diff --git a/docs/vllm_mindspore/docs/source_en/getting_started/tutorials/deepseek_parallel/deepseek_r1_671b_w8a8_dp4_tp4_ep4.md b/docs/vllm_mindspore/docs/source_en/getting_started/tutorials/deepseek_parallel/deepseek_r1_671b_w8a8_dp4_tp4_ep4.md
index cb7a0d2945a2deb3ed60a83d36fd8a89a8477e66..0a786c659c0ed5614188466ebb25e5909ea71b65 100644
--- a/docs/vllm_mindspore/docs/source_en/getting_started/tutorials/deepseek_parallel/deepseek_r1_671b_w8a8_dp4_tp4_ep4.md
+++ b/docs/vllm_mindspore/docs/source_en/getting_started/tutorials/deepseek_parallel/deepseek_r1_671b_w8a8_dp4_tp4_ep4.md
@@ -242,10 +242,10 @@ The Ascend runtime package can be downloaded from the Ascend homepage. For examp
 
 Before managing a multi-node cluster, check that the hostnames of all nodes are different. If any are the same, set different hostnames using `hostname <new-host-name>`.
 
-1. Start the head node: `ray start --head --port=<port-to-ray>`. Upon successful startup, the connection method for worker nodes will be displayed. For example, in an environment with IP `192.5.5.5`, running `ray start --head --port=6379` will prompt:
+1. Start the head node: `ray start --head --port=<port-to-ray>`. Upon successful startup, the connection method for worker nodes will be displayed. Configure as follows, replacing `IP` and `address` with the actual environment information.
 
   ```text
-  Local node IP: 192.5.5.5
+  Local node IP: *.*.*.*
 
   -------------------
   Ray runtime started.
@@ -253,7 +253,7 @@ Before managing a multi-node cluster, check that the hostnames of all nodes are
 
   Next steps
     To add another node to this Ray cluster, run
-      ray start --address='192.5.5.5:6379'
+      ray start --address='*.*.*.*:*'
 
     To connect to this Ray cluster:
       import ray
diff --git a/docs/vllm_mindspore/docs/source_en/user_guide/supported_features/parallel/parallel.md b/docs/vllm_mindspore/docs/source_en/user_guide/supported_features/parallel/parallel.md
index f734fb1fe2b6953089ff705b3c635239453c01bd..7d529f196cbb33e3968cc6c4f7f736a37d096000 100644
--- a/docs/vllm_mindspore/docs/source_en/user_guide/supported_features/parallel/parallel.md
+++ b/docs/vllm_mindspore/docs/source_en/user_guide/supported_features/parallel/parallel.md
@@ -163,10 +163,10 @@ The Ascend runtime package can be downloaded from the Ascend homepage. For examp
 
 Before managing a multi-node cluster, check that the hostnames of all nodes are different. If any are the same, set different hostnames using `hostname <new-host-name>`.
 
-1. Start the head node: `ray start --head --port=<port-to-ray>`. Upon successful startup, the connection method for worker nodes will be displayed. For example, in an environment with IP `192.5.5.5`, running `ray start --head --port=6379` will prompt:
+1. Start the head node: `ray start --head --port=<port-to-ray>`. Upon successful startup, the connection method for worker nodes will be displayed. Configure as follows, replacing `IP` and `address` with the actual environment information.
 
   ```text
-  Local node IP: 192.5.5.5
+  Local node IP: *.*.*.*
 
   -------------------
   Ray runtime started.
@@ -174,7 +174,7 @@ Before managing a multi-node cluster, check that the hostnames of all nodes are
 
   Next steps
     To add another node to this Ray cluster, run
-      ray start --address='192.5.5.5:6379'
+      ray start --address='*.*.*.*:*'
 
     To connect to this Ray cluster:
       import ray
@@ -296,12 +296,14 @@ The following are execution examples for the multiprocess and Ray startup method
 
 ```bash
 # Master Node:
-vllm-mindspore serve MindSpore-Lab/DeepSeek-R1-0528-A8W8 --trust-remote-code --max-num-seqs=256 --max-model-len=32768 --max-num-batched-tokens=4096 --block-size=128 --gpu-memory-utilization=0.9 --tensor-parallel-size 4 --data-parallel-size 4 --data-parallel-size-local 2 --data-parallel-start-rank 0 --data-parallel-address 192.10.10.10 --data-parallel-rpc-port 12370 --enable-expert-parallel --addition-config '{"data_parallel": 4, "model_parallel": 4, "expert_parallel": 4}'
+vllm-mindspore serve MindSpore-Lab/DeepSeek-R1-0528-A8W8 --trust-remote-code --max-num-seqs=256 --max-model-len=32768 --max-num-batched-tokens=4096 --block-size=128 --gpu-memory-utilization=0.9 --tensor-parallel-size 4 --data-parallel-size 4 --data-parallel-size-local 2 --data-parallel-start-rank 0 --data-parallel-address 127.0.0.1 --data-parallel-rpc-port 29550 --enable-expert-parallel --addition-config '{"data_parallel": 4, "model_parallel": 4, "expert_parallel": 4}'
 
 # Worker Node:
-vllm-mindspore serve MindSpore-Lab/DeepSeek-R1-0528-A8W8 --headless --trust-remote-code --max-num-seqs=256 --max-model-len=32768 --max-num-batched-tokens=4096 --block-size=128 --gpu-memory-utilization=0.9 --tensor-parallel-size 4 --data-parallel-size 4 --data-parallel-size-local 2 --data-parallel-start-rank 2 --data-parallel-address 192.10.10.10 --data-parallel-rpc-port 12370 --enable-expert-parallel --addition-config '{"data_parallel": 4, "model_parallel": 4, "expert_parallel": 4}'
+vllm-mindspore serve MindSpore-Lab/DeepSeek-R1-0528-A8W8 --headless --trust-remote-code --max-num-seqs=256 --max-model-len=32768 --max-num-batched-tokens=4096 --block-size=128 --gpu-memory-utilization=0.9 --tensor-parallel-size 4 --data-parallel-size 4 --data-parallel-size-local 2 --data-parallel-start-rank 2 --data-parallel-address 127.0.0.1 --data-parallel-rpc-port 29550 --enable-expert-parallel --addition-config '{"data_parallel": 4, "model_parallel": 4, "expert_parallel": 4}'
 ```
 
+Specifically, `data-parallel-address` and `--data-parallel-rpc-port` must be configured with the actual environment information for the running instance.
+
 **Ray Startup Method**
 
 ```bash
diff --git a/docs/vllm_mindspore/docs/source_zh_cn/getting_started/tutorials/deepseek_parallel/deepseek_r1_671b_w8a8_dp4_tp4_ep4.md b/docs/vllm_mindspore/docs/source_zh_cn/getting_started/tutorials/deepseek_parallel/deepseek_r1_671b_w8a8_dp4_tp4_ep4.md
index cd7967a4bf429384ccfe02aa2a71672972bdaf29..8f509ca66d242d6eab1010f7d8a246be7c4e000d 100644
--- a/docs/vllm_mindspore/docs/source_zh_cn/getting_started/tutorials/deepseek_parallel/deepseek_r1_671b_w8a8_dp4_tp4_ep4.md
+++ b/docs/vllm_mindspore/docs/source_zh_cn/getting_started/tutorials/deepseek_parallel/deepseek_r1_671b_w8a8_dp4_tp4_ep4.md
@@ -242,10 +242,10 @@ chmod -R 777 ./Ascend-pyACL_8.0.RC1_linux-aarch64.run
 
 多节点集群管理前，需要检查各节点的 hostname 是否各异。如果存在相同的，需要通过 `hostname <new-host-name>` 设置不同的 hostname。
 
-1. 启动主节点 `ray start --head --port=<port-to-ray>`。启动成功后，会提示从节点的连接方式。例如，在 IP 为 `192.5.5.5` 的环境中，通过 `ray start --head --port=6379`，提示如下：
+1. 启动主节点 `ray start --head --port=<port-to-ray>`。启动成功后，会提示从节点的连接方式。配置方式如下，其中`IP`和`address`需要修改成实际运行的环境信息。
 
   ```text
-  Local node IP: 192.5.5.5
+  Local node IP: *.*.*.*
 
   --------------------
   Ray runtime started.
@@ -253,7 +253,7 @@ chmod -R 777 ./Ascend-pyACL_8.0.RC1_linux-aarch64.run
 
   Next steps
    To add another node to this Ray cluster, run
-     ray start --address='192.5.5.5:6379'
+     ray start --address='*.*.*.*:*'
 
      To connect to this Ray cluster:
       import ray
diff --git a/docs/vllm_mindspore/docs/source_zh_cn/user_guide/supported_features/parallel/parallel.md b/docs/vllm_mindspore/docs/source_zh_cn/user_guide/supported_features/parallel/parallel.md
index 9c652b1e1e6e01b3bdddef2d9f97fdde8888f63e..359cf45f81786b3294c8fb1503fc8a5f3954fa3b 100644
--- a/docs/vllm_mindspore/docs/source_zh_cn/user_guide/supported_features/parallel/parallel.md
+++ b/docs/vllm_mindspore/docs/source_zh_cn/user_guide/supported_features/parallel/parallel.md
@@ -163,10 +163,10 @@ chmod -R 777 ./Ascend-pyACL_8.0.RC1_linux-aarch64.run
 
 多节点集群管理前，需要检查各节点的 hostname 是否各异。如果存在相同的，需要通过 `hostname <new-host-name>` 设置不同的 hostname。
 
-1. 启动主节点 `ray start --head --port=<port-to-ray>`，启动成功后，会提示从节点的连接方式。如在 IP 为 `192.5.5.5` 的环境中，通过 `ray start --head --port=6379`，提示如下：
+1. 启动主节点 `ray start --head --port=<port-to-ray>`，启动成功后，会提示从节点的连接方式。配置方式如下，其中`IP`和`address`需要修改成实际运行的环境信息。
 
   ```text
-  Local node IP: 192.5.5.5
+  Local node IP: *.*.*.*
 
   -------------------
   Ray runtime started.
@@ -174,7 +174,7 @@ chmod -R 777 ./Ascend-pyACL_8.0.RC1_linux-aarch64.run
 
   Next steps
     To add another node to this Ray cluster, run
-      ray start --address='192.5.5.5:6379'
+      ray start --address='*.*.*.*:*'
 
     To connect to this Ray cluster:
       import ray
@@ -297,12 +297,14 @@ vllm-mindspore serve
 
 ```bash
 # 主节点：
-vllm-mindspore serve MindSpore-Lab/DeepSeek-R1-0528-A8W8 --trust-remote-code --max-num-seqs=256 --max-model-len=32768 --max-num-batched-tokens=4096 --block-size=128 --gpu-memory-utilization=0.9 --tensor-parallel-size 4 --data-parallel-size 4 --data-parallel-size-local 2 --data-parallel-start-rank 0 --data-parallel-address 192.10.10.10 --data-parallel-rpc-port 12370 --enable-expert-parallel --addition-config '{"data_parallel": 4, "model_parallel": 4, "expert_parallel": 4}'
+vllm-mindspore serve MindSpore-Lab/DeepSeek-R1-0528-A8W8 --trust-remote-code --max-num-seqs=256 --max-model-len=32768 --max-num-batched-tokens=4096 --block-size=128 --gpu-memory-utilization=0.9 --tensor-parallel-size 4 --data-parallel-size 4 --data-parallel-size-local 2 --data-parallel-start-rank 0 --data-parallel-address 127.0.0.1 --data-parallel-rpc-port 29550 --enable-expert-parallel --addition-config '{"data_parallel": 4, "model_parallel": 4, "expert_parallel": 4}'
 
 # 从节点：
-vllm-mindspore serve MindSpore-Lab/DeepSeek-R1-0528-A8W8 --headless --trust-remote-code --max-num-seqs=256 --max-model-len=32768 --max-num-batched-tokens=4096 --block-size=128 --gpu-memory-utilization=0.9 --tensor-parallel-size 4 --data-parallel-size 4 --data-parallel-size-local 2 --data-parallel-start-rank 2 --data-parallel-address 192.10.10.10 --data-parallel-rpc-port 12370 --enable-expert-parallel --addition-config '{"data_parallel": 4, "model_parallel": 4, "expert_parallel": 4}'
+vllm-mindspore serve MindSpore-Lab/DeepSeek-R1-0528-A8W8 --headless --trust-remote-code --max-num-seqs=256 --max-model-len=32768 --max-num-batched-tokens=4096 --block-size=128 --gpu-memory-utilization=0.9 --tensor-parallel-size 4 --data-parallel-size 4 --data-parallel-size-local 2 --data-parallel-start-rank 2 --data-parallel-address 127.0.0.1 --data-parallel-rpc-port 29550 --enable-expert-parallel --addition-config '{"data_parallel": 4, "model_parallel": 4, "expert_parallel": 4}'
 ```
 
+其中，`data-parallel-address`和`--data-parallel-rpc-port`需要设置成实际运行的环境信息。
+
 **Ray启动方式**
 
 ```bash