add st:qwen3

Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>

Author: weijinqian_v1

tests/multicard/test_qwen3_moe.py

@@ -0,0 +1,71 @@
+
+# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
+# Copyright 2023 The vLLM team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# This file is a part of the vllm-ascend project.
+#
+"""
+Compare the outputs of vLLM with and without aclgraph.
+Run `pytest tests/multicard/test_data_parallel.py`.
+"""
+
+import os
+import subprocess
+import sys
+from unittest.mock import patch
+
+import pytest
+
+MODELS = ["vllm-ascend/Qwen3-30B-A3B-Puring"]
+
+
+@pytest.mark.parametrize("model", MODELS)
+@pytest.mark.parametrize("max_tokens", [32])
+@patch.dict(os.environ, {"ASCEND_RT_VISIBLE_DEVICES": "0,1,2,3", "VLLM_ASCEND_ENABLE_MOE_ALL2ALL_SEQ": "1", "VLLM_ASCEND_ENABLE_DBO": "1"})
+def test_qwen3_moe_inference(model, max_tokens):
+    script = "examples/offline_data_parallel.py"
+
+    env = os.environ.copy()
+
+    cmd = [
+        sys.executable,
+        script,
+        "--model",
+        model,
+        "--dp-size",
+        "2",
+        "--tp-size",
+        "2",
+        "--node-size",
+        "1",
+        "--node-rank",
+        "0",
+        "--trust-remote-code",
+        "--enforce-eager",
+    ]
+
+    print(f"Running subprocess: {' '.join(cmd)}")
+    proc = subprocess.run(cmd,
+                          env=env,
+                          stdout=subprocess.PIPE,
+                          stderr=subprocess.STDOUT,
+                          timeout=600)
+    output = proc.stdout.decode()
+
+    print(output)
+
+    assert "DP rank 0 needs to process" in output
+    assert "DP rank 1 needs to process" in output
+    assert "Generated text:" in output
+    assert proc.returncode == 0

tests/singlecard/test_offline_inference.py

@@ -132,23 +132,3 @@ def test_models_topk() -> None:
                     gpu_memory_utilization=0.7) as vllm_model:
         vllm_model.generate(example_prompts, sampling_params)
 
-
-@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_MOE_ALL2ALL_SEQ": "1", "VLLM_ASCEND_ENABLE_DBO": "1"})
-def test_models_topk() -> None:
-    example_prompts = [
-        "Hello, my name is",
-        "The president of the United States is",
-        "The capital of France is",
-        "The future of AI is",
-    ]
-    sampling_params = SamplingParams(max_tokens=5,
-                                     temperature=0.0,
-                                     top_k=50,
-                                     top_p=0.9)
-
-    with VllmRunner("Qwen/Qwen2.5-0.5B-Instruct",
-                    max_model_len=8192,
-                    dtype="float16",
-                    enforce_eager=True,
-                    gpu_memory_utilization=0.7) as vllm_model:
-        vllm_model.generate(example_prompts, sampling_params)