update

microsoft · Aug 3, 2024 · 95894bb · 95894bb
1 parent 426445c
commit 95894bb
Show file tree

Hide file tree

Showing 26 changed files with 4,403 additions and 0 deletions.
diff --git a/deepspeed/.github/workflows/amd-mi200.yml b/deepspeed/.github/workflows/amd-mi200.yml
@@ -0,0 +1,86 @@
+name: amd-mi200
+
+on:
+  workflow_dispatch:
+  pull_request:
+    paths:
+      - '.github/workflows/amd-mi200.yml'
+      - 'requirements/**'
+  schedule:
+    - cron: "0 0 * * *"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+  issues: write
+
+jobs:
+  amd-tests:
+    # The type of runner that the job will run on
+    runs-on: [self-hosted, amd, mi200]
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+      - uses: actions/checkout@v4
+
+      - id: setup-venv
+        uses: ./.github/workflows/setup-venv
+
+      - name: Install pytorch
+        run: |
+          pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/rocm6.0
+          python -c "import torch; print('torch:', torch.__version__, torch)"
+          python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
+
+      - name: Install transformers
+        run: |
+          git clone https://github.com/huggingface/transformers
+          cd transformers
+          # if needed switch to the last known good SHA until transformers@master is fixed
+          # git checkout 1cc453d33
+          git rev-parse --short HEAD
+          pip install .
+
+      - name: Install (ROCm) apex
+        run: |
+          git clone https://github.com/ROCmSoftwarePlatform/apex.git
+          cd apex
+          git checkout torch_2.1_higher
+          CURRENT_VER=$(git rev-parse HEAD)
+          INSTALLED_VER=$(cat /blob/amd-apex/.venv_installed_version)
+          if [[ "$CURRENT_VER" != "$INSTALLED_VER" ]]; then
+            pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings="--global-option=--cpp_ext" --config-settings="--global-option=--cuda_ext" --target=/blob/amd-apex/ --upgrade .
+            git rev-parse HEAD > /blob/amd-apex/.venv_installed_version
+          fi
+          echo PYTHONPATH=$PYTHONPATH:/blob/amd-apex/ >> $GITHUB_ENV
+      # Runs a set of commands using the runners shell
+      - name: Install deepspeed
+        run: |
+          pip install .[dev,1bit,autotuning]
+          #python -c "from deepspeed.env_report import cli_main; cli_main()"
+          ds_report
+
+      - name: Python environment
+        run: |
+          pip list
+
+      # Runs a set of commands using the runners shell
+      - name: Unit tests
+        run: |
+          unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
+          cd tests
+          pytest $PYTEST_OPTS -n 4 --verbose unit/
+          pytest $PYTEST_OPTS -m 'sequential' unit/
+
+      - name: Open GitHub issue if nightly CI fails
+        if: ${{ failure() && (github.event_name == 'schedule') }}
+        uses: JasonEtco/create-an-issue@v2
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          filename: .github/ISSUE_TEMPLATE/ci_failure_report.md
+          update_existing: true
diff --git a/deepspeed/.github/workflows/nv-mii.yml b/deepspeed/.github/workflows/nv-mii.yml
@@ -0,0 +1,74 @@
+name: nv-mii
+
+on:
+  workflow_dispatch:
+    inputs:
+      mii_branch:
+        description: 'DeepSpeed-MII Branch'
+        required: false
+        default: 'main'
+        type: string
+  pull_request:
+    paths:
+      - '.github/workflows/nv-mii.yml'
+      - 'requirements/**'
+      - 'setup.py'
+      - 'deepspeed/__init__.py'
+      - 'deepspeed/inference/**'
+      - '!deepspeed/inference/v2/**' # exclude v2 dir
+  merge_group:
+    branches: [ master ]
+  schedule:
+    - cron: "0 0 * * *"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  unit-tests:
+    runs-on: [self-hosted, nvidia, cu117, v100]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - id: setup-venv
+        uses: ./.github/workflows/setup-venv
+
+      - name: Install pytorch
+        run: |
+          pip3 install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu118
+          python -c "import torch; print('torch:', torch.__version__, torch)"
+          python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
+
+      - name: Install transformers
+        run: |
+          git clone https://github.com/huggingface/transformers
+          cd transformers
+          # if needed switch to the last known good SHA until transformers@master is fixed
+          git checkout v4.42.4
+          git rev-parse --short HEAD
+          pip install .
+
+      - name: Install deepspeed
+        run: |
+          pip install .[dev]
+          ds_report
+
+      - name: Python environment
+        run: |
+          pip list
+
+      - name: MII unit tests
+        run: |
+          BRANCH="main"
+          if [[ ! -z "${{ github.event.inputs.mii_branch }}" ]]; then
+              BRANCH="${{ github.event.inputs.mii_branch }}"
+          fi
+          echo "Cloning DeepSpeed-MII branch: $BRANCH"
+          git clone -b $BRANCH --depth=1 https://github.com/microsoft/DeepSpeed-MII.git
+          cd DeepSpeed-MII
+          pip install .[dev]
+          unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
+          cd tests/legacy
+          pytest $PYTEST_OPTS --forked -m "deepspeed" ./