f6e5decc10
Upgrade to vllm 0.9.0. 0.8.5 will not be supported any more. Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
108 lines
3.8 KiB
YAML
108 lines
3.8 KiB
YAML
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
# 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.
|
|
#
|
|
name: 'e2e test / pd-disaggregation'
|
|
|
|
on:
|
|
schedule:
|
|
# Runs at 23:00 UTC (7:00 AM Beijing) every day
|
|
- cron: '0 23 * * *'
|
|
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}
|
|
|
|
concurrency:
|
|
group: pr-${{ github.event.pull_request.number }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
prefilling-decoding-disaggregation:
|
|
# pd-test will be triggered when tag 'pd-test' & 'ready-for-test' or schedule job
|
|
if: ${{ contains(github.event.pull_request.labels.*.name, 'pd-test') && contains(github.event.pull_request.labels.*.name, 'ready-for-test') || github.event_name == 'schedule' }}
|
|
strategy:
|
|
matrix:
|
|
vllm_verison: [main, v0.9.0]
|
|
name: vLLM Ascend prefilling decoding disaggregation test
|
|
runs-on: linux-arm64-npu-static-8
|
|
|
|
container:
|
|
image: m.daocloud.io/quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10
|
|
volumes:
|
|
- /usr/local/dcmi:/usr/local/dcmi
|
|
- /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
|
|
- /usr/local/Ascend/driver/:/usr/local/Ascend/driver/
|
|
# Use self-host cache speed up pip and model download
|
|
- /home/action/.cache:/github/home/.cache/
|
|
options: >-
|
|
--device /dev/davinci0
|
|
--device /dev/davinci1
|
|
--device /dev/davinci2
|
|
--device /dev/davinci3
|
|
--device /dev/davinci4
|
|
--device /dev/davinci5
|
|
--device /dev/davinci6
|
|
--device /dev/davinci7
|
|
--device /dev/davinci_manager
|
|
--device /dev/devmm_svm
|
|
--device /dev/hisi_hdc
|
|
env:
|
|
HF_ENDPOINT: https://hf-mirror.com
|
|
HF_TOKEN: ${{ secrets.HF_TOKEN }}
|
|
steps:
|
|
- name: Check npu and CANN info
|
|
run: |
|
|
npu-smi info
|
|
cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
|
|
|
|
- name: Config mirrors
|
|
run: |
|
|
sed -i 's|ports.ubuntu.com|mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list
|
|
pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
|
|
apt-get update -y
|
|
apt install git -y
|
|
git config --global url."https://gh-proxy.test.osinfra.cn/https://github.com/".insteadOf https://github.com/
|
|
|
|
- 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 gcc g++ cmake libnuma-dev
|
|
|
|
- name: Checkout vllm-project/vllm repo
|
|
uses: actions/checkout@v4
|
|
with:
|
|
repository: vllm-project/vllm
|
|
ref: ${{ matrix.vllm_verison }}
|
|
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: |
|
|
pip install -r requirements-dev.txt
|
|
pip install -v -e .
|