Files
xc-llm-ascend/tests/e2e/multicard/2-cards/test_pipeline_parallel.py
wangxiyuan 6f7a81cd9f [CI] cleanup single/multi-card test (#5623)
1. speed up e2e light test.
2. create `2-cards` and `4-cards` folder in multicard
3. move ops to nightly
4. run test in Alphabetical Order

- vLLM version: v0.13.0
- vLLM main:
8be6432bda

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2026-01-07 14:13:34 +08:00

49 lines
1.7 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",
"deepseek-ai/DeepSeek-V2-Lite-Chat",
]
TENSOR_PARALLELS = [1]
PIPELINE_PARALLELS = [2]
DIST_EXECUTOR_BACKEND = ["mp", "ray"]
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)
@pytest.mark.parametrize("distributed_executor_backend", DIST_EXECUTOR_BACKEND)
def test_models_pp2(model: str, tp_size: int, pp_size: int,
distributed_executor_backend: str) -> None:
with VllmRunner(model,
tensor_parallel_size=tp_size,
pipeline_parallel_size=pp_size,
cudagraph_capture_sizes=[1, 2, 4, 8],
distributed_executor_backend=distributed_executor_backend,
gpu_memory_utilization=0.7) as vllm_model:
vllm_model.generate_greedy(prompts, 64)