1+ #
2+ # Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
3+ #
4+ # Licensed under the Apache License, Version 2.0 (the "License");
5+ # you may not use this file except in compliance with the License.
6+ # You may obtain a copy of the License at
7+ #
8+ # http://www.apache.org/licenses/LICENSE-2.0
9+ #
10+ # Unless required by applicable law or agreed to in writing, software
11+ # distributed under the License is distributed on an "AS IS" BASIS,
12+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13+ # See the License for the specific language governing permissions and
14+ # limitations under the License.
15+ # This file is a part of the vllm-ascend project.
16+ #
17+
18+ name : ' e2e test / 310p-test'
19+
20+ on :
21+ push :
22+ tags :
23+ - ' v*'
24+ schedule :
25+ # Runs every 6 hours
26+ - cron : ' 0 */6 * * *'
27+ pull_request :
28+ types : [ labeled ]
29+
30+ # Bash shells do not use ~/.profile or ~/.bashrc so these shells need to be explicitly
31+ # declared as "shell: bash -el {0}" on steps that need to be properly activated.
32+ # It's used to activate ascend-toolkit environment variables.
33+ defaults :
34+ run :
35+ shell : bash -el {0}
36+
37+ # only cancel in-progress runs of the same workflow
38+ # and ignore the lint / 1 card / 4 cards test type
39+ concurrency :
40+ group : ${{ github.workflow }}-${{ github.ref }}
41+ cancel-in-progress : true
42+
43+ jobs :
44+ e2e :
45+ # e2e-310p-test will be triggered when tag 'e2e-310p-test' & 'ready-for-test' or schedule job
46+ if : >-
47+ ${{
48+ (contains(github.event.pull_request.labels.*.name, 'e2e-310p-test')) &&
49+ contains(github.event.pull_request.labels.*.name, 'ready-for-test') ||
50+ github.event_name == 'schedule' || github.event_name == 'push'
51+ }}
52+ strategy :
53+ max-parallel : 2
54+ matrix :
55+ os : [linux-aarch64-310p-1, linux-aarch64-310p-4]
56+ vllm_version : [main, v0.10.0]
57+ name : 310p e2e test
58+ runs-on : ${{ matrix.os }}
59+ container :
60+ # TODO(yikun): Remove m.daocloud.io prefix when infra proxy ready
61+ image : swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-310p-ubuntu22.04-py3.10
62+ env :
63+ VLLM_LOGGING_LEVEL : ERROR
64+ VLLM_USE_MODELSCOPE : True
65+ steps :
66+ - name : Check npu and CANN info
67+ run : |
68+ npu-smi info
69+ cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
70+
71+ name : Config mirrors
72+ run : |
73+ sed -Ei 's@(ports|archive)[email protected] :8081@g' /etc/apt/sources.list 74+ pip config set global.index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple
75+ pip config set global.trusted-host cache-service.nginx-pypi-cache.svc.cluster.local
76+ apt-get update -y
77+ apt install git -y
78+
79+ name : Checkout vllm-project/vllm-ascend repo
80+ uses : actions/checkout@v4
81+
82+ - name : Install system dependencies
83+ run : |
84+ apt-get -y install `cat packages.txt`
85+ apt-get -y install git vim wget net-tools gcc g++ cmake libnuma-dev curl gnupg2
86+
87+ name : Checkout vllm-project/vllm repo
88+ uses : actions/checkout@v4
89+ with :
90+ repository : vllm-project/vllm
91+ ref : ${{ matrix.vllm_version }}
92+ path : ./vllm-empty
93+
94+ - name : Install vllm-project/vllm from source
95+ working-directory : ./vllm-empty
96+ run : |
97+ VLLM_TARGET_DEVICE=empty pip install -e .
98+
99+ name : Install vllm-project/vllm-ascend
100+ run : |
101+ export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
102+ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/x86_64-linux/devlib
103+ export SOC_VERSION=ASCEND310P3
104+ pip install -r requirements-dev.txt
105+ pip install -v -e .
106+
107+ name : Run e2e test
108+ env :
109+ VLLM_WORKER_MULTIPROC_METHOD : spawn
110+ VLLM_USE_MODELSCOPE : True
111+ PYTORCH_NPU_ALLOC_CONF : max_split_size_mb:256
112+ run : |
113+ if [[ "${{ matrix.os }}" == "linux-aarch64-310p-1" ]]; then
114+ pytest -sv tests/e2e/singlecard/test_offline_inference_310p.py
115+ else
116+ pytest -sv tests/e2e/multicard/test_offline_inference_310p.py
117+ fi
0 commit comments