[fbsync] Migrate docs workflow to GHA (#7407)

Summary: Co-authored-by: Nikita Shulga <[email protected]>

Reviewed By: vmoens

Differential Revision: D44416559

fbshipit-source-id: 48db0e9e718954b3c0313df2cf3214d178d3fa5c

Author: NicolasHug

.circleci/config.yml

@@ -869,73 +869,6 @@ jobs:
             conda activate python39
             packaging/build_cmake.sh
 
-  build_docs:
-    <<: *binary_common
-    docker:
-      - image: cimg/python:3.8
-    resource_class: 2xlarge+
-    steps:
-      - attach_workspace:
-          at: ~/workspace
-      - checkout
-      - download_model_weights
-      - run:
-          name: Setup
-          command: .circleci/unittest/linux/scripts/setup_env.sh
-      - designate_upload_channel
-      - run:
-          name: Install torchvision
-          command: .circleci/unittest/linux/scripts/install.sh
-      - run:
-          name: Build docs
-          command: |
-            set -ex
-            # turn v1.12.0rc3 into 1.12.0
-            tag=$(echo $CIRCLE_TAG | sed -e 's/v*\([0-9.]*\).*/\1/')
-            VERSION=${tag:-main}
-            eval "$(./conda/bin/conda shell.bash hook)"
-            conda activate ./env
-            pushd docs
-            pip install --progress-bar=off -r requirements.txt
-            make html
-            popd
-      - persist_to_workspace:
-          root: ./
-          paths:
-            - "*"
-      - store_artifacts:
-          path: ./docs/build/html
-          destination: docs
-
-  upload_docs:
-    <<: *binary_common
-    docker:
-      - image: "pytorch/manylinux-cuda100"
-    resource_class: 2xlarge+
-    steps:
-      - attach_workspace:
-          at: ~/workspace
-      - run:
-          name: Generate netrc
-          command: |
-            # set credentials for https pushing
-            # requires the org-member context
-            cat > ~/.netrc \<<DONE
-              machine github.com
-              login pytorchbot
-              password ${GITHUB_PYTORCHBOT_TOKEN}
-            DONE
-      - run:
-          name: Upload docs
-          command: |
-            # Don't use "checkout" step since it uses ssh, which cannot git push
-            # https://circleci.com/docs/2.0/configuration-reference/#checkout
-            set -ex
-            # Change v1.12.1rc1 into 1.12 (only major.minor)
-            tag=$(echo $CIRCLE_TAG | sed -e 's/v*\([0-9]*\.[0-9]*\).*/\1/')
-            target=${tag:-main}
-            ~/workspace/.circleci/build_docs/commit_docs.sh ~/workspace $target
-
 
 workflows:
   lint:

.circleci/config.yml.in

@@ -61,12 +61,8 @@ def build_workflows(prefix="", filter_branch=None, upload=False, indentation=6,
                             fb = "/.*/"
 
                         # Disable all Linux Wheels Workflows from CircleCI
-                        # since those will now be done through Nova. We'll keep
-                        # around the py3.8 CPU Linux Wheels build since the docs
-                        # job depends on it.
                         if os_type == "linux" and btype == "wheel":
-                            if not (python_version == "3.8" and cu_version == "cpu"):
-                                continue
+                            continue
 
                         # Disable all Macos Wheels Workflows from CircleCI.
                         if os_type == "macos" and btype == "wheel":
@@ -80,10 +76,6 @@ def build_workflows(prefix="", filter_branch=None, upload=False, indentation=6,
                             btype, os_type, python_version, cu_version, unicode, prefix, upload, filter_branch=fb
                         )
 
-    if not filter_branch:
-        # Build on every pull request, but upload only on nightly and tags
-        w += build_doc_job("/.*/")
-        w += upload_doc_job("nightly")
     return indent(indentation, w)
 
 
@@ -114,35 +106,6 @@ def workflow_pair(btype, os_type, python_version, cu_version, unicode, prefix=""
     return w
 
 
-def build_doc_job(filter_branch):
-    job = {
-        "name": "build_docs",
-        "python_version": "3.8",
-        "requires": [
-            "binary_linux_wheel_py3.8_cpu",
-        ],
-    }
-
-    if filter_branch:
-        job["filters"] = gen_filter_branch_tree(filter_branch, tags_list=RC_PATTERN)
-    return [{"build_docs": job}]
-
-
-def upload_doc_job(filter_branch):
-    job = {
-        "name": "upload_docs",
-        "context": "org-member",
-        "python_version": "3.8",
-        "requires": [
-            "build_docs",
-        ],
-    }
-
-    if filter_branch:
-        job["filters"] = gen_filter_branch_tree(filter_branch, tags_list=RC_PATTERN)
-    return [{"upload_docs": job}]
-
-
 manylinux_images = {
     "cu117": "pytorch/manylinux-cuda117",
     "cu118": "pytorch/manylinux-cuda118",

.circleci/regenerate.py

@@ -0,0 +1,68 @@
+name: Docs
+
+on:
+  pull_request:
+  push:
+    branches:
+      - nightly
+      - main
+      - release/*
+  workflow_dispatch:
+
+jobs:
+  build:
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
+    with:
+      repository: pytorch/vision
+      upload-artifact: docs
+      script: |
+        set -euo pipefail
+
+        export PYTHON_VERSION=3.8
+        export GPU_ARCH_TYPE=cpu
+        export GPU_ARCH_VERSION=''
+        ./.github/scripts/setup-env.sh
+        
+        # Prepare conda
+        CONDA_PATH=$(which conda)
+        eval "$(${CONDA_PATH} shell.bash hook)"
+        conda activate ci
+        # FIXME: not sure why we need this. `ldd torchvision/video_reader.so` shows that it
+        #  already links against the one pulled from conda. However, at runtime it pulls from
+        #  /lib64
+        # Should we maybe always do this in `./.github/scripts/setup-env.sh` so that we don't
+        # have to pay attention in all other workflows?
+        export LD_LIBRARY_PATH="${CONDA_PREFIX}/lib:${LD_LIBRARY_PATH}"
+        
+        cd docs
+        
+        echo '::group::Install doc requirements'
+        pip install --progress-bar=off -r requirements.txt
+        echo '::endgroup::'
+        
+        echo '::group::Build HTML docs'
+        # The runner does not have sufficient memory to run with as many processes as their are
+        # cores (`-j auto`). Thus, we limit to a single process (`-j 1`) here.
+        sed -i -e 's/-j auto/-j 1/' Makefile
+        make html
+        echo '::endgroup::'
+        
+        mv build/html "${RUNNER_ARTIFACT_DIR}"
+
+  upload-preview:
+    if: github.event_name == 'pull_request'
+    needs: [build]
+    runs-on: [self-hosted, linux.2xlarge]
+    steps:
+      - uses: actions/download-artifact@v3
+        with:
+          name: docs
+
+      - name: Upload docs preview
+        uses: seemethere/upload-artifact-s3@v5
+        with:
+          retention-days: 14
+          s3-bucket: doc-previews
+          if-no-files-found: error
+          path: html
+          s3-prefix: pytorch/vision/${{ github.event.pull_request.number }}