Enable pytest and yaml style accuracy test #33
Workflow file for this run
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # | |
| # 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. | |
| # This test will be triggered: | |
| # 1. PR labeled with: '*accuracy-test' (ONLY 1 label valid) & 'ready-for-test' | |
| # 2. workflow_dispatch with models input | |
| # See detail rule in strategy.matrix note | |
| name: Benchmarks / accuracy / new | |
| on: | |
| schedule: | |
| # Runs every 6 hours | |
| - cron: '0 */6 * * *' | |
| # Remove this | |
| push: | |
| branches: [ acc-test ] | |
| pull_request: | |
| types: [ labeled ] | |
| workflow_dispatch: | |
| inputs: | |
| vllm-ascend-version: | |
| description: 'vllm-ascend:' | |
| required: true | |
| type: choice | |
| # Please also update this when bump matched version | |
| # Current supported vLLM versions | |
| options: | |
| - latest | |
| - main | |
| default: main | |
| # 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 | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| accuracy_tests: | |
| # test will be triggered when tag '*-accuracy-test' & 'ready-for-test' or workflow_dispatch job | |
| if: >- | |
| ${{ | |
| contains(github.event.pull_request.labels.*.name, 'accuracy-new-test') && | |
| contains(github.event.pull_request.labels.*.name, 'ready-for-test') || | |
| github.event_name == 'workflow_dispatch' || github.event_name == 'schedule' | |
| }} | |
| runs-on: ${{ matrix.runner }} | |
| strategy: | |
| matrix: | |
| include: | |
| - model_name: Qwen3-8B-Base | |
| runner: linux-aarch64-a2-1 | |
| - model_name: Qwen2.5-VL-7B-Instruct | |
| runner: linux-aarch64-a2-1 | |
| fail-fast: false | |
| name: ${{ matrix.model_name }} accuracy | |
| container: | |
| image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11 | |
| env: | |
| DATASET_SOURCE: ModelScope | |
| VLLM_USE_MODELSCOPE: True | |
| USE_MODELSCOPE_HUB: 1 | |
| # 1. If version specified (work_dispatch), do specified branch accuracy test | |
| # 2. If no version (labeled PR), do accuracy test by default ref: | |
| # The branch, tag or SHA to checkout. When checking out the repository that | |
| # triggered a workflow, this defaults to the reference or SHA for that event. | |
| # Otherwise, uses the default branch. | |
| GHA_VLLM_ASCEND_VERSION: ${{ github.event.inputs.vllm-ascend-version }} | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v4 | |
| - name: Check npu and CANN info | |
| run: | | |
| npu-smi info | |
| cat /usr/local/Ascend/ascend-toolkit/latest/"$(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: 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: v0.10.0 | |
| path: ./vllm-empty | |
| - name: Install vllm-project/vllm from source | |
| working-directory: ./vllm-empty | |
| run: | | |
| VLLM_TARGET_DEVICE=empty pip install -e . | |
| - name: Resolve vllm-ascend version | |
| run: | | |
| VERSION_INPUT="${{ github.event.inputs.vllm-ascend-version }}" | |
| if [[ "$VERSION_INPUT" == "latest" ]]; then | |
| TAGS=$(git ls-remote --tags --sort=-v:refname https://github.com/vllm-project/vllm-ascend "v*" | cut -f2 | sed 's|refs/tags/||') | |
| LATEST_TAG=$(echo "$TAGS" | head -n1) | |
| if [[ -z "$LATEST_TAG" ]]; then | |
| RESOLVED_VERSION="main" | |
| else | |
| RESOLVED_VERSION="$LATEST_TAG" | |
| fi | |
| else | |
| RESOLVED_VERSION="$VERSION_INPUT" | |
| fi | |
| echo "GHA_VLLM_ASCEND_VERSION=$RESOLVED_VERSION" >> $GITHUB_ENV | |
| - name: Checkout vllm-project/vllm-ascend repo | |
| uses: actions/checkout@v4 | |
| with: | |
| repository: vllm-project/vllm-ascend | |
| path: ./vllm-ascend | |
| ref: ${{ env.GHA_VLLM_ASCEND_VERSION }} | |
| - name: Install vllm-project/vllm-ascend | |
| working-directory: ./vllm-ascend | |
| env: | |
| PIP_EXTRA_INDEX_URL: https://mirrors.huaweicloud.com/ascend/repos/pypi | |
| run: | | |
| pip install -r requirements-dev.txt | |
| pip install -v -e . | |
| - name: Get vLLM commit hash and URL | |
| working-directory: ./vllm-empty | |
| run: | | |
| VLLM_COMMIT=$(git rev-parse --short=7 HEAD) | |
| echo "VLLM_COMMIT=$VLLM_COMMIT" >> $GITHUB_ENV | |
| - name: Get vLLM-Ascend commit hash and URL | |
| working-directory: ./vllm-ascend | |
| run: | | |
| VLLM_ASCEND_COMMIT=$(git rev-parse --short=7 HEAD) | |
| echo "VLLM_ASCEND_COMMIT=$VLLM_ASCEND_COMMIT" >> $GITHUB_ENV | |
| - name: Collect version info | |
| run: | | |
| for dir in /usr/local/Ascend/ascend-toolkit/*; do | |
| dname=$(basename "$dir") | |
| if [ "$dname" != "latest" ]; then | |
| TOOLKIT_DIR="$dname" | |
| break | |
| fi | |
| done | |
| INFO_FILE="/usr/local/Ascend/ascend-toolkit/${TOOLKIT_DIR}/$(uname -i)-linux/ascend_toolkit_install.info" | |
| GHA_CANN_VERSION=$(grep "version=" "$INFO_FILE" \ | |
| | head -n1 \ | |
| | cut -d'=' -f2 \ | |
| | tr -d '"') | |
| { | |
| echo "GHA_CANN_VERSION=$GHA_CANN_VERSION" | |
| pip show torch | grep "Version:" | awk '{print "GHA_TORCH_VERSION="$2}' | |
| pip show torch_npu | grep "Version:" | awk '{print "GHA_TORCH_NPU_VERSION="$2}' | |
| pip show vllm | grep "Version:" | awk '{print "GHA_VLLM_VERSION="$2}' | sed 's/+.*//' | |
| } >> "$GITHUB_ENV" | |
| - name: Run accuracy test | |
| env: | |
| VLLM_WORKER_MULTIPROC_METHOD: spawn | |
| VLLM_USE_MODELSCOPE: True | |
| VLLM_VERSION: ${{ env.GHA_VLLM_VERSION }} | |
| VLLM_COMMIT: ${{ env.VLLM_COMMIT }} | |
| VLLM_ASCEND_VERSION: ${{ env.GHA_VLLM_ASCEND_VERSION || github.ref }} | |
| VLLM_ASCEND_COMMIT: ${{ env.VLLM_ASCEND_COMMIT }} | |
| CANN_VERSION: ${{ env.GHA_CANN_VERSION }} | |
| TORCH_VERSION: ${{ env.GHA_TORCH_VERSION }} | |
| TORCH_NPU_VERSION: ${{ env.GHA_TORCH_NPU_VERSION }} | |
| run: | | |
| model_base_name=$(basename ${{ matrix.model_name }}) | |
| mkdir -p ./benchmarks/accuracy | |
| cd tests/e2e/singlecard/models/ | |
| pip install lm-eval==0.4.8 | |
| pytest -sv test_lm_eval_correctness.py \ | |
| --config configs/${{ matrix.model_name }}.yaml \ | |
| --report_template report_template.md \ | |
| --report_output ./benchmarks/accuracy/${model_base_name}_accuracy.md |