sglang/.github/workflows/pr-test-npu.yml

name: PR Test (Ascend NPU)

on:
  push:
    branches: [ main ]
    paths:
      - "python/**"
      - "scripts/ci/**"
      - "test/**"
      - ".github/workflows/pr-test-npu.yml"
  pull_request:
    branches: [ main ]
    paths:
      - "python/**"
      - "scripts/ci/**"
      - "test/**"
      - ".github/workflows/pr-test-npu.yml"
  workflow_dispatch:

concurrency:
  group: pr-test-npu-${{ github.ref }}
  cancel-in-progress: true

jobs:
  per-commit-1-ascend-npu:
    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
        github.event.pull_request.draft == false
    runs-on: linux-arm64-npu-1
    container:
      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Install dependencies
        run: |
          # speed up by using infra cache services
          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
          pip config set global.index-url http://${CACHING_URL}/pypi/simple
          pip config set global.trusted-host ${CACHING_URL}

          bash scripts/ci/npu_ci_install_dependency.sh
          # copy required file from our daily cache
          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
          # copy download through proxy
          curl -o /tmp/test.jsonl -L https://gh-proxy.test.osinfra.cn/https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl

      - name: Run test
        timeout-minutes: 60
        env:
          SGLANG_USE_MODELSCOPE: true
          SGLANG_IS_IN_CI: true
          HF_ENDPOINT: https://hf-mirror.com
          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
        run: |
          cd test/srt
          python3 run_suite.py --suite per-commit-1-ascend-npu

  per-commit-2-ascend-npu:
    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
        github.event.pull_request.draft == false
    runs-on: linux-arm64-npu-2
    container:
      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Install dependencies
        run: |
          # speed up by using infra cache services
          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
          pip config set global.index-url http://${CACHING_URL}/pypi/simple
          pip config set global.trusted-host ${CACHING_URL}

          bash scripts/ci/npu_ci_install_dependency.sh
          # copy required file from our daily cache
          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
          # copy download through proxy
          curl -o /tmp/test.jsonl -L https://gh-proxy.test.osinfra.cn/https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl

      - name: Run test
        timeout-minutes: 90
        env:
          SGLANG_USE_MODELSCOPE: true
          SGLANG_IS_IN_CI: true
          HF_ENDPOINT: https://hf-mirror.com
          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
        run: |
          cd test/srt
          python3 run_suite.py --suite per-commit-2-ascend-npu

  per-commit-4-ascend-npu:
    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
        github.event.pull_request.draft == false
    runs-on: linux-arm64-npu-4
    container:
      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Install dependencies
        run: |
          # speed up by using infra cache services
          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
          pip config set global.index-url http://${CACHING_URL}/pypi/simple
          pip config set global.trusted-host ${CACHING_URL}

          bash scripts/ci/npu_ci_install_dependency.sh
          # copy required file from our daily cache
          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
          # copy download through proxy
          curl -o /tmp/test.jsonl -L https://gh-proxy.test.osinfra.cn/https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl

      - name: Run test
        timeout-minutes: 60
        env:
          SGLANG_USE_MODELSCOPE: true
          SGLANG_IS_IN_CI: true
          HF_ENDPOINT: https://hf-mirror.com
          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
        run: |
          cd test/srt
          python3 run_suite.py --suite per-commit-4-ascend-npu --timeout-per-file 3600

  pr-test-npu-finish:
    if: always()
    needs:
      - per-commit-1-ascend-npu
      - per-commit-2-ascend-npu
      - per-commit-4-ascend-npu
    runs-on: ubuntu-latest
    steps:
      - name: Check all dependent job statuses
        run: |
          results=(${{ join(needs.*.result, ' ') }})
          for result in "${results[@]}"; do
            if [ "$result" = "failure" ] || [ "$result" = "cancelled" ]; then
              echo "Job failed with result: $result"
              exit 1
            fi
          done
          echo "All jobs completed successfully"
          exit 0