787010a637
V1 is enabled by default, no need to set it by hand now. This PR remove
the useless setting in example and tests
- vLLM version: v0.9.2
- vLLM main:
9ad0a4588b
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
44 lines
1.4 KiB
Python
44 lines
1.4 KiB
Python
# 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.
|
|
#
|
|
import pytest
|
|
|
|
from tests.e2e.conftest import VllmRunner
|
|
|
|
MODELS = [
|
|
"Qwen/Qwen3-0.6B",
|
|
]
|
|
|
|
TENSOR_PARALLELS = [2]
|
|
PIPELINE_PARALLELS = [2]
|
|
|
|
prompts = [
|
|
"Hello, my name is",
|
|
"The future of AI is",
|
|
]
|
|
|
|
|
|
@pytest.mark.parametrize("model", MODELS)
|
|
@pytest.mark.parametrize("tp_size", TENSOR_PARALLELS)
|
|
@pytest.mark.parametrize("pp_size", PIPELINE_PARALLELS)
|
|
def test_models(model: str, tp_size: int, pp_size: int) -> None:
|
|
with VllmRunner(model,
|
|
tensor_parallel_size=tp_size,
|
|
pipeline_parallel_size=pp_size,
|
|
enforce_eager=True,
|
|
gpu_memory_utilization=0.7) as vllm_model:
|
|
vllm_model.generate_greedy(prompts, 64)
|