xc-llm-ascend/.github/workflows/vllm_ascend_test_full.yaml

#
# 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: 'test-full'

on:
  pull_request:
    branches:
      - 'main'
      - '*-dev'
    types: [ labeled, synchronize ]

# 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:
  changes:
    runs-on: ubuntu-latest
    if: ${{ contains(github.event.pull_request.labels.*.name, 'ready') && contains(github.event.pull_request.labels.*.name, 'ready-for-test') }}
    outputs:
      e2e_tracker: ${{ steps.filter.outputs.e2e_tracker }}
      ut_tracker: ${{ steps.filter.outputs.ut_tracker }}
    steps:
      - uses: actions/checkout@v4
      - uses: dorny/paths-filter@v3
        id: filter
        with:
          filters: |
            e2e_tracker:
              - '.github/workflows/vllm_ascend_test.yaml'
              - 'vllm_ascend/**'
              - 'csrc/**'
              - 'cmake/**'
              - 'tests/e2e/**'
              - 'CMakeLists.txt'
              - 'setup.py'
              - 'requirements.txt'
              - 'requirements-dev.txt'
              - 'requirements-lint.txt'
              - 'packages.txt'
            ut_tracker:
              - 'tests/ut/**'

  e2e-full:
    # only trigger full test when pull request is approved
    needs: [changes]
    if: ${{ needs.changes.outputs.e2e_tracker == 'true' }}
    strategy:
      max-parallel: 2
      matrix:
        os: [linux-aarch64-a2-1]
        vllm_version: [v0.10.2]
    name: singlecard e2e test - full
    runs-on: ${{ matrix.os }}
    container:
      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
      env:
        VLLM_LOGGING_LEVEL: ERROR
        VLLM_USE_MODELSCOPE: True
    steps:
      - name: Check npu and CANN info
        run: |
          npu-smi info
          cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info

      - name: Config mirrors
        run: |
          sed -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: 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_version }}
          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: Run e2e test
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
          VLLM_USE_MODELSCOPE: True
        run: |
          # We found that if running aclgraph tests in batch, it will cause AclmdlRICaptureBegin error. So we run
          # the test separately.

          pytest -sv tests/e2e/singlecard/test_aclgraph.py
          pytest -sv tests/e2e/singlecard/test_ascend_scheduler.py
          pytest -sv tests/e2e/singlecard/test_camem.py
          pytest -sv tests/e2e/singlecard/test_chunked.py
          pytest -sv tests/e2e/singlecard/test_embedding.py
          pytest -sv tests/e2e/singlecard/test_guided_decoding.py
          #pytest -sv tests/e2e/singlecard/test_ilama_lora.py
          pytest -sv tests/e2e/singlecard/test_profile_execute_duration.py
          pytest -sv tests/e2e/singlecard/test_quantization.py
          pytest -sv tests/e2e/singlecard/test_sampler.py
          pytest -sv tests/e2e/singlecard/test_vlm.py

          # ------------------------------------ v1 spec decode test ------------------------------------ #
          pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py
          pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_torchair_correctness.py
          pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py

          pytest -sv tests/e2e/singlecard/ops/

  e2e-2-cards-full:
    # only trigger full test when pull request is approved
    needs: [changes]
    if: ${{ needs.changes.outputs.e2e_tracker == 'true' }}
    strategy:
      max-parallel: 2
      matrix:
        os: [linux-aarch64-a2-2]
        vllm_version: [v0.10.2]
    name: multicard e2e test - full
    runs-on: ${{ matrix.os }}
    container:
      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
      env:
        VLLM_LOGGING_LEVEL: ERROR
        VLLM_USE_MODELSCOPE: True
    steps:
      - name: Check npu and CANN info
        run: |
          npu-smi info
          cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info

      - name: Config mirrors
        run: |
          sed -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: 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_version }}
          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: Run vllm-project/vllm-ascend test
        env:
          VLLM_WORKER_MULTIPROC_METHOD: spawn
          VLLM_USE_MODELSCOPE: True
        run: |
          pytest -sv tests/e2e/multicard/test_data_parallel.py
          pytest -sv tests/e2e/multicard/test_expert_parallel.py
          # external_launcher test is not stable enough. Fix it later
          # pytest -sv tests/e2e/multicard/test_external_launcher.py
          pytest -sv tests/e2e/multicard/test_fused_moe_allgather_ep.py
          #pytest -sv tests/e2e/multicard/test_ilama_lora_tp2.py

          # To avoid oom, we need to run the test in a single process.
          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_QwQ
          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe
          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W8A8
          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC
          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC
          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_sp_for_qwen3_moe
          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen_Dense_with_flashcomm_v1
          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen_Dense_with_prefetch_mlp_weight

          #pytest -sv tests/e2e/multicard/test_pipeline_parallel.py
          pytest -sv tests/e2e/multicard/test_prefix_caching.py
          pytest -sv tests/e2e/multicard/test_qwen3_moe.py
          pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py