fix: Add weight: 1 to the EPP config plugins (#6756)

Signed-off-by: Anna Tchernych <atchernych@nvidia.com>

deploy/inference-gateway/standalone/helm/dynamo-gaie/epp-config-dynamo.yaml

@@ -46,6 +46,8 @@ schedulingProfiles:
   - name: decode
     plugins:
       - pluginRef: decode-filter
+        weight: 1
       - pluginRef: dyn-decode
         weight: 1
       - pluginRef: picker
+        weight: 1

docs/kubernetes/inference-gateway.md

@@ -278,7 +278,7 @@ ps aux | grep "minikube tunnel" | grep -v grep # make sure minikube tunnel is no
 minikube tunnel # start the tunnel
 
 # in second terminal where you want to send inference requests
-GATEWAY_URL=$(kubectl get svc inference-gateway -n my-model -o jsonpath='{.spec.clusterIP}') & echo $GATEWAY_URL
+GATEWAY_URL=$(kubectl get svc inference-gateway -n my-model -o jsonpath='{.spec.clusterIP}') && echo $GATEWAY_URL
 ```
 
 b. use port-forward to expose the gateway to the host

examples/backends/vllm/deploy/gaie/agg.yaml

@@ -14,6 +14,9 @@ spec:
       extraPodSpec:
         mainContainer:
           image: nvcr.io/nvidia/ai-dynamo/epp-image:my-tag
+          env:
+            - name: DYN_DECODE_FALLBACK
+              value: "true"
       eppConfig:
         config:
           plugins:
@@ -33,9 +36,11 @@ spec:
             - name: decode
               plugins:
                 - pluginRef: decode-filter
+                  weight: 1
                 - pluginRef: dyn-decode
                   weight: 1
                 - pluginRef: picker
+                  weight: 1
     VllmDecodeWorker:
       componentType: worker
       envFromSecret: hf-token-secret

recipes/llama-3-70b/vllm/agg/gaie/deploy.yaml

@@ -46,9 +46,11 @@ spec:
             - name: decode
               plugins:
                 - pluginRef: decode-filter
+                  weight: 1
                 - pluginRef: dyn-decode
                   weight: 1
                 - pluginRef: picker
+                  weight: 1
     VllmDecodeWorker:
       componentType: worker
       envFromSecret: hf-token-secret

recipes/llama-3-70b/vllm/disagg-single-node/gaie/deploy.yaml

@@ -45,15 +45,19 @@ spec:
           - name: prefill
             plugins:
             - pluginRef: prefill-filter
+              weight: 1
             - pluginRef: dyn-prefill
               weight: 1
             - pluginRef: picker
+              weight: 1
           - name: decode
             plugins:
             - pluginRef: decode-filter
+              weight: 1
             - pluginRef: dyn-decode
               weight: 1
             - pluginRef: picker
+              weight: 1
     VllmPrefillWorker:
       componentType: worker
       subComponentType: prefill