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"
    types: [synchronize, labeled]
  workflow_dispatch:

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

jobs:
  per-commit-1-ascend-npu:
    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
    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.extra-index-url "https://pypi.tuna.tsinghua.edu.cn/simple https://mirrors.aliyun.com/pypi/simple/"
          pip config set global.trusted-host "${CACHING_URL} pypi.tuna.tsinghua.edu.cn mirrors.aliyun.com"

          bash scripts/ci/npu_ci_install_dependency.sh 910b
          # 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
          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
          STREAMS_PER_DEVICE: 32
        run: |
          export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
          cd test/srt
          python3 run_suite.py --suite per-commit-1-ascend-npu

  per-commit-2-ascend-npu:
    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
    runs-on: linux-arm64-npu-2
    strategy:
      fail-fast: true
      matrix:
        part: [0, 1, 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.extra-index-url "https://pypi.tuna.tsinghua.edu.cn/simple https://mirrors.aliyun.com/pypi/simple/"
          pip config set global.trusted-host "${CACHING_URL} pypi.tuna.tsinghua.edu.cn mirrors.aliyun.com"

          bash scripts/ci/npu_ci_install_dependency.sh 910b
          # 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
          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
          STREAMS_PER_DEVICE: 32
        run: |
          export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
          cd test/srt
          python3 run_suite.py --suite per-commit-2-ascend-npu --auto-partition-id ${{ matrix.part }} --auto-partition-size 3

  per-commit-4-ascend-npu:
    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
    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.extra-index-url "https://pypi.tuna.tsinghua.edu.cn/simple https://mirrors.aliyun.com/pypi/simple/"
          pip config set global.trusted-host "${CACHING_URL} pypi.tuna.tsinghua.edu.cn mirrors.aliyun.com"

          bash scripts/ci/npu_ci_install_dependency.sh 910b
          # 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
          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
          STREAMS_PER_DEVICE: 32
        run: |
          export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
          cd test/srt
          python3 run_suite.py --suite per-commit-4-ascend-npu --timeout-per-file 3600

  per-commit-16-ascend-a3:
    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
    runs-on: linux-aarch64-a3-16
    strategy:
      fail-fast: true
      matrix:
        part: [0, 1]
    container:
      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-a3-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.extra-index-url "https://pypi.tuna.tsinghua.edu.cn/simple https://mirrors.aliyun.com/pypi/simple/"
          pip config set global.trusted-host "${CACHING_URL} pypi.tuna.tsinghua.edu.cn mirrors.aliyun.com"

          bash scripts/ci/npu_ci_install_dependency.sh a3
          # 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
          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
          STREAMS_PER_DEVICE: 32
        run: |
          export PATH="/usr/local/Ascend/8.3.RC1/compiler/bishengir/bin:${PATH}"
          cd test/srt
          python3 run_suite.py --suite per-commit-16-ascend-a3 --timeout-per-file 3600 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2