment replicas). --- infrastructure/gpus/base/keda-gpu-scaling/keda-vllm.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/infrastructure/gpus/base/keda-gpu-scaling/keda-vllm.yaml b/infrastructure/gpus/base/keda-gpu-scaling/keda-vllm.yaml index ef7278d..34dea56 100644 --- a/infrastructure/gpus/base/keda-gpu-scaling/keda-vllm.yaml +++ b/infrastructure/gpus/base/keda-gpu-scaling/keda-vllm.yaml @@ -13,6 +13,6 @@ spec: service: rtx6000-brain-service port: 8000 replicas: - min: 0 + min: 1 max: 1