From fffe3f20d6c5d9c57a3855c4d8437f4005391de3 Mon Sep 17 00:00:00 2001 From: Sirius Claw Date: Thu, 23 Apr 2026 02:55:07 +0000 Subject: [PATCH] fix(keda): correct HTTPScaledObject for A100 vLLM wake-on-request - Use proper scaleTargetRef structure for http.keda.sh/v1alpha1 - Uncomment keda-vllm.yaml in kustomization - This should allow Flux to reconcile the scaler --- apps/base/customer1/openclaw/keda-vllm.yaml | 16 ++++------------ apps/base/customer1/openclaw/kustomization.yaml | 2 +- 2 files changed, 5 insertions(+), 13 deletions(-) diff --git a/apps/base/customer1/openclaw/keda-vllm.yaml b/apps/base/customer1/openclaw/keda-vllm.yaml index 5f8d82b..52fbc1e 100644 --- a/apps/base/customer1/openclaw/keda-vllm.yaml +++ b/apps/base/customer1/openclaw/keda-vllm.yaml @@ -4,21 +4,13 @@ metadata: name: openclaw-brain-a100-scaling namespace: customer1 spec: - # The host header the interceptor should match - - # Target to scale + routing info (old style) scaleTargetRef: - deployment: openclaw-brain-vllm # your Deployment name - service: openclaw-brain-service # your Service name - port: 8000 # ← change if your container port is different (e.g. 8080, 11434 for vLLM, etc.) - host: openclaw-brain-service.customer1.svc.cluster.local - # Replica settings + name: openclaw-brain-vllm + kind: Deployment + apiVersion: apps/v1 replicas: min: 0 max: 1 - - # Scaling metric - best for "wake on first request" use case + host: openclaw-brain-service.customer1.svc.cluster.local targetPendingRequests: 1 - - # Cooldown before scaling down (15 minutes idle) scaledownPeriod: 900 diff --git a/apps/base/customer1/openclaw/kustomization.yaml b/apps/base/customer1/openclaw/kustomization.yaml index f916c2b..d6862f7 100644 --- a/apps/base/customer1/openclaw/kustomization.yaml +++ b/apps/base/customer1/openclaw/kustomization.yaml @@ -2,7 +2,7 @@ apiVersion: kustomize.config.k8s.io/v1beta1 kind: Kustomization resources: # - vllm-l4.yaml - #- keda-vllm.yaml + - keda-vllm.yaml - pvc.yaml - new-configmap.yaml - deployment.yaml