added limits to cpu deployment

Signed-off-by: Nir Rozenbaum <[email protected]>

Author: nirrozenbaum

config/manifests/vllm/cpu-deployment.yaml

@@ -31,6 +31,8 @@ spec:
               value: "8000"
             - name: VLLM_ALLOW_RUNTIME_LORA_UPDATING
               value: "true"
+            - name: VLLM_CPU_KVCACHE_SPACE
+              value: "4"
           ports:
             - containerPort: 8000
               name: http
@@ -55,6 +57,13 @@ spec:
             periodSeconds: 5
             successThreshold: 1
             timeoutSeconds: 1
+          resources:
+             limits:
+               cpu: "12"
+               memory: "9000Mi"
+             requests:
+               cpu: "12"
+               memory: "9000Mi"
           volumeMounts:
             - mountPath: /data
               name: data