update

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

@@ -3,7 +3,7 @@ name: Build docker images (scheduled)
 on:
   push:
     branches:
-      - build_ci_docker_image*
+      - flex_attn_example
   repository_dispatch:
   workflow_call:
     inputs:
@@ -43,351 +43,4 @@ jobs:
           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
-
-      - name: Post to Slack
-        if: always()
-        uses: huggingface/hf-workflows/.github/actions/post-slack@main
-        with:
-          slack_channel: ${{ secrets.CI_SLACK_CHANNEL_DOCKER }}
-          title: 🤗 Results of the transformers-all-latest-gpu-push-ci docker build 
-          status: ${{ job.status }}
-          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
-
-  latest-torch-deepspeed-docker:
-    name: "Latest PyTorch + DeepSpeed"
-    runs-on:
-      group: aws-general-8-plus
-    steps:
-      -
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      -
-        name: Check out code
-        uses: actions/checkout@v4
-      -
-        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 }}
-
-      - name: Post to Slack
-        if: always()
-        uses: huggingface/hf-workflows/.github/actions/post-slack@main
-        with:
-          slack_channel: ${{ secrets.CI_SLACK_CHANNEL_DOCKER}}
-          title: 🤗 Results of the transformers-pytorch-deepspeed-latest-gpu docker build 
-          status: ${{ job.status }}
-          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
-
-  # 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:
-      group: aws-general-8-plus
-    steps:
-      -
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      -
-        name: Check out code
-        uses: actions/checkout@v4
-      -
-        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
-
-      - name: Post to Slack
-        if: always()
-        uses: huggingface/hf-workflows/.github/actions/post-slack@main
-        with:
-          slack_channel: ${{ secrets.CI_SLACK_CHANNEL_DOCKER }}
-          title: 🤗 Results of the transformers-pytorch-deepspeed-latest-gpu-push-ci docker build 
-          status: ${{ job.status }}
-          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
-
-  doc-builder:
-    name: "Doc builder"
-    # Push CI doesn't need this image
-    if: inputs.image_postfix != '-push-ci'
-    runs-on:
-      group: aws-general-8-plus
-    steps:
-      -
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      -
-        name: Check out code
-        uses: actions/checkout@v4
-      -
-        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
-
-      - name: Post to Slack
-        if: always()
-        uses: huggingface/hf-workflows/.github/actions/post-slack@main
-        with:
-          slack_channel: ${{ secrets.CI_SLACK_CHANNEL_DOCKER }}
-          title: 🤗 Results of the huggingface/transformers-doc-builder docker build 
-          status: ${{ job.status }}
-          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
-
-  latest-pytorch:
-    name: "Latest PyTorch [dev]"
-    # Push CI doesn't need this image
-    if: inputs.image_postfix != '-push-ci'
-    runs-on:
-      group: aws-general-8-plus
-    steps:
-      -
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      -
-        name: Check out code
-        uses: actions/checkout@v4
-      -
-        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
-
-      - name: Post to Slack
-        if: always()
-        uses: huggingface/hf-workflows/.github/actions/post-slack@main
-        with:
-          slack_channel: ${{ secrets.CI_SLACK_CHANNEL_DOCKER }}
-          title: 🤗 Results of the huggingface/transformers-pytorch-gpudocker build 
-          status: ${{ job.status }}
-          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
-
-  latest-pytorch-amd:
-    name: "Latest PyTorch (AMD) [dev]"
-    runs-on:
-      group: aws-general-8-plus
-    steps:
-      - 
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      - 
-        name: Check out code
-        uses: actions/checkout@v4
-      - 
-        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
-
-      - name: Post to Slack
-        if: always()
-        uses: huggingface/hf-workflows/.github/actions/post-slack@main
-        with:
-          slack_channel: ${{ secrets.CI_SLACK_CHANNEL_DOCKER }}
-          title: 🤗 Results of the huggingface/transformers-pytorch-amd-gpu-push-ci build 
-          status: ${{ job.status }}
-          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
-
-  latest-tensorflow:
-    name: "Latest TensorFlow [dev]"
-    # Push CI doesn't need this image
-    if: inputs.image_postfix != '-push-ci'
-    runs-on:
-      group: aws-general-8-plus
-    steps:
-      -
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      -
-        name: Check out code
-        uses: actions/checkout@v4
-      -
-        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
-
-      - name: Post to Slack
-        if: always()
-        uses: huggingface/hf-workflows/.github/actions/post-slack@main
-        with:
-          slack_channel: ${{ secrets.CI_SLACK_CHANNEL_DOCKER }}
-          title: 🤗 Results of the huggingface/transformers-tensorflow-gpu build 
-          status: ${{ job.status }}
-          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
-
-  latest-pytorch-deepspeed-amd:
-    name: "PyTorch + DeepSpeed (AMD) [dev]"
-    runs-on:
-      group: aws-general-8-plus
-    steps:
-      - 
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      - 
-        name: Check out code
-        uses: actions/checkout@v4
-      - 
-        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
-
-      - name: Post to Slack
-        if: always()
-        uses: huggingface/hf-workflows/.github/actions/post-slack@main
-        with:
-          slack_channel: ${{ secrets.CI_SLACK_CHANNEL_DOCKER }}
-          title: 🤗 Results of the transformers-pytorch-deepspeed-amd-gpu build 
-          status: ${{ job.status }}
-          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
-
-  latest-quantization-torch-docker:
-    name: "Latest Pytorch + Quantization [dev]"
-     # Push CI doesn't need this image
-    if: inputs.image_postfix != '-push-ci'
-    runs-on:
-      group: aws-general-8-plus
-    steps:
-      -
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      -
-        name: Check out code
-        uses: actions/checkout@v4
-      -
-        name: Login to DockerHub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_PASSWORD }}
-      -
-        name: Build and push
-        uses: docker/build-push-action@v5
-        with:
-          context: ./docker/transformers-quantization-latest-gpu
-          build-args: |
-            REF=main
-          push: true
-          tags: huggingface/transformers-quantization-latest-gpu${{ inputs.image_postfix }}
-
-      - name: Post to Slack
-        if: always()
-        uses: huggingface/hf-workflows/.github/actions/post-slack@main
-        with:
-          slack_channel: ${{ secrets.CI_SLACK_CHANNEL_DOCKER }}
-          title: 🤗 Results of the transformers-quantization-latest-gpu build 
-          status: ${{ job.status }}
-          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
+          tags: huggingface/transformers-all-latest-gpu${{ inputs.image_postfix }}-test

docker/transformers-all-latest-gpu/Dockerfile

@@ -1,4 +1,4 @@
-FROM nvidia/cuda:12.1.0-cudnn8-devel-ubuntu20.04
+FROM nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04
 LABEL maintainer="Hugging Face"
 
 ARG DEBIAN_FRONTEND=noninteractive
@@ -6,14 +6,6 @@ ARG DEBIAN_FRONTEND=noninteractive
 # Use login shell to read variables from `~/.profile` (to pass dynamic created variables between RUN commands)
 SHELL ["sh", "-lc"]
 
-# The following `ARG` are mainly used to specify the versions explicitly & directly in this docker file, and not meant
-# to be used as arguments for docker build (so far).
-
-ARG PYTORCH='2.4.0'
-# (not always a valid torch version)
-ARG INTEL_TORCH_EXT='2.3.0'
-# Example: `cu102`, `cu113`, etc.
-ARG CUDA='cu121'
 
 RUN apt update
 RUN apt install -y git libsndfile1-dev tesseract-ocr espeak-ng python3 python3-pip ffmpeg git-lfs
@@ -26,44 +18,8 @@ RUN git clone https://github.com/huggingface/transformers && cd transformers &&
 # 1. Put several commands in a single `RUN` to avoid image/layer exporting issue. Could be revised in the future.
 # 2. Regarding `torch` part, We might need to specify proper versions for `torchvision` and `torchaudio`.
 #    Currently, let's not bother to specify their versions explicitly (so installed with their latest release versions).
-RUN python3 -m pip install --no-cache-dir -U tensorflow==2.13 protobuf==3.20.3 tensorflow_text tensorflow_probability && python3 -m pip install --no-cache-dir -e ./transformers[dev,onnxruntime] && [ ${#PYTORCH} -gt 0 -a "$PYTORCH" != "pre" ] && VERSION='torch=='$PYTORCH'.*' ||  VERSION='torch'; echo "export VERSION='$VERSION'" >> ~/.profile && echo torch=$VERSION && [ "$PYTORCH" != "pre" ] && python3 -m pip install --no-cache-dir -U $VERSION torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/$CUDA || python3 -m pip install --no-cache-dir -U --pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/$CUDA
+RUN python3 -m pip install --no-cache-dir -U torch==2.5.0 --index-url https://download.pytorch.org/whl/test/cu124
 
-RUN python3 -m pip uninstall -y flax jax
-
-RUN python3 -m pip install --no-cache-dir intel_extension_for_pytorch==$INTEL_TORCH_EXT -f https://developer.intel.com/ipex-whl-stable-cpu
-
-RUN python3 -m pip install --no-cache-dir git+https://github.com/facebookresearch/detectron2.git pytesseract
-RUN python3 -m pip install -U "itsdangerous<2.1.0"
-
-RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/accelerate@main#egg=accelerate
-
-RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/peft@main#egg=peft
-
-# For bettertransformer
-RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/optimum@main#egg=optimum
-
-# For video model testing
-RUN python3 -m pip install --no-cache-dir decord av==9.2.0
-
-# Some slow tests require bnb
-RUN python3 -m pip install --no-cache-dir bitsandbytes
-
-# Some tests require quanto
-RUN python3 -m pip install --no-cache-dir quanto
-
-# `quanto` will install `ninja` which leads to many `CUDA error: an illegal memory access ...` in some model tests
-# (`deformable_detr`, `rwkv`, `mra`)
-RUN python3 -m pip uninstall -y ninja
-
-# For `dinat` model
-# The `XXX` part in `torchXXX` needs to match `PYTORCH` (to some extent)
-RUN python3 -m pip install --no-cache-dir natten==0.15.1+torch220$CUDA -f https://shi-labs.com/natten/wheels
-
-# For `nougat` tokenizer
-RUN python3 -m pip install --no-cache-dir python-Levenshtein
-
-# For `FastSpeech2ConformerTokenizer` tokenizer
-RUN python3 -m pip install --no-cache-dir g2p-en
 
 # 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.