update nrp cms config

fastmachinelearning · Jan 29, 2025 · 882782e · 882782e
1 parent 90490cb
commit 882782e
Showing 1 changed file with 9 additions and 6 deletions.
diff --git a/values/values-nautilus-cms.yaml b/values/values-nautilus-cms.yaml
@@ -12,8 +12,8 @@ triton:
       --exit-timeout-secs=60 \
       --backend-config=onnxruntime,enable-global-threadpool=1
   resources:
-    limits: { cpu: 2, memory: 16G}
-    requests: { cpu: 2, memory: 16G}
+    limits: { cpu: 2, memory: 4G}
+    requests: { cpu: 2, memory: 4G}
   modelRepository:
     enabled: true
     storageType: cvmfs-pvc
@@ -37,9 +37,9 @@ triton:
                   # - Tesla-T4
                   # - NVIDIA-A10
                   # - NVIDIA-GeForce-RTX-3090
-                  - NVIDIA-GeForce-RTX-4090
+                  # - NVIDIA-GeForce-RTX-4090
                   # - NVIDIA-TITAN-RTX
-                  # - NVIDIA-RTX-A5000
+                  - NVIDIA-RTX-A5000
                   # - Quadro-RTX-6000
                   # - Tesla-V100-SXM2-32GB
                   # - NVIDIA-A40
@@ -51,7 +51,10 @@ envoy:
   enabled: true
 prometheus:
   external: false
-  serverLoadThreshold: 10
+  url: prometheus.nrp-nautilus.io
+  port: 443
+  scheme: https
+  serverLoadThreshold: 100
   ingress:
     enabled: true
     hostName: prometheus-cms.nrp-nautilus.io
@@ -78,7 +81,7 @@ ingress:
     haproxy-ingress.github.io/health-check-rise-count: "1"
 
 nodeSelector:
-  topology.kubernetes.io/zone: ucsd
+  topology.kubernetes.io/zone: cwru
 
 grafana:
   enabled: true