[Test refactor 5/5] Build docker images (huggingface#15729)

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

@@ -0,0 +1,70 @@
+name: Build docker images (scheduled)
+
+on:
+  push:
+    branches:
+      - master
+      - updating-dockerfiles
+    paths:
+      - "src/**"
+      - "tests/**"
+      - ".github/**"
+      - "templates/**"
+      - "utils/**"
+      - "docker/**"
+  repository_dispatch:
+  schedule:
+    - cron: "0 1 * * *"
+
+jobs:
+  latest-docker:
+    name: "Latest PyTorch + TensorFlow [dev]"
+    runs-on: ubuntu-latest
+    steps:
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+      -
+        name: Check out code
+        uses: actions/checkout@v2
+      -
+        name: Login to DockerHub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_PASSWORD }}
+      -
+        name: Build and push
+        uses: docker/build-push-action@v2
+        with:
+          context: ./docker/transformers-all-latest-gpu
+          build-args: |
+            REF=master
+          push: true
+          tags: huggingface/transformers-all-latest-gpu
+
+  latest-torch-deepspeed-docker:
+    name: "Latest PyTorch + DeepSpeed"
+    runs-on: ubuntu-latest
+    steps:
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+      -
+        name: Check out code
+        uses: actions/checkout@v2
+      -
+        name: Login to DockerHub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_PASSWORD }}
+      -
+        name: Build and push
+        uses: docker/build-push-action@v2
+        with:
+          context: ./docker/transformers-pytorch-deepspeed-latest-gpu
+          build-args: |
+            REF=master
+          push: true
+          tags: huggingface/transformers-pytorch-deepspeed-latest-gpu

docker/transformers-all-latest-gpu/Dockerfile

@@ -0,0 +1,22 @@
+FROM nvidia/cuda:11.2.2-cudnn8-runtime-ubuntu20.04
+LABEL maintainer="Hugging Face"
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+RUN apt update
+RUN apt install -y git libsndfile1-dev tesseract-ocr espeak-ng python3 python3-pip ffmpeg
+RUN python3 -m pip install --no-cache-dir --upgrade pip
+
+ARG REF=master
+RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
+RUN python3 -m pip install --no-cache-dir -e ./transformers[dev,onnxruntime]
+
+RUN python3 -m pip install --no-cache-dir -U torch tensorflow
+RUN python3 -m pip uninstall -y flax jax
+RUN python3 -m pip install --no-cache-dir torch-scatter -f https://data.pyg.org/whl/torch-$(python3 -c "from torch import version; print(version.__version__.split('+')[0])")+cpu.html
+RUN python3 -m pip install --no-cache-dir git+https://github.com/facebookresearch/detectron2.git pytesseract https://github.com/kpu/kenlm/archive/master.zip
+RUN python3 -m pip install -U "itsdangerous<2.1.0"
+
+# 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

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

@@ -0,0 +1,21 @@
+FROM nvcr.io/nvidia/pytorch:21.03-py3
+LABEL maintainer="Hugging Face"
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+RUN apt -y update
+RUN apt install -y libaio-dev
+RUN python3 -m pip install --no-cache-dir --upgrade pip
+
+ARG REF=master
+RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
+RUN python3 -m pip install --no-cache-dir -e ./transformers[testing,deepspeed]
+
+RUN git clone https://github.com/microsoft/DeepSpeed && cd DeepSpeed && rm -rf build && \
+    DS_BUILD_CPU_ADAM=1 DS_BUILD_AIO=1 DS_BUILD_UTILS=1 python3 -m pip install -e . --global-option="build_ext" --global-option="-j8" --no-cache -v --disable-pip-version-check 2>&1
+
+# 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-gpu/Dockerfile

@@ -1,30 +1,25 @@
-FROM nvidia/cuda:10.2-cudnn7-devel-ubuntu18.04
+FROM nvidia/cuda:11.2.2-cudnn8-runtime-ubuntu20.04
 LABEL maintainer="Hugging Face"
-LABEL repository="transformers"
 
-RUN apt update && \
-    apt install -y bash \
-                   build-essential \
-                   git \
-                   curl \
-                   ca-certificates \
-                   python3 \
-                   python3-pip && \
-    rm -rf /var/lib/apt/lists
+ARG DEBIAN_FRONTEND=noninteractive
 
-RUN python3 -m pip install --no-cache-dir --upgrade pip && \
-    python3 -m pip install --no-cache-dir \
-    mkl \
-    torch
+RUN apt update
+RUN apt install -y git libsndfile1-dev tesseract-ocr espeak-ng python3 python3-pip ffmpeg
+RUN python3 -m pip install --no-cache-dir --upgrade pip
 
-RUN git clone https://github.com/NVIDIA/apex
-RUN cd apex && \
-    python3 setup.py install && \
-    pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./
+ARG REF=master
+RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
+RUN python3 -m pip install --no-cache-dir -e ./transformers[dev,onnxruntime]
 
-WORKDIR /workspace
-COPY . transformers/
-RUN cd transformers/ && \
-    python3 -m pip install --no-cache-dir .
+# If set to nothing, will install the latest version
+ARG PYTORCH=''
 
-CMD ["/bin/bash"]
+RUN [ ${#PYTORCH} -gt 0 ] && VERSION='torch=='$PYTORCH'.*' ||  VERSION='torch'; python3 -m pip install --no-cache-dir -U $VERSION
+RUN python3 -m pip uninstall -y tensorflow flax
+
+RUN python3 -m pip install --no-cache-dir torch-scatter -f https://data.pyg.org/whl/torch-$(python3 -c "from torch import version; print(version.__version__.split('+')[0])")+cpu.html
+RUN python3 -m pip install --no-cache-dir git+https://github.com/facebookresearch/detectron2.git pytesseract https://github.com/kpu/kenlm/archive/master.zip
+
+# 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

docker/transformers-tensorflow-gpu/Dockerfile

@@ -1,25 +1,22 @@
-FROM nvidia/cuda:10.1-cudnn7-runtime-ubuntu18.04
+FROM nvidia/cuda:11.2.2-cudnn8-runtime-ubuntu20.04
 LABEL maintainer="Hugging Face"
-LABEL repository="transformers"
 
-RUN apt update && \
-    apt install -y bash \
-                   build-essential \
-                   git \
-                   curl \
-                   ca-certificates \
-                   python3 \
-                   python3-pip && \
-    rm -rf /var/lib/apt/lists
+ARG DEBIAN_FRONTEND=noninteractive
 
-RUN python3 -m pip install --no-cache-dir --upgrade pip && \
-    python3 -m pip install --no-cache-dir \
-    mkl \
-    tensorflow
+RUN apt update
+RUN apt install -y git libsndfile1-dev tesseract-ocr espeak-ng python3 python3-pip ffmpeg
+RUN python3 -m pip install --no-cache-dir --upgrade pip
 
-WORKDIR /workspace
-COPY . transformers/
-RUN cd transformers/ && \
-    python3 -m pip install --no-cache-dir .
+ARG REF=master
+RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
+RUN python3 -m pip install --no-cache-dir -e ./transformers[dev,onnxruntime]
 
-CMD ["/bin/bash"]
+# If set to nothing, will install the latest version
+ARG TENSORFLOW=''
+
+RUN [ ${#TENSORFLOW} -gt 0 ] && VERSION='tensorflow=='$TENSORFLOW'.*' ||  VERSION='tensorflow'; python3 -m pip install --no-cache-dir -U $VERSION
+RUN python3 -m pip uninstall -y torch flax
+
+# 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