Add deepspeed test to amd scheduled CI

.github/workflows/build-docker-images.yml

@@ -271,3 +271,39 @@ jobs:
             REF=main
           push: true
           tags: huggingface/transformers-tensorflow-gpu
+
+  # latest-pytorch-deepspeed-amd:
+  #   name: "PyTorch + DeepSpeed (AMD) [dev]"
+
+  #   runs-on: [self-hosted, docker-gpu, amd-gpu, single-gpu, mi210]
+  #   steps:
+  #     - name: Set up Docker Buildx
+  #       uses: docker/setup-buildx-action@v3
+  #     - name: Check out code
+  #       uses: actions/checkout@v3
+  #     - name: Login to DockerHub
+  #       uses: docker/login-action@v3
+  #       with:
+  #         username: ${{ secrets.DOCKERHUB_USERNAME }}
+  #         password: ${{ secrets.DOCKERHUB_PASSWORD }}
+  #     - name: Build and push
+  #       uses: docker/build-push-action@v5
+  #       with:
+  #         context: ./docker/transformers-pytorch-deepspeed-amd-gpu
+  #         build-args: |
+  #           REF=main
+  #         push: true
+  #         tags: huggingface/transformers-pytorch-deepspeed-amd-gpu${{ inputs.image_postfix }}
+  #     # Push CI images still need to be re-built daily
+  #     -
+  #       name: Build and push (for Push CI) in a daily basis
+  #       # This condition allows `schedule` events, or `push` events that trigger this workflow NOT via `workflow_call`.
+  #       # The later case is useful for manual image building for debugging purpose. Use another tag in this case!
+  #       if: inputs.image_postfix != '-push-ci'
+  #       uses: docker/build-push-action@v5
+  #       with:
+  #         context: ./docker/transformers-pytorch-deepspeed-amd-gpu
+  #         build-args: |
+  #           REF=main
+  #         push: true
+  #         tags: huggingface/transformers-pytorch-deepspeed-amd-gpu-push-ci

.github/workflows/self-scheduled-amd-caller.yml

@@ -5,7 +5,7 @@ on:
     - cron: "17 2 * * *"
   push:
     branches:
-      - run_amd_scheduled_ci_caller*
+      - run_amd_scheduled_ci_caller__*
 
 jobs:
   run_amd_ci_mi210:

.github/workflows/self-scheduled-amd.yml

@@ -356,6 +356,62 @@ jobs:
           name: ${{ matrix.machine_type }}_run_tests_torch_pipeline_gpu
           path: /transformers/reports/${{ matrix.machine_type }}_tests_torch_pipeline_gpu
 
+  run_tests_torch_deepspeed_gpu:
+    name: Torch ROCm deepspeed tests
+    strategy:
+      fail-fast: false
+      matrix:
+        machine_type: [single-gpu, multi-gpu]
+
+    runs-on: [self-hosted, docker-gpu, amd-gpu, '${{ matrix.machine_type }}', '${{ inputs.gpu_flavor }}']
+    needs: setup
+    container:
+      image: huggingface/transformers-pytorch-deepspeed-amd-gpu
+      options: --device /dev/kfd --device /dev/dri --env ROCR_VISIBLE_DEVICES --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
+    steps:
+      - name: Update clone
+        working-directory: /transformers
+        run: git fetch && git checkout ${{ github.sha }}
+
+      - name: Reinstall transformers in edit mode (remove the one installed during docker image build)
+        working-directory: /transformers
+        run: python3 -m pip uninstall -y transformers && python3 -m pip install -e .
+
+      - name: ROCM-SMI
+        run: |
+          rocm-smi
+      - name: ROCM-INFO
+        run: |
+          rocminfo  | grep "Agent" -A 14
+      - name: Show ROCR environment
+        run: |
+          echo "ROCR: $ROCR_VISIBLE_DEVICES"
+
+      - name: Environment
+        working-directory: /transformers
+        run: |
+          python3 utils/print_env.py
+
+      - name: Show installed libraries and their versions
+        working-directory: /transformers
+        run: pip freeze
+
+      - name: Run all tests on GPU
+        working-directory: /transformers
+        run: python3 -m pytest -v --make-reports=${{ matrix.machine_type }}_tests_torch_deepspeed_gpu tests/deepspeed tests/extended
+
+      - name: Failure short reports
+        if: ${{ failure() }}
+        continue-on-error: true
+        run: cat /transformers/reports/${{ matrix.machine_type }}_tests_torch_deepspeed_gpu/failures_short.txt
+
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v3
+        with:
+          name: ${{ matrix.machine_type }}_run_tests_torch_deepspeed_gpu_test_reports
+          path: /transformers/reports/${{ matrix.machine_type }}_tests_torch_deepspeed_gpu
+
   run_extract_warnings:
     name: Extract warnings in CI artifacts
     runs-on: ubuntu-22.04
@@ -368,7 +424,7 @@ jobs:
       run_tests_multi_gpu,
       run_examples_gpu,
       run_pipelines_torch_gpu,
-      # run_all_tests_torch_cuda_extensions_gpu
+      run_tests_torch_deepspeed_gpu
     ]
     steps:
       - name: Checkout transformers
@@ -417,7 +473,7 @@ jobs:
       run_tests_multi_gpu,
       run_examples_gpu,
       run_pipelines_torch_gpu,
-      # run_all_tests_torch_cuda_extensions_gpu,
+      run_tests_torch_deepspeed_gpu,
       run_extract_warnings
     ]
     steps:

docker/transformers-pytorch-deepspeed-amd-gpu/Dockerfile

@@ -0,0 +1,26 @@
+FROM rocm/pytorch:rocm5.7_ubuntu22.04_py3.10_pytorch_2.0.1
+LABEL maintainer="Hugging Face"
+
+ARG DEBIAN_FRONTEND=noninteractive
+ARG PYTORCH='2.0.1'
+ARG ROCM='5.7'
+
+RUN apt update && \
+    apt install -y --no-install-recommends libaio-dev git && \
+    apt clean && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN python3 -m pip install --no-cache-dir --upgrade pip
+
+RUN python3 -m pip uninstall -y apex
+
+ARG REF=main
+WORKDIR /
+RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
+RUN python3 -m pip install --no-cache-dir ./transformers[deepspeed-testing]
+
+# When installing in editable mode, `transformers` is not recognized as a package.
+# this line must be added in order for python to be aware of transformers.
+RUN cd transformers && python3 setup.py develop
+
+RUN python3 -c "from deepspeed.launcher.runner import main"

docker/transformers-pytorch-deepspeed-latest-gpu/Dockerfile

@@ -34,7 +34,7 @@ RUN python3 -m pip uninstall -y torch-tensorrt
 
 # recompile apex
 RUN python3 -m pip uninstall -y apex
-RUN git clone https://github.com/NVIDIA/apex
+# RUN git clone https://github.com/NVIDIA/apex
 #  `MAX_JOBS=1` disables parallel building to avoid cpu memory OOM when building image on GitHub Action (standard) runners
 # TODO: check if there is alternative way to install latest apex
 # RUN cd apex && MAX_JOBS=1 python3 -m pip install --global-option="--cpp_ext" --global-option="--cuda_ext" --no-cache -v --disable-pip-version-check .