fef18b60bc
Refactor E2E CI to make it clear and faster
1. remove some uesless e2e test
2. remove some uesless function
3. Make sure all test runs with VLLMRunner to avoid oom error
4. Make sure all ops test end with torch.empty_cache to avoid oom error
5. run the test one by one to avoid resource limit error
- vLLM version: v0.10.1.1
- vLLM main:
a344a5aa0a
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
118 lines
4.2 KiB
YAML
118 lines
4.2 KiB
YAML
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
#
|
|
# 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.
|
|
#
|
|
|
|
name: 'e2e test / 310p-test'
|
|
|
|
on:
|
|
push:
|
|
tags:
|
|
- 'v*'
|
|
schedule:
|
|
# Runs every 6 hours
|
|
- cron: '0 */6 * * *'
|
|
pull_request:
|
|
types: [ labeled ]
|
|
|
|
# Bash shells do not use ~/.profile or ~/.bashrc so these shells need to be explicitly
|
|
# declared as "shell: bash -el {0}" on steps that need to be properly activated.
|
|
# It's used to activate ascend-toolkit environment variables.
|
|
defaults:
|
|
run:
|
|
shell: bash -el {0}
|
|
|
|
# only cancel in-progress runs of the same workflow
|
|
# and ignore the lint / 1 card / 4 cards test type
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
e2e:
|
|
# e2e-310p-test will be triggered when tag 'e2e-310p-test' & 'ready-for-test' or schedule job
|
|
if: >-
|
|
${{
|
|
(contains(github.event.pull_request.labels.*.name, 'e2e-310p-test')) &&
|
|
contains(github.event.pull_request.labels.*.name, 'ready-for-test') ||
|
|
github.event_name == 'schedule' || github.event_name == 'push'
|
|
}}
|
|
strategy:
|
|
max-parallel: 2
|
|
matrix:
|
|
os: [linux-aarch64-310p-1, linux-aarch64-310p-4]
|
|
vllm_version: [v0.10.1.1, main]
|
|
name: 310p e2e test
|
|
runs-on: ${{ matrix.os }}
|
|
container:
|
|
# TODO(yikun): Remove m.daocloud.io prefix when infra proxy ready
|
|
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-310p-ubuntu22.04-py3.11
|
|
env:
|
|
VLLM_LOGGING_LEVEL: ERROR
|
|
VLLM_USE_MODELSCOPE: True
|
|
steps:
|
|
- name: Check npu and CANN info
|
|
run: |
|
|
npu-smi info
|
|
cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
|
|
|
|
- name: Config mirrors
|
|
run: |
|
|
sed -Ei 's@(ports|archive).ubuntu.com@cache-service.nginx-pypi-cache.svc.cluster.local:8081@g' /etc/apt/sources.list
|
|
pip config set global.index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple
|
|
pip config set global.trusted-host cache-service.nginx-pypi-cache.svc.cluster.local
|
|
apt-get update -y
|
|
apt install git -y
|
|
|
|
- name: Checkout vllm-project/vllm-ascend repo
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Install system dependencies
|
|
run: |
|
|
apt-get -y install `cat packages.txt`
|
|
apt-get -y install git vim wget net-tools gcc g++ cmake libnuma-dev curl gnupg2
|
|
|
|
- name: Checkout vllm-project/vllm repo
|
|
uses: actions/checkout@v4
|
|
with:
|
|
repository: vllm-project/vllm
|
|
ref: ${{ matrix.vllm_version }}
|
|
path: ./vllm-empty
|
|
|
|
- name: Install vllm-project/vllm from source
|
|
working-directory: ./vllm-empty
|
|
run: |
|
|
VLLM_TARGET_DEVICE=empty pip install -e .
|
|
|
|
- name: Install vllm-project/vllm-ascend
|
|
run: |
|
|
export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
|
|
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/x86_64-linux/devlib
|
|
export SOC_VERSION=ASCEND310P3
|
|
pip install -r requirements-dev.txt
|
|
pip install -v -e .
|
|
|
|
- name: Run e2e test
|
|
env:
|
|
VLLM_WORKER_MULTIPROC_METHOD: spawn
|
|
VLLM_USE_MODELSCOPE: True
|
|
PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
|
|
run: |
|
|
if [[ "${{ matrix.os }}" == "linux-aarch64-310p-1" ]]; then
|
|
pytest -sv tests/e2e/310p/test_offline_inference_310p.py
|
|
else
|
|
pytest -sv tests/e2e/310p/test_offline_inference_parallel_310p.py
|
|
fi
|