replace test docker image with original image

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

@@ -4,7 +4,6 @@ on:
   push:
     branches:
       - build_ci_docker_image*
-      - run_amd_scheduled_ci_caller_deepspeed_test
   repository_dispatch:
   workflow_call:
     inputs:
@@ -19,10 +18,264 @@ concurrency:
   cancel-in-progress: false
 
 jobs:
+  latest-docker:
+    name: "Latest PyTorch + TensorFlow [dev]"
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Cleanup disk
+        run: |
+          sudo ls -l /usr/local/lib/
+          sudo ls -l /usr/share/
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /usr/share/dotnet
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+      -
+        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: ${{ secrets.DOCKERHUB_PASSWORD }}
+      -
+        name: Build and push
+        uses: docker/build-push-action@v5
+        with:
+          context: ./docker/transformers-all-latest-gpu
+          build-args: |
+            REF=main
+          push: true
+          tags: huggingface/transformers-all-latest-gpu${{ 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-all-latest-gpu
+          build-args: |
+            REF=main
+          push: true
+          tags: huggingface/transformers-all-latest-gpu-push-ci
+
+  latest-torch-deepspeed-docker:
+    name: "Latest PyTorch + DeepSpeed"
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Cleanup disk
+        run: |
+          sudo ls -l /usr/local/lib/
+          sudo ls -l /usr/share/
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /usr/share/dotnet
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+      -
+        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: ${{ secrets.DOCKERHUB_PASSWORD }}
+      -
+        name: Build and push
+        uses: docker/build-push-action@v5
+        with:
+          context: ./docker/transformers-pytorch-deepspeed-latest-gpu
+          build-args: |
+            REF=main
+          push: true
+          tags: huggingface/transformers-pytorch-deepspeed-latest-gpu${{ inputs.image_postfix }}
+
+  # Can't build 2 images in a single job `latest-torch-deepspeed-docker` (for `nvcr.io/nvidia`)
+  latest-torch-deepspeed-docker-for-push-ci-daily-build:
+    name: "Latest PyTorch + DeepSpeed (Push CI - Daily Build)"
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Cleanup disk
+        run: |
+          sudo ls -l /usr/local/lib/
+          sudo ls -l /usr/share/
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /usr/share/dotnet
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+      -
+        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 }}
+      # 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-latest-gpu
+          build-args: |
+            REF=main
+          push: true
+          tags: huggingface/transformers-pytorch-deepspeed-latest-gpu-push-ci
+
+  doc-builder:
+    name: "Doc builder"
+    # Push CI doesn't need this image
+    if: inputs.image_postfix != '-push-ci'
+    runs-on: ubuntu-22.04
+    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-doc-builder
+          push: true
+          tags: huggingface/transformers-doc-builder
+
+  latest-pytorch:
+    name: "Latest PyTorch [dev]"
+    # Push CI doesn't need this image
+    if: inputs.image_postfix != '-push-ci'
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Cleanup disk
+        run: |
+          sudo ls -l /usr/local/lib/
+          sudo ls -l /usr/share/
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /usr/share/dotnet
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+      -
+        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-gpu
+          build-args: |
+            REF=main
+          push: true
+          tags: huggingface/transformers-pytorch-gpu
+
+# Need to be fixed with the help from Guillaume.
+#  latest-pytorch-amd:
+#    name: "Latest PyTorch (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: ${{ secrets.DOCKERHUB_PASSWORD }}
+#      - name: Build and push
+#        uses: docker/build-push-action@v5
+#        with:
+#          context: ./docker/transformers-pytorch-amd-gpu
+#          build-args: |
+#            REF=main
+#          push: true
+#          tags: huggingface/transformers-pytorch-amd-gpu${{ 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-amd-gpu
+#          build-args: |
+#            REF=main
+#          push: true
+#          tags: huggingface/transformers-pytorch-amd-gpu-push-ci
+
+  latest-tensorflow:
+    name: "Latest TensorFlow [dev]"
+    # Push CI doesn't need this image
+    if: inputs.image_postfix != '-push-ci'
+    runs-on: ubuntu-22.04
+    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-tensorflow-gpu
+          build-args: |
+            REF=main
+          push: true
+          tags: huggingface/transformers-tensorflow-gpu
+
   latest-pytorch-deepspeed-amd:
     name: "PyTorch + DeepSpeed (AMD) [dev]"
 
-    runs-on: [self-hosted, yih-dar-shieh-debug-doctest]
+    runs-on: [self-hosted, docker-gpu, amd-gpu, single-gpu, mi210]
     steps:
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
@@ -41,3 +294,16 @@ jobs:
             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

@@ -366,7 +366,7 @@ jobs:
     runs-on: [self-hosted, docker-gpu, amd-gpu, '${{ matrix.machine_type }}', '${{ inputs.gpu_flavor }}']
     needs: setup
     container:
-      image: huggingface/transformers-pytorch-deepspeed-amd-gpu-test # remove -test
+      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