diff --git a/docs/deployment/frameworks/lws.md b/docs/deployment/frameworks/lws.md
index 3319dc6c90e1e..3b9fa3ea43d64 100644
--- a/docs/deployment/frameworks/lws.md
+++ b/docs/deployment/frameworks/lws.md
@@ -22,7 +22,7 @@ Deploy the following yaml file `lws.yaml`
     metadata:
       name: vllm
     spec:
-      replicas: 2
+      replicas: 1
       leaderWorkerTemplate:
         size: 2
         restartPolicy: RecreateGroupOnPodRestart
@@ -41,7 +41,7 @@ Deploy the following yaml file `lws.yaml`
                   - sh
                   - -c
                   - "bash /vllm-workspace/examples/online_serving/multi-node-serving.sh leader --ray_cluster_size=$(LWS_GROUP_SIZE); 
-                    python3 -m vllm.entrypoints.openai.api_server --port 8080 --model meta-llama/Meta-Llama-3.1-405B-Instruct --tensor-parallel-size 8 --pipeline_parallel_size 2"
+                    vllm serve meta-llama/Meta-Llama-3.1-405B-Instruct --port 8080 --tensor-parallel-size 8 --pipeline_parallel_size 2"
                 resources:
                   limits:
                     nvidia.com/gpu: "8"
@@ -126,8 +126,6 @@ Should get an output similar to this:
 NAME       READY   STATUS    RESTARTS   AGE
 vllm-0     1/1     Running   0          2s
 vllm-0-1   1/1     Running   0          2s
-vllm-1     1/1     Running   0          2s
-vllm-1-1   1/1     Running   0          2s
 ```
 
 Verify that the distributed tensor-parallel inference works:
diff --git a/examples/online_serving/multi-node-serving.sh b/examples/online_serving/multi-node-serving.sh
index e8ad8d3de5f41..3fc5502fb9bc2 100644
--- a/examples/online_serving/multi-node-serving.sh
+++ b/examples/online_serving/multi-node-serving.sh
@@ -11,7 +11,7 @@
 # Example usage:
 # On the head node machine, start the Ray head node process and run a vLLM server.
 #   ./multi-node-serving.sh leader --ray_port=6379 --ray_cluster_size=<SIZE> [<extra ray args>]  && \
-#   python3 -m vllm.entrypoints.openai.api_server --port 8080 --model meta-llama/Meta-Llama-3.1-405B-Instruct --tensor-parallel-size 8 --pipeline_parallel_size 2
+#   vllm serve meta-llama/Meta-Llama-3.1-405B-Instruct --port 8080 --tensor-parallel-size 8 --pipeline_parallel_size 2
 # 
 # On each worker node, start the Ray worker node process.
 #   ./multi-node-serving.sh worker --ray_address=<HEAD_NODE_IP> --ray_port=6379 [<extra ray args>]