Skip to content

[V0.7.3][LoRA][Qwen3] Make v0.7.3 support Qwen3+LoRA #2991

[V0.7.3][LoRA][Qwen3] Make v0.7.3 support Qwen3+LoRA

[V0.7.3][LoRA][Qwen3] Make v0.7.3 support Qwen3+LoRA #2991

#
# 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'
on:
pull_request:
branches:
- 'main'
- '*-dev'
paths:
- '*.txt'
- '**/*.py'
- '.github/workflows/vllm_ascend_test.yaml'
- '!docs/**'
- 'pytest.ini'
# 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:
test:
name: vLLM Ascend test v0.7.3-dev
runs-on: linux-arm64-npu-1
container:
# TODO(yikun): Remove m.daocloud.io prefix when infra proxy ready
image: m.daocloud.io/quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10
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 --add safe.directory "$GITHUB_WORKSPACE"
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: v0.7.3
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 -e .
- name: Run vllm-project/vllm-ascend e2e test
run: |
pytest -sv tests/test_offline_inference.py
# only run test on spec decode when the related code changed
- name: Check for changes in Speculative Decode
id: filter
uses: dorny/paths-filter@v2
with:
filters: |
speculative_tests_changed:
- "tests/spec_decode/**"
- "vllm_ascend/worker/multi_step_runner.py"
- "vllm_ascend/worker/multi_step_worker.py"
- "vllm_ascend/patch/patch_rejection_sampler.py"
- "vllm_ascend/patch/patch_spec_decode_worker.py"
- "vllm_ascend/patch/patch_multi_step_worker.py"
- name: Run vllm-project/vllm-ascend key feature test
if: steps.filter.outputs.speculative_tests_changed == 'true'
run: |
pytest -sv tests/spec_decode/e2e/test_mtp_correctness.py # it needs a clean process
pytest -sv tests/spec_decode/e2e/test_multistep_correctness.py # it needs a clean process
pytest -sv tests/spec_decode --ignore=tests/spec_decode/e2e/test_mtp_correctness.py --ignore=tests/spec_decode/e2e/test_multistep_correctness.py
- name: Run vllm-project/vllm test
run: |
pytest -sv