From f26983c8400188f3cc196ddfc3d301c0e3fbf459 Mon Sep 17 00:00:00 2001
From: leo-pony <nengjunma@outlook.com>
Date: Wed, 24 Sep 2025 17:42:52 +0800
Subject: [PATCH] Add OOT platform E2E test case to be run in the vllm
 buildkite pipeline

Signed-off-by: leo-pony <nengjunma@outlook.com>
---
 .../vllm_interface/singlecard/test_sampler.py | 36 +++++++++++++++++++
 tests/e2e/vllm_interface/vllm_test.cfg        |  2 ++
 2 files changed, 38 insertions(+)
 create mode 100644 tests/e2e/vllm_interface/singlecard/test_sampler.py
 create mode 100644 tests/e2e/vllm_interface/vllm_test.cfg

diff --git a/tests/e2e/vllm_interface/singlecard/test_sampler.py b/tests/e2e/vllm_interface/singlecard/test_sampler.py
new file mode 100644
index 0000000000..662e76e3e7
--- /dev/null
+++ b/tests/e2e/vllm_interface/singlecard/test_sampler.py
@@ -0,0 +1,36 @@
+#
+# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
+# This file is a part of the vllm-ascend project.
+# Adapted from vllm/tests/entrypoints/llm/test_guided_generate.py
+# 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.
+#
+from vllm import SamplingParams
+
+from tests.e2e.conftest import VllmRunner
+
+
+def test_models_topk() -> None:
+    example_prompts = [
+        "The capital of France is",
+    ]
+    sampling_params = SamplingParams(max_tokens=10,
+                                     temperature=0.0,
+                                     top_k=10,
+                                     top_p=0.9)
+
+    with VllmRunner("Qwen/Qwen3-0.6B",
+                    max_model_len=4096,
+                    gpu_memory_utilization=0.7) as runner:
+        runner.generate(example_prompts, sampling_params)
diff --git a/tests/e2e/vllm_interface/vllm_test.cfg b/tests/e2e/vllm_interface/vllm_test.cfg
new file mode 100644
index 0000000000..7029e20d98
--- /dev/null
+++ b/tests/e2e/vllm_interface/vllm_test.cfg
@@ -0,0 +1,2 @@
+# Base docker image used to build the vllm-ascend e2e test image, which is built in the vLLM repository
+BASE_IMAGE_NAME="quay.io/ascend/cann:8.3.rc1.alpha002-910b-ubuntu22.04-py3.11"