diff --git a/k8s/apps/llm-serving/ornith.yaml b/k8s/apps/llm-serving/ornith.yaml
index ec8754e..fb0c4bc 100644
--- a/k8s/apps/llm-serving/ornith.yaml
+++ b/k8s/apps/llm-serving/ornith.yaml
@@ -3,6 +3,20 @@ kind: InferenceService
 metadata:
   annotations:
     serving.kserve.io/deploymentMode: RawDeployment
+    # Kong reads its timeouts from the Kubernetes Service, not the Ingress —
+    # Ingress annotations configure Route entities (strip-path, methods,
+    # plugins), these configure the Service entity. They were on
+    # llm-chat-ornith's Ingress and therefore ignored, leaving Kong's 60s
+    # default in force. KServe propagates InferenceService annotations to the
+    # Service it generates, which is how they reach Kong from here.
+    #
+    # This was invisible while OLLAMA_KEEP_ALIVE=-1 kept the model resident: no
+    # request ever waited on a cold load. A pod restart flushes VRAM, and
+    # loading ornith:35b takes longer than 60s, so the first request after any
+    # restart returned 504.
+    konghq.com/connect-timeout: "10000"
+    konghq.com/read-timeout: "3600000"
+    konghq.com/write-timeout: "3600000"
   labels:
     app.kubernetes.io/name: llm-ornith
     app.kubernetes.io/part-of: llm-serving
@@ -26,6 +40,10 @@ spec:
 
         ollama pull qwen2.5:3b-instruct
 
+        ollama run ornith:35b "ok" >/dev/null 2>&1 || true
+
+        ollama run qwen2.5:3b-instruct "ok" >/dev/null 2>&1 || true
+
         wait $SERVE_PID
 
         '
@@ -52,7 +70,7 @@ spec:
           command:
           - /bin/sh
           - -c
-          - ollama list 2>/dev/null | grep -q ornith && ollama list 2>/dev/null |
+          - ollama ps 2>/dev/null | grep -q ornith && ollama ps 2>/dev/null |
             grep -q qwen2.5
         periodSeconds: 10
       resources:
@@ -69,7 +87,7 @@ spec:
           command:
           - /bin/sh
           - -c
-          - ollama list 2>/dev/null | grep -q ornith && ollama list 2>/dev/null |
+          - ollama ps 2>/dev/null | grep -q ornith && ollama ps 2>/dev/null |
             grep -q qwen2.5
         failureThreshold: 120
         periodSeconds: 15