tinygrad/.github/workflows/test.yml

name: Unit Tests

on:
  push:
  pull_request:
  workflow_dispatch:

jobs:
  linter:
    name: Linters
    runs-on: ubuntu-latest
    timeout-minutes: 20

    steps:
    - name: Checkout Code
      uses: actions/checkout@v3
    - name: Set up Python 3.8
      uses: actions/setup-python@v4
      with:
        python-version: 3.8
    - name: Cache pip
      uses: actions/cache@v3
      with:
        path: ~/.cache/pip
        key: linting
    - name: Install dependencies
      run: pip install -e '.[linting,testing]' --extra-index-url https://download.pytorch.org/whl/cpu
    - name: Repo line count
      run: python3 sz.py
    - name: Lint with pylint
      run: python -m pylint --disable=all -e W0311 -e C0303 --jobs=0 --indent-string='  ' **/*.py
    - name: Lint with flake8
      run: flake8 --statistics -j4
    - name: Lint tinygrad with pylint
      run: pylint tinygrad/
    - name: Run mypy
      run: mypy tinygrad/ --ignore-missing-imports --check-untyped-defs --explicit-package-bases --warn-unreachable
    - name: Install SLOCCount
      run: sudo apt-get install sloccount
    - name: Check <5000 lines
      run: sloccount tinygrad test examples extra; if [ $(sloccount tinygrad | sed -n 's/.*Total Physical Source Lines of Code (SLOC)[ ]*= \([^ ]*\).*/\1/p' | tr -d ',') -gt 5000 ]; then exit 1; fi

  testcpuimagenet:
    name: CPU and ImageNet to C Tests
    runs-on: ubuntu-latest
    timeout-minutes: 20

    steps:
    - name: Checkout Code
      uses: actions/checkout@v3
    - name: Set up Python 3.8
      uses: actions/setup-python@v4
      with:
        python-version: 3.8
    - name: Cache pip
      uses: actions/cache@v3
      with:
        path: ~/.cache/pip
        key: testing
    - name: Install Dependencies
      run: pip install -e '.[testing]' --extra-index-url https://download.pytorch.org/whl/cpu
    - name: Test Docs
      run: python docs/abstractions.py
    - name: Test Quickstart
      run: awk '/```python/{flag=1;next}/```/{flag=0}flag' docs/quickstart.md > quickstart.py && PYTHONPATH=. python3 quickstart.py
    - name: Run Pytest
      run: python -m pytest -n=auto test/ -k "not (test_efficientnet and models/test_train.py)"
    - name: Fuzz Test symbolic
      run: python test/external/fuzz_symbolic.py
    - name: Fuzz Test shapetracker
      run: PYTHONPATH="." python test/external/fuzz_shapetracker.py
    - name: Compile EfficientNet to C
      run: PYTHONPATH="." CLANG=1 python3 examples/compile_efficientnet.py > recognize.c
    - name: Compile C to native
      run: clang -O2 recognize.c -lm -o recognize
    - name: Test EfficientNet
      run: curl https://media.istockphoto.com/photos/hen-picture-id831791190 | ./recognize | grep hen

  testtorch:
    name: Torch Tests
    runs-on: ubuntu-latest
    timeout-minutes: 20

    steps:
    - name: Checkout Code
      uses: actions/checkout@v3
    - name: Set up Python 3.8
      uses: actions/setup-python@v4
      with:
        python-version: 3.8
    - name: Cache pip
      uses: actions/cache@v3
      with:
        path: ~/.cache/pip
        key: testing
    - name: Install Dependencies
      run: pip install -e '.[testing]' --extra-index-url https://download.pytorch.org/whl/cpu
    - name: Run Pytest
      run: TORCH=1 python -m pytest -n=auto test/
    - name: Run ONNX
      run: TORCH=1 python -m pytest -n=auto test/external/external_test_onnx_backend.py --tb=no --disable-warnings || true

  testopencl:
    strategy:
      fail-fast: false
      matrix:
        task: [optimage, openpilot, multigpu]
    name: ${{ matrix.task=='optimage'&&'GPU OPT and IMAGE Tests'|| matrix.task=='openpilot'&&'openpilot (OpenCL) Tests'|| matrix.task=='multigpu'&&'MultiGPU Tests'}}
    runs-on: ubuntu-20.04
    timeout-minutes: 20

    steps:
      - name: Checkout Code
        uses: actions/checkout@v3
      - name: Find faster apt mirror
        uses: vegardit/fast-apt-mirror.sh@v1
      - name: Update packages
        run: |
          wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | sudo tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null
          echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | sudo tee /etc/apt/sources.list.d/oneAPI.list
          sudo apt-get update
      - name: Install OpenCL
        #run: sudo apt-get install -y pocl-opencl-icd
        run: sudo apt-get install -y intel-oneapi-runtime-compilers intel-oneapi-runtime-opencl
      - name: Set up Python 3.8
        uses: actions/setup-python@v4
        with:
          python-version: 3.8
      - name: Cache pip
        uses: actions/cache@v3
        with:
          path: ~/.cache/pip
          key: testing
      - name: Install Dependencies
        run: pip install -e '.[testing]' --extra-index-url https://download.pytorch.org/whl/cpu
      - if: ${{ matrix.task == 'optimage' }}
        name: Run Optimizer Test (OPT 2 and 3)
        run: |
          PYTHONPATH="." OPT=2 GPU=1 python -m pytest -n=auto test/external/external_test_opt.py
          PYTHONPATH="." OPT=3 GPU=1 python -m pytest -n=auto test/external/external_test_opt.py
      - if: ${{ matrix.task == 'optimage'}}
        name: Test GPU IMAGE ops
        run: |
          GPU=1 IMAGE=1 python3 -m pytest -n=auto test/test_ops.py
          FORWARD_ONLY=1 GPU=1 IMAGE=2 python3 -m pytest -n=auto test/test_ops.py
      - if: ${{ matrix.task == 'openpilot' }}
        name: Test openpilot model compile and size
        run: |
          DEBUG=2 ALLOWED_KERNEL_COUNT=199 FLOAT16=1 DEBUGCL=1 GPU=1 IMAGE=2 python3 openpilot/compile.py
          python3 -c 'import os; assert os.path.getsize("/tmp/output.thneed") < 100_000_000'
      - if: ${{ matrix.task == 'openpilot' }}
        name: Test openpilot model correctness (float32)
        run: DEBUGCL=1 GPU=1 IMAGE=2 python3 openpilot/compile.py
      - if: ${{ matrix.task == 'openpilot' }}
        name: Test tensor core ops
        run: GPU=1 TC=2 python3 -m pytest -n=auto test/test_ops.py
      - if: ${{ matrix.task == 'multigpu' }}
        name: Test multigpu
        run: |
          PYTHONPATH="." python test/external/dist/test_world.py
          PYTHONPATH="." python test/external/dist/test_collectives.py

  testmetalwebgpu:
    name: Metal and WebGPU Tests
    runs-on: macos-13
    timeout-minutes: 20

    steps:
    - name: Checkout Code
      uses: actions/checkout@v3
    - name: Set up Python 3.11
      uses: actions/setup-python@v4
      with:
        python-version: 3.11
    - name: Cache pip
      uses: actions/cache@v3
      with:
        path: ~/Library/Caches/pip
        key: metalwebgpu
    - name: Install Dependencies
      run: pip install -e '.[metal,webgpu,testing]' --extra-index-url https://download.pytorch.org/whl/cpu
    - name: Test LLaMA compile speed
      run: PYTHONPATH="." METAL=1 python3 test/external/external_test_speed_llama.py
    #- name: Run dtype test
    #  run: DEBUG=4 METAL=1 python -m pytest -n=auto test/test_dtype.py
    # dtype test has issues on test_half_to_int8
    - name: Run metal ops test
      run: DEBUG=2 METAL=1 python -m pytest -n=auto test/test_ops.py
    - name: Run JIT test
      run: DEBUG=2 METAL=1 python -m pytest -n=auto test/test_jit.py
    - name: Check Device.DEFAULT
      run: WEBGPU=1 python -c "from tinygrad.lazy import Device; assert Device.DEFAULT == 'WEBGPU', Device.DEFAULT"
    #- name: Run webgpu pytest
    #  run: WEBGPU=1 WGPU_BACKEND_TYPE=Metal python -m pytest -n=auto --ignore test/models/ --ignore test/unit/test_example.py --ignore test/extra/test_lr_scheduler.py --ignore test/test_linearizer.py test/
    #- name: Build WEBGPU Efficientnet
    #  run: WEBGPU=1 WGPU_BACKEND_TYPE=Metal python -m examples.compile_efficientnet

  tests:
    strategy:
      fail-fast: false
      matrix:
        backend: [llvm, clang, gpu, cuda]

    name: Tests on (${{ matrix.backend }})
    runs-on: ${{ matrix.backend == 'gpu'  && 'ubuntu-20.04' || 'ubuntu-latest' }}
    timeout-minutes: 20

    steps:
      - name: Checkout Code
        uses: actions/checkout@v3
      - name: Set up Python 3.8
        uses: actions/setup-python@v4
        with:
          python-version: 3.8
      - name: Cache pip
        uses: actions/cache@v3
        with:
          path: '~/.cache/pip'
          key: ${{ matrix.backend }}
      - name: Set env
        run: printf "${{ matrix.backend == 'llvm' && 'ENABLE_METHOD_CACHE=1\nLLVM=1' || matrix.backend == 'clang' && 'CLANG=1\nENABLED_METHOD_CACHE=1' || matrix.backend == 'gpu' && 'GPU=1' || matrix.backend == 'cuda' && 'FORWARD_ONLY=1\nJIT=1\nOPT=2\nCUDA=1\nCUDACPU=1\n'}}" >> $GITHUB_ENV
      - name: Find faster apt mirror
        uses: vegardit/fast-apt-mirror.sh@v1
      - name: Install packages (gpu)
        if: matrix.backend == 'gpu'
        run: |
          wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | sudo tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null
          echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | sudo tee /etc/apt/sources.list.d/oneAPI.list
          sudo apt-get update -y && \
          sudo apt-get install -y intel-oneapi-runtime-compilers intel-oneapi-runtime-opencl
      - name: Install packages (cuda)
        if: matrix.backend == 'cuda'
        run: |
          sudo apt-get update -y && \
          sudo apt-get install -y --no-install-recommends git g++ cmake ninja-build llvm-15-dev zlib1g-dev libglew-dev flex bison libfl-dev libboost-thread-dev libboost-filesystem-dev nvidia-cuda-toolkit-gcc
      - name: Cache gpuocelot
        if: matrix.backend == 'cuda'
        id: cache-build
        uses: actions/cache@v3
        env:
          cache-name: cache-gpuocelot-build
        with:
          path: ${{ github.workspace }}/gpuocelot/ocelot
          key: ubuntu22.04-gpuocelot-19626fc00b6ee321638c3111074269c69050e091
      - name: Clone/compile gpuocelot
        if: matrix.backend == 'cuda' && steps.cache-build.outputs.cache-hit != 'true'
        run: |
          git clone --recurse-submodules https://github.com/gpuocelot/gpuocelot.git ${{ github.workspace }}/gpuocelot
          cd ${{ github.workspace }}/gpuocelot/ocelot
          git checkout 19626fc00b6ee321638c3111074269c69050e091
          mkdir build
          cd build
          cmake .. -Wno-dev -G Ninja -DOCELOT_BUILD_TOOLS=OFF
          ninja
      - name: Install gpuocelot
        if: matrix.backend == 'cuda'
        run: |
          cd ${{ github.workspace }}/gpuocelot/ocelot/build
          sudo ninja install
      - name: Install dependencies
        run: pip install -e '.[testing${{matrix.backend=='llvm'&&',llvm'||matrix.backend=='cuda'&&',cuda'||''}}]' --extra-index-url https://download.pytorch.org/whl/cpu
      - name: Check Device.DEFAULT
        run: python -c "from tinygrad.lazy import Device; assert Device.DEFAULT in ['LLVM','CLANG','CUDA','GPU'], Device.DEFAULT"
      - name: Run pytest (not cuda)
        if: matrix.backend!='cuda'
        run: python -m pytest -n=auto test/ -k '${{matrix.backend=='llvm'&&'not (test_nn.py and test_conv_transpose2d)'||'test'}}' -m 'not exclude_${{matrix.backend}}'
      - name: Run pytest (cuda)
        if: matrix.backend=='cuda'
        run: python -m pytest -n=auto test/ -k 'not (half or test_efficientnet_safetensors) and not (test_conv2d and test_tensor.py)' -m 'not exclude_cuda' --ignore=test/external --ignore=test/models

  testunicorn:
    name: ARM64 unicorn Test
    runs-on: ubuntu-latest
    timeout-minutes: 20
    steps:
      - name: Checkout Code
        uses: actions/checkout@v3
      - name: Set up Python 3.8
        uses: actions/setup-python@v4
        with:
          python-version: 3.8
      - name: Cache pip
        uses: actions/cache@v3
        with:
          path: '~/.cache/pip'
          key: unicorn 
      - name: Install cross-assembler
        run: |
          sudo apt-get update -y && \
          sudo apt-get install -y --no-install-recommends gcc-aarch64-linux-gnu
      - name: Install dependencies
        run: pip install -e '.[testing,arm]' --extra-index-url https://download.pytorch.org/whl/cpu
      - name: Test arm
        run: CI=1 ARM64=1 CLANG=1 python -m pytest -n=auto test/ -k 'not (test_nn.py and (test_conv_transpose2d or test_conv2d))' --ignore=test/models --ignore=test/test_speed_v_torch.py --ignore=test/test_net_speed.py --ignore=test/test_specific_conv.py  --ignore=test/unit/test_disk_tensor.py