diff --git a/.github/workflows/_e2e_nightly.yaml b/.github/workflows/_e2e_nightly.yaml deleted file mode 100644 index 3caa6fe..0000000 --- a/.github/workflows/_e2e_nightly.yaml +++ /dev/null @@ -1,115 +0,0 @@ -# -# 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 nightly test' - -on: - workflow_call: - inputs: - vllm: - required: true - type: string - runner: - required: true - type: string - image: - required: false - type: string - default: "swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11" - tests: - required: true - type: string - -# 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-nightly: - name: e2e-nightly - runs-on: ${{ inputs.runner }} - container: - image: ${{ inputs.image }} - env: - VLLM_USE_MODELSCOPE: True - steps: - - name: Check npu and CANN info - run: | - npu-smi info - cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info - - - name: Config mirrors - run: | - sed -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: ${{ inputs.vllm }} - 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 - env: - PIP_EXTRA_INDEX_URL: https://mirrors.huaweicloud.com/ascend/repos/pypi - run: | - pip install -r requirements-dev.txt - pip install -v -e . - - - name: Checkout aisbench repo and Install aisbench - run: | - git clone https://gitee.com/aisbench/benchmark.git - cd benchmark - git checkout v3.0-20250930-master - pip3 install -e ./ - pip3 install -r requirements/api.txt - pip3 install -r requirements/extra.txt - - - name: Run vllm-project/vllm-ascend test - env: - VLLM_WORKER_MULTIPROC_METHOD: spawn - VLLM_USE_MODELSCOPE: True - VLLM_CI_RUNNER: ${{ inputs.runner }} - run: | - # TODO: enable more tests - pytest -sv ${{ inputs.tests }} diff --git a/.github/workflows/vllm_ascend_test_nightly.yaml b/.github/workflows/vllm_ascend_test_nightly.yaml deleted file mode 100644 index f4acd82..0000000 --- a/.github/workflows/vllm_ascend_test_nightly.yaml +++ /dev/null @@ -1,105 +0,0 @@ -# -# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved. -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. -# This file is a part of the vllm-ascend project. -# - -name: 'ascend test / nightly' - -on: - schedule: - # Run test at 24:00 Beijing time (UTC+8) - - cron: "0 16 * * *" - workflow_dispatch: - pull_request: - branches: - - 'main' - - '*-dev' - paths: - - 'tests/e2e/nightly/**' - - '.github/workflows/vllm_ascend_test_nightly.yaml' - -# Bash shells do not use ~/.profile or ~/.bashrc so these shells need to be explicitly -# declared as "shell: bash -el {0}" on steps that need to be properly activated. -# It's used to activate ascend-toolkit environment variables. -defaults: - run: - shell: bash -el {0} - -# only cancel in-progress runs of the same workflow -# and ignore the lint / 1 card / 4 cards test type -concurrency: - group: ascend-nightly-${{ github.ref }} - #cancel-in-progress: true - -jobs: - qwen3-32b: - strategy: - matrix: - # should add A3 chip runner when available - os: [linux-aarch64-a2-4] - # Note (yikun): If CI resource are limited we can split job into two chain jobs - # only trigger e2e test after lint passed and the change is e2e related with pull request. - uses: ./.github/workflows/_e2e_nightly.yaml - with: - vllm: v0.11.0 - runner: ${{ matrix.os }} - tests: tests/e2e/nightly/models/test_qwen3_32b.py - qwen3-32b-in8-a3: - strategy: - matrix: - os: [ linux-aarch64-a3-4 ] - uses: ./.github/workflows/_e2e_nightly.yaml - with: - vllm: v0.11.0 - runner: ${{ matrix.os }} - image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-a3-ubuntu22.04-py3.11 - tests: tests/e2e/nightly/models/test_qwen3_32b_int8.py - qwen3-32b-in8-a2: - strategy: - matrix: - os: [ linux-aarch64-a2-4 ] - uses: ./.github/workflows/_e2e_nightly.yaml - with: - vllm: v0.11.0 - runner: ${{ matrix.os }} - tests: tests/e2e/nightly/models/test_qwen3_32b_int8.py - qwen3-235b-a22b-w8a8-eplb: - strategy: - matrix: - # should add A3 chip runner when available - os: [ linux-aarch64-a3-16 ] - # Note (yikun): If CI resource are limited we can split job into two chain jobs - # only trigger e2e test after lint passed and the change is e2e related with pull request. - uses: ./.github/workflows/_e2e_nightly.yaml - with: - vllm: v0.11.0 - runner: ${{ matrix.os }} - image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-a3-ubuntu22.04-py3.11 - tests: tests/e2e/nightly/models/test_qwen3_235b_a22b_w8a8_eplb.py - deepseek-r1-w8a8-eplb: - strategy: - matrix: - # should add A3 chip runner when available - os: [ linux-aarch64-a3-16 ] - # Note (yikun): If CI resource are limited we can split job into two chain jobs - # only trigger e2e test after lint passed and the change is e2e related with pull request. - uses: ./.github/workflows/_e2e_nightly.yaml - with: - vllm: v0.11.0 - runner: ${{ matrix.os }} - image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-a3-ubuntu22.04-py3.11 - tests: tests/e2e/nightly/models/test_deepseek_r1_w8a8_eplb.py - -