update the average itl, and other metrics into router.py, engine_stat…

…s.py and request_stats.py, update observe/install.sh to helm update to solve the problem already run helm service same name, update dashboard layout with latest metrics, update request_generator to align with the new endpoint /v1 Signed-off-by: sitloboi2012 <[email protected]>
vllm-project · Feb 18, 2025 · 0915c17 · 0915c17
1 parent a0108ed
commit 0915c17
Show file tree

Hide file tree

Showing 7 changed files with 338 additions and 321 deletions.
diff --git a/observability/install.sh b/observability/install.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 
 helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
-helm install kube-prom-stack prometheus-community/kube-prometheus-stack \
+helm upgrade --install kube-prom-stack prometheus-community/kube-prometheus-stack \
   --namespace monitoring \
   --create-namespace \
   -f values.yaml