Merge branch 'main' into check-tests

.github/workflows/check_code_quality.yml

@@ -51,4 +51,4 @@ jobs:
     - name: Check style with ruff
       run: |
         source venv/bin/activate
-        ruff .
+        ruff check .

.github/workflows/security.yml

@@ -0,0 +1,29 @@
+name: Security Checks
+
+on:
+  push:
+
+permissions:
+  contents: read
+
+jobs:
+  secrets:
+    runs-on: ubuntu-latest
+    steps:
+      - shell: bash
+        run: |
+          if [ "${{ github.event_name }}" == "push" ]; then
+            echo "depth=$(($(jq length <<< '${{ toJson(github.event.commits) }}') + 2))" >> $GITHUB_ENV
+            echo "branch=${{ github.ref_name }}" >> $GITHUB_ENV
+          fi
+          if [ "${{ github.event_name }}" == "pull_request" ]; then
+            echo "depth=$((${{ github.event.pull_request.commits }}+2))" >> $GITHUB_ENV
+            echo "branch=${{ github.event.pull_request.head.ref }}" >> $GITHUB_ENV
+          fi
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{env.branch}}
+          fetch-depth: ${{env.depth}}
+      - name: Scan for secrets
+        uses: trufflesecurity/trufflehog@main

.github/workflows/test_inc.yml

@@ -4,9 +4,12 @@ name: Intel Neural Compressor - Test
 
 on:
   push:
-    branches: [ main ]
+    branches:
+      - main
+      - v*-release
   pull_request:
-    branches: [ main ]
+    branches:
+      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}

.github/workflows/test_ipex.yml

@@ -4,23 +4,31 @@ name: Intel IPEX - Test
 
 on:
   push:
-    branches: [ main ]
+    branches:
+      - main
+      - v*-release
   pull_request:
-    branches: [ main ]
+    branches:
+      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
 jobs:
   build:
+    runs-on: ubuntu-latest
     strategy:
       fail-fast: false
       matrix:
-        python-version: [3.8, 3.9]
-        os: [ubuntu-latest]
+        python-version: [3.9]
+        transformers-version: [4.39.0, 4.42.3]
+        ipex-version: [2.2.0, 2.3.*]
+        include:
+          - python-version: 3.8
+            transformers-version: 4.39.0
+            ipex-version: 2.2.0
 
-    runs-on: ${{ matrix.os }}
     steps:
     - uses: actions/checkout@v2
     - name: Setup Python ${{ matrix.python-version }}
@@ -30,8 +38,11 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install torch torchaudio torchvision --extra-index-url https://download.pytorch.org/whl/cpu
-        pip install .[ipex,tests]
+        pip install torch==${{ matrix.ipex-version }} --extra-index-url https://download.pytorch.org/whl/cpu
+        pip install intel_extension_for_pytorch==${{ matrix.ipex-version }}
+        pip install Pillow parameterized
+        pip install transformers[testing]==${{ matrix.transformers-version }}
+        pip install .[ipex]
     - name: Test with Pytest
       run: |
-        pytest tests/ipex/
+        pytest tests/ipex/

.github/workflows/test_openvino.yml

@@ -4,9 +4,12 @@ name: OpenVINO - Test
 
 on:
   push:
-    branches: [ main ]
+    branches:
+      - main
+      - v*-release
   pull_request:
-    branches: [ main ]
+    branches:
+      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
@@ -17,23 +20,27 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: [3.8, 3.11]
+        python-version: ["3.8", "3.12"]
+        transformers-version: ["4.36.0", "4.42.*"]
         os: [ubuntu-latest]
 
     runs-on: ${{ matrix.os }}
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
     - name: Setup Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
         # install PyTorch CPU version to avoid installing CUDA packages on GitHub runner without GPU
         pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+        pip install transformers==${{ matrix.transformers-version }}
         pip install .[openvino,openvino-tokenizers,tests,diffusers] onnxruntime
     - name: Test with Pytest
+      env:
+        HF_HUB_READ_TOKEN: ${{ secrets.HF_HUB_READ_TOKEN }}
       run: |
         pytest tests/openvino/ --ignore tests/openvino/test_modeling_basic.py --durations=0
     - name: Test basic
@@ -46,3 +53,4 @@ jobs:
         pip install openvino-nightly
         python -c "from optimum.intel import OVModelForCausalLM; OVModelForCausalLM.from_pretrained('hf-internal-testing/tiny-random-gpt2', export=True, compile=False)"
         optimum-cli export openvino -m hf-internal-testing/tiny-random-gpt2 gpt2-ov
+

.github/workflows/test_openvino_basic.yml

@@ -5,35 +5,37 @@ on:
   schedule:
     - cron:  '41 1 * * *'  # run every day at 1:41
   push:
-    paths:
-    - 'tests/openvino/test_modeling_basic.py'
-    - '.github/workflows/test_openvino_basic.yml'
+    branches:
+      - v*-release
   pull_request:
-    paths:
-    - 'tests/openvino/test_modeling_basic.py'
-    - '.github/workflows/test_openvino_basic.yml'
+    types: [opened, synchronize, reopened, labeled]
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
 jobs:
   build:
+    if: ${{ (github.event_name == 'workflow_dispatch') || (github.event_name == 'schedule') ||  (github.event_name == 'push') || contains( github.event.pull_request.labels.*.name, 'openvino-test') }}
     strategy:
       fail-fast: false
       matrix:
         # Testing lower and upper bound of supported Python versions
         # This also ensures that the test fails if dependencies break for Python 3.7
-        python-version: ["3.8", "3.11"]
-        transformers: ['transformers']
-        optimum: ['optimum', 'git+https://github.com/huggingface/optimum.git']
+        python-version: ["3.8", "3.12"]
+        os: ["ubuntu-22.04", "windows-latest"]
+        transformers-version: ["4.42.*"]
+        include:
+          - transformers-version: "4.36.0"
+            python-version: "3.12"
+            os: "ubuntu-22.04"
 
-    runs-on: ubuntu-20.04
+    runs-on: ${{ matrix.os }}
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
     - name: Setup Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
 
@@ -43,12 +45,19 @@ jobs:
         # optimum or transformers to a specific version
         # Install PyTorch CPU to prevent unnecessary downloading/installing of CUDA packages
         pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
-        pip install .[tests] openvino onnx onnxruntime ${{ matrix.optimum}} ${{ matrix.transformers }}
+        pip install transformers==${{ matrix.transformers-version }}
+        pip install .[tests] openvino
 
-    - name: Pip freeze        
+    - name: Pip freeze
       run: pip freeze
 
     - name: Test with Pytest
       run: |
         pytest tests/openvino/test_modeling_basic.py
-        RUN_SLOW=1 pytest tests/openvino/test_modeling.py -s -m "run_slow" --durations=0
+
+    - name: Slow tests
+      run: |
+        pip install nncf
+        pytest tests/openvino -s -m "run_slow" --durations=0
+      env:
+        RUN_SLOW: 1

.github/workflows/test_openvino_examples.yml

@@ -22,7 +22,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.11"]
+        python-version: ["3.8", "3.12"]
 
     runs-on: ubuntu-22.04
 

.github/workflows/test_openvino_notebooks.yml

@@ -23,7 +23,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.11"]
+        python-version: ["3.8", "3.12"]
 
     runs-on: ubuntu-22.04
 

README.md

@@ -239,3 +239,8 @@ Do not forget to install requirements for every example:
 cd <example-folder>
 pip install -r requirements.txt
 ```
+
+
+## Gaudi
+
+To train your model on [Intel Gaudi AI Accelerators (HPU)](https://docs.habana.ai/en/latest/index.html), check out [Optimum Habana](https://github.com/huggingface/optimum-habana) which provides a set of tools enabling easy model loading, training and inference on single- and multi-HPU settings for different downstream tasks. After training your model, feel free to submit it to the Intel [leaderboard](https://huggingface.co/spaces/Intel/powered_by_intel_llm_leaderboard) which is designed to evaluate, score, and rank open-source LLMs that have been pre-trained or fine-tuned on Intel Hardwares. Models submitted to the leaderboard will be evaluated on the Intel Developer Cloud. The evaluation platform consists of Gaudi Accelerators and Xeon CPUs running benchmarks from the Eleuther AI Language Model Evaluation Harness.

docker/Dockerfile.intel

@@ -9,10 +9,10 @@
 #           https://docs.docker.com/develop/develop-images/build_enhancements/
 
 ARG BASE_IMAGE=ubuntu:22.04
-FROM ${BASE_IMAGE} AS dev-base
+FROM ${BASE_IMAGE}
+
 RUN --mount=type=cache,id=apt-dev,target=/var/cache/apt \
-    apt-get update && \
-    DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y \
+    sh -c "apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y \
     ca-certificates \
     git \
     curl \
@@ -25,46 +25,29 @@ RUN --mount=type=cache,id=apt-dev,target=/var/cache/apt \
     libjpeg-dev \
     pybind11-dev \
     libpng-dev \
-    pybind11-dev \
-    && rm -rf /var/lib/apt/lists/*
+    python3 \
+    python3-pip \
+    && rm -rf /var/lib/apt/lists/*"
 RUN /usr/sbin/update-ccache-symlinks
 RUN mkdir /opt/ccache && ccache --set-config=cache_dir=/opt/ccache
-ENV PATH /opt/conda/bin:$PATH
 
-FROM dev-base as conda
-ARG PYTHON_VERSION=3.10
-RUN curl -fsSL -v -o ~/miniconda.sh -O  https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh  && \
-    chmod +x ~/miniconda.sh && \
-    ~/miniconda.sh -b -p /opt/conda && \
-    rm ~/miniconda.sh && \
-    /opt/conda/bin/conda install -y python=${PYTHON_VERSION} conda-build pyyaml numpy ipython mkl mkl-include ninja cython typing pybind11 Pillow && \
-    /opt/conda/bin/conda clean -ya
+ARG IPEX_VERSION=2.3.100
+ARG PYTORCH_VERSION=2.3.1
+ARG TORCHVISION_VERSION=0.18.1+cpu
+ARG TORCHAUDIO_VERSION=2.3.1+cpu
 
-FROM dev-base AS build
-ARG IPEX_VERSION=v1.13.0
-ARG PYTORCH_VERSION=v1.13.0
-ARG TORCHVISION_VERSION=0.13.0+cpu
-ARG TORCHAUDIO_VERSION=0.13.0+cpu
-COPY --from=conda /opt/conda /opt/conda
-RUN --mount=type=cache,target=/opt/ccache \
-    python -m pip install --no-cache-dir torch==${PYTORCH_VERSION}+cpu torchvision==${TORCHVISION_VERSION} torchaudio==${TORCHAUDIO_VERSION} -f https://download.pytorch.org/whl/torch_stable.html && \
-    git clone https://github.com/intel/intel-extension-for-pytorch && \
-    cd intel-extension-for-pytorch && \
-    git checkout ${IPEX_VERSION} && \
-    git submodule sync && \
-    git submodule update --init --recursive && \
-    python -m pip install --no-cache-dir -r requirements.txt && \
-    python setup.py bdist_wheel && \
-    python -m pip install --no-cache-dir dist/*.whl && \
-    cd .. && rm -rf intel-extension-for-pytorch
+RUN python3 -m pip install --no-cache-dir \
+    torch==${PYTORCH_VERSION}+cpu \
+    torchvision==${TORCHVISION_VERSION} \
+    torchaudio==${TORCHAUDIO_VERSION} \
+    -f https://download.pytorch.org/whl/torch_stable.html && \
+    python3 -m pip install intel-extension-for-pytorch==$IPEX_VERSION && \
+    python3 -m pip install oneccl_bind_pt --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/cpu/us/
 
-FROM dev-base as dev
-COPY --from=build /opt/conda /opt/conda
 ARG OMP_NUM_THREADS=1
-ENV OMP_NUM_THREADS ${OMP_NUM_THREADS}
+ENV OMP_NUM_THREADS=${OMP_NUM_THREADS}
 ARG KMP_BLOCKTIME=1
-ENV KMP_BLOCKTIME ${KMP_BLOCKTIME}
+ENV KMP_BLOCKTIME=${KMP_BLOCKTIME}
 ARG KMP_HW_SUBSET=1T
-ENV KMP_HW_SUBSET ${KMP_HW_SUBSET}
-ENV LD_PRELOAD "/opt/conda/lib/libiomp5.so /usr/lib/x86_64-linux-gnu/libtcmalloc.so"
-ENV LD_LIBRARY_PATH "/opt/conda/lib/python3.8/site-packages/lib/"
+ENV KMP_HW_SUBSET=${KMP_HW_SUBSET}
+ENV LD_PRELOAD="/usr/local/lib/libiomp5.so /usr/lib/x86_64-linux-gnu/libtcmalloc.so"

docs/Dockerfile

@@ -25,4 +25,4 @@ RUN npm install [email protected] -g && \
 RUN python3 -m pip install --no-cache-dir --upgrade pip
 RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/doc-builder.git
 RUN git clone $clone_url && cd optimum-intel && git checkout $commit_sha
-RUN python3 -m pip install --no-cache-dir ./optimum-intel[neural-compressor,openvino,nncf,quality]
+RUN python3 -m pip install --no-cache-dir ./optimum-intel[neural-compressor,openvino,diffusers,quality]

docs/source/_toctree.yml

@@ -4,20 +4,31 @@
   - local: installation
     title: Installation
   - sections:
-    - local: optimization_inc
+    - local: neural_compressor/optimization
       title: Optimization
-    - local: distributed_training
+    - local: neural_compressor/distributed_training
       title: Distributed Training
-    - local: reference_inc
+    - local: neural_compressor/reference
       title: Reference
     title: Neural Compressor
   - sections:
-    - local: inference
-      title: Models for inference
-    - local: optimization_ov
+    - local: openvino/export
+      title: Export
+    - local: openvino/inference
+      title: Inference
+    - local: openvino/optimization
       title: Optimization
-    - local: reference_ov
+    - local: openvino/models
+      title: Supported Models
+    - local: openvino/reference
       title: Reference
+    - sections:
+      - local: openvino/tutorials/notebooks
+        title: Notebooks
+      - local: openvino/tutorials/diffusers
+        title: Generate images with Diffusion models
+      title: Tutorials
+      isExpanded: false
     title: OpenVINO
   title: Optimum Intel
   isExpanded: false

docs/source/index.mdx

@@ -25,11 +25,11 @@ limitations under the License.
 
 <div class="mt-10">
   <div class="w-full flex flex-col space-x-4 md:grid md:grid-cols-2 md:gap-x-5">
-    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./optimization_inc"
+    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="neural_compressor/optimization"
       ><div class="w-full text-center bg-gradient-to-br from-blue-400 to-blue-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Neural Compressor</div>
       <p class="text-gray-700">Learn how to apply compression techniques such as quantization, pruning and knowledge distillation to speed up inference with Intel Neural Compressor.</p>
     </a>
-    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./inference"
+    <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="openvino/export"
       ><div class="w-full text-center bg-gradient-to-br from-purple-400 to-purple-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">OpenVINO</div>
       <p class="text-gray-700">Learn how to run inference with OpenVINO Runtime and to apply quantization, pruning and knowledge distillation on your model to further speed up inference.</p>
     </a>