a9f730b853
### What this PR does / why we need it?
fix bug : https://github.com/vllm-project/vllm-ascend/issues/5634
Intermittent CI failure due to a compilation error in the triton
operator
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef
---------
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
98 lines
3.9 KiB
YAML
98 lines
3.9 KiB
YAML
name: 'unit test'
|
|
|
|
on:
|
|
workflow_call:
|
|
inputs:
|
|
vllm:
|
|
required: true
|
|
type: string
|
|
runner:
|
|
required: true
|
|
type: string
|
|
image:
|
|
required: true
|
|
type: string
|
|
type:
|
|
required: true
|
|
type: string
|
|
|
|
jobs:
|
|
unit-test:
|
|
name: unit test
|
|
runs-on: ${{ inputs.runner }}
|
|
container:
|
|
image: ${{ inputs.image }}
|
|
env:
|
|
VLLM_LOGGING_LEVEL: ERROR
|
|
VLLM_USE_MODELSCOPE: True
|
|
SOC_VERSION: ascend910b1
|
|
MAX_JOBS: 4
|
|
steps:
|
|
- name: Install packages
|
|
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-get install -y python3-pip git vim wget net-tools gcc g++ cmake libnuma-dev curl gnupg2
|
|
|
|
- name: Checkout vllm-project/vllm repo
|
|
uses: actions/checkout@v6
|
|
with:
|
|
repository: vllm-project/vllm
|
|
ref: ${{ inputs.vllm }}
|
|
path: ./vllm-empty
|
|
|
|
- name: Install vllm-project/vllm from source
|
|
working-directory: ./vllm-empty
|
|
run: |
|
|
VLLM_TARGET_DEVICE=empty python3 -m pip install . --extra-index https://download.pytorch.org/whl/cpu/
|
|
python3 -m pip uninstall -y triton
|
|
|
|
- name: Checkout vllm-project/vllm-ascend repo
|
|
uses: actions/checkout@v6
|
|
|
|
- name: Install vllm-project/vllm-ascend
|
|
run: |
|
|
export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
|
|
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/x86_64-linux/devlib
|
|
python3 -m pip install -v . --extra-index https://download.pytorch.org/whl/cpu/
|
|
python3 -m pip install -r requirements-dev.txt --extra-index https://download.pytorch.org/whl/cpu/
|
|
|
|
- name: Install Ascend toolkit & triton_ascend
|
|
shell: bash -l {0}
|
|
run: |
|
|
apt-get -y install clang-15
|
|
update-alternatives --install /usr/bin/clang clang /usr/bin/clang-15 20
|
|
update-alternatives --install /usr/bin/clang++ clang++ /usr/bin/clang++-15 20
|
|
BISHENG_NAME="Ascend-BiSheng-toolkit_aarch64_20260105.run"
|
|
BISHENG_URL="https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${BISHENG_NAME}"
|
|
wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./${BISHENG_NAME}" --install && rm "${BISHENG_NAME}"
|
|
export PATH=/usr/local/Ascend/tools/bishengir/bin:$PATH
|
|
python3 -m pip install -i https://test.pypi.org/simple/ triton-ascend==3.2.0.dev20260105
|
|
|
|
- name: Run unit test
|
|
env:
|
|
VLLM_WORKER_MULTIPROC_METHOD: spawn
|
|
TORCH_DEVICE_BACKEND_AUTOLOAD: 0
|
|
run: |
|
|
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/x86_64-linux/devlib
|
|
pytest -sv --cov --cov-report=xml:unittests-coverage.xml tests/ut \
|
|
--ignore tests/ut/model_loader/netloader/test_netloader_elastic.py \
|
|
--ignore tests/ut/kv_connector/test_remote_prefill_lifecycle.py \
|
|
--ignore tests/ut/kv_connector/test_remote_decode_lifecycle.py \
|
|
--ignore tests/ut/core/test_scheduler_dynamic_batch.py \
|
|
--ignore tests/ut/kv_connector/test_mooncake_connector.py \
|
|
--ignore tests/ut/worker/test_worker_v1.py
|
|
|
|
- name: Upload coverage to Codecov
|
|
# only upload coverage when commits merged
|
|
if: ${{ inputs.type == 'schedule' }}
|
|
uses: codecov/codecov-action@v5
|
|
env:
|
|
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
|
|
with:
|
|
flags: unittests
|
|
name: vllm-ascend
|
|
verbose: true
|