From 9673b76fc74f04281235a56d098b1cfd1d5ec2c4 Mon Sep 17 00:00:00 2001 From: Sirius Claw Date: Wed, 22 Apr 2026 17:22:22 +0000 Subject: [PATCH] fix: trigger KEDA scale-up on 1 request instead of 3 - Wake script handles cold start, so scale immediately on first request - Reduces latency for /wake command and manual requests --- apps/base/customer1/openclaw/keda-vllm.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/apps/base/customer1/openclaw/keda-vllm.yaml b/apps/base/customer1/openclaw/keda-vllm.yaml index 09dadc2..c26cf69 100644 --- a/apps/base/customer1/openclaw/keda-vllm.yaml +++ b/apps/base/customer1/openclaw/keda-vllm.yaml @@ -18,4 +18,4 @@ spec: metadata: path: "/v1/models" host: "openclaw-brain-service.customer1.svc.cluster.local" - requestCount: "3" # Scale up when 3+ requests pending + requestCount: "1" # Scale up on 1+ request (wake script handles cold start)