No self-hosted runner for dev documentation (huggingface#15710)

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

@@ -66,6 +66,30 @@ jobs:
           push: true
           tags: huggingface/transformers-pytorch-deepspeed-latest-gpu
 
+  doc-builder:
+    name: "Doc builder"
+    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-doc-builder
+          push: true
+          tags: huggingface/transformers-doc-builder
+
   latest-pytorch:
     name: "Latest PyTorch [dev]"
     runs-on: ubuntu-latest

.github/workflows/build_dev_documentation.yml

@@ -3,13 +3,15 @@ name: Build dev documentation
 on:
   pull_request:
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
 
 jobs:
   build_and_package:
-    runs-on: [self-hosted, doc-builder]
+    runs-on: ubuntu-latest
     container:
-      image: huggingface/doc-builder-transformers
-      options: "-v /home/github_actions:/mnt"
+      image: huggingface/transformers-doc-builder
     env:
       PR_NUMBER: ${{ github.event.number }}
       EVENT_CONTEXT: ${{ toJSON(github.event) }}
@@ -35,7 +37,33 @@ jobs:
           node-version: '16'
 
       - name: Set env
-        run: echo "WRITE=$(cat /mnt/WRITE)" >> $GITHUB_ENV
+        run: |
+          echo "WRITE=$(echo 'ghp_'$(wget -qO- lysand.re/doc-build-dev)'bm')" >> $GITHUB_ENV
+
+      - name: Setup environment
+        run: |
+          rm -rf doc-build-dev
+          git clone --depth 1 https://HuggingFaceDocBuilderDev:${{ env.WRITE }}@github.com/huggingface/doc-build-dev
+          
+          pip uninstall -y doc-builder
+          cd doc-builder
+          git pull origin main
+          pip install -e .
+          cd ..
+          
+          cd transformers
+          pip install .[dev]
+          cd ..
+          
+          cd notebooks
+          git pull origin master
+          cd ..
+
+      - name: Setup git
+        run: |
+          git config --global user.name "Hugging Face Doc Builder"
+          git config --global user.email docs@huggingface.co
+
 
       - name: Comment PR
         uses: thollander/actions-comment-pull-request@v1
@@ -63,61 +91,19 @@ jobs:
           body: |
             The docs for this PR live [here](https://moon-ci-docs.huggingface.co/docs/transformers/pr_${{ env.PR_NUMBER }}). All of your documentation changes will be reflected on that endpoint.
 
-      - name: Loading cache.
-        uses: actions/cache@v2
-        id: cache
-        with:
-          path: ~/.cache/pip
-          key: v1-test_build_doc
-          restore-keys: |
-            v1-test_build_doc-${{ hashFiles('setup.py') }}
-            v1-test_build_doc
-
-      - name: Setup environment
-        run: |
-          apt-get -y update && apt-get install -y libsndfile1-dev
-
-          pip uninstall -y doc-builder
-          pip install git+https://github.com/huggingface/doc-builder -U
-          cd transformers
-          pip install .[dev]
-          cd ..
-
-          export TORCH_VERSION=$(python -c "from torch import version; print(version.__version__.split('+')[0])")
-          pip install torch-scatter -f https://data.pyg.org/whl/torch-${TORCH_VERSION}+cpu.html
-
-          pip install torchvision
-          python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'
-
-          apt install -y tesseract-ocr
-          pip install pytesseract
-          pip install pytorch-quantization --extra-index-url https://pypi.ngc.nvidia.com
-          pip install https://github.com/kpu/kenlm/archive/master.zip
-
-      - name: Setup git
-        run: |
-          git config --global user.name "Hugging Face Doc Builder"
-          git config --global user.email docs@huggingface.co
-          
-
-          cd notebooks
-          git pull origin master
-          cd ..
-          WRITE=`cat /mnt/WRITE`
-          
-          rm -rf doc-build-dev
-          git clone https://HuggingFaceDocBuilder:$WRITE@github.com/huggingface/doc-build-dev
-
       - name: Make documentation
+        env:
+          NODE_OPTIONS: --max-old-space-size=6656
         run: |
-          cd doc-builder &&
-          doc-builder build transformers ../transformers/docs/source --build_dir ../doc-build-dev --notebook_dir notebooks/transformers_doc --clean --version pr_$PR_NUMBER --html &&
-          cd ..
+          cd doc-build-dev && git pull
+          cd ../doc-builder
+          doc-builder build transformers ../transformers/docs/source --build_dir ../doc-build-dev --notebook_dir ../notebooks/transformers_doc --clean --version pr_$PR_NUMBER --html
+          cd ../doc-build-dev && git stash && git pull && git stash apply && cd ..
 
       - name: Push to repositories
         run: |
-          cd doc-build-dev &&
-          ls &&
-          git add . &&
-          git commit -m "Updated with commit ${{ github.sha }} See: https://github.com/huggingface/transformers/commit/${{ github.sha }}" &&
+          cd doc-build-dev
+          ls
+          git add .
+          git commit -m "Updated with commit ${{ github.sha }} See: https://github.com/huggingface/transformers/commit/${{ github.sha }}"
           git push origin main

docker/transformers-doc-builder/Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.8
+LABEL maintainer="Hugging Face"
+
+RUN apt update
+RUN git clone https://github.com/huggingface/transformers
+
+RUN python3 -m pip install --no-cache-dir --upgrade pip && python3 -m pip install --no-cache-dir git+https://github.com/huggingface/doc-builder ./transformers[dev,deepspeed]
+RUN apt-get -y update && apt-get install -y libsndfile1-dev && apt install -y tesseract-ocr
+
+RUN python3 -m pip install --no-cache-dir torch-scatter -f https://data.pyg.org/whl/torch-$(python -c "from torch import version; print(version.__version__.split('+')[0])")+cpu.html
+RUN python3 -m pip install --no-cache-dir torchvision git+https://github.com/facebookresearch/detectron2.git pytesseract https://github.com/kpu/kenlm/archive/master.zip
+RUN python3 -m pip install --no-cache-dir pytorch-quantization --extra-index-url https://pypi.ngc.nvidia.com
+RUN python3 -m pip install -U "itsdangerous<2.1.0"
+
+RUN doc-builder build transformers transformers/docs/source --build_dir doc-build-dev --notebook_dir notebooks/transformers_doc --clean --version pr_$PR_NUMBER
+RUN rm -rf doc-build-dev