diff --git a/.github/workflows/nightly_test_a2.yaml b/.github/workflows/nightly_test_a2.yaml
index 02fd67fe..55db7f5a 100644
--- a/.github/workflows/nightly_test_a2.yaml
+++ b/.github/workflows/nightly_test_a2.yaml
@@ -78,6 +78,9 @@ jobs:
           - name: multi-node-deepseek-dp
             config_file_path: DeepSeek-R1-W8A8-A2.yaml
             size: 2
+          - name: multi-node-qwen3-235b-dp
+            config_file_path: Qwen3-235B-A22B-A2.yaml
+            size: 2
     uses: ./.github/workflows/_e2e_nightly_multi_node.yaml
     with:
       soc_version: a2
diff --git a/tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A22B-A2.yaml b/tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A22B-A2.yaml
new file mode 100644
index 00000000..d56f00fb
--- /dev/null
+++ b/tests/e2e/nightly/multi_node/config/models/Qwen3-235B-A22B-A2.yaml
@@ -0,0 +1,72 @@
+test_name: "test Qwen3-235B-A22B multi-dp on A2"
+model: "Qwen/Qwen3-235B-A22B"
+num_nodes: 2
+npu_per_node: 8
+env_common:
+  VLLM_USE_MODELSCOPE: true
+  OMP_PROC_BIND: false
+  OMP_NUM_THREADS: 1
+  HCCL_BUFFSIZE: 1024
+  SERVER_PORT: 8080
+  NUMEXPR_MAX_THREADS: 128
+  TASK_QUEUE_ENABLE: 1
+  PYTORCH_NPU_ALLOC_CONF: expandable_segments:True
+
+deployment:
+  -
+    server_cmd: >
+        vllm serve "Qwen/Qwen3-235B-A22B"
+        --host 0.0.0.0
+        --port $SERVER_PORT
+        --data-parallel-size 2
+        --data-parallel-size-local 1
+        --data-parallel-address $LOCAL_IP
+        --data-parallel-rpc-port 13389
+        --tensor-parallel-size 8
+        --seed 1024
+        --enable-expert-parallel
+        --max-num-seqs 128
+        --max-model-len 40960
+        --max-num-batched-tokens 256
+        --trust-remote-code
+        --gpu-memory-utilization 0.9
+        --async-scheduling
+  -
+    server_cmd: >
+        vllm serve "Qwen/Qwen3-235B-A22B"
+        --headless
+        --data-parallel-size 2
+        --data-parallel-size-local 1
+        --data-parallel-start-rank 1
+        --data-parallel-address $MASTER_IP
+        --data-parallel-rpc-port 13389
+        --tensor-parallel-size 8
+        --seed 1024
+        --max-num-seqs 128
+        --max-model-len 40960
+        --max-num-batched-tokens 256
+        --enable-expert-parallel
+        --trust-remote-code
+        --gpu-memory-utilization 0.9
+        --async-scheduling
+benchmarks:
+  perf:
+    case_type: performance
+    dataset_path: vllm-ascend/GSM8K-in3500-bs2800
+    request_conf: vllm_api_stream_chat
+    dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_str_perf
+    num_prompts: 2800
+    max_out_len: 1500
+    batch_size: 256
+    request_rate: 4.8
+    baseline: 1
+    threshold: 0.97
+  acc:
+    case_type: accuracy
+    dataset_path: vllm-ascend/gsm8k-lite
+    request_conf: vllm_api_general_chat
+    dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_chat_prompt
+    max_out_len: 7680
+    batch_size: 256
+    baseline: 96
+    threshold: 5