Merge branch 'paged_attn' into paged_attn

.github/workflows/build_pr_documentation.yml

@@ -2,32 +2,39 @@ name: Build PR documentation
 
 on:
   pull_request:
-    branches: [ main ]
+    branches:
+      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
 jobs:
   build_documentation:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
+
     env:
       COMMIT_SHA: ${{ github.event.pull_request.head.sha }}
       PR_NUMBER: ${{ github.event.number }}
       EVENT_CONTEXT: ${{ toJSON(github.event) }}
       PR_CLONE_URL: ${{ github.event.pull_request.head.repo.clone_url }}
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
-          repository: 'huggingface/doc-builder'
+          repository: "huggingface/doc-builder"
           path: doc-builder
 
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
-          repository: 'huggingface/optimum-intel'
+          repository: "huggingface/optimum-intel"
           path: optimum-intel
 
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.9
+
       - name: Setup environment
         run: |
           pip uninstall -y doc-builder

.github/workflows/dockerfile_sanity.yml

@@ -5,40 +5,40 @@ on:
     branches:
       - main
     paths:
-      - 'docker/Dockerfile.intel'
- 
+      - "docker/Dockerfile.intel"
+
   pull_request:
     branches:
       - main
     paths:
-      - 'docker/Dockerfile.intel'
+      - "docker/Dockerfile.intel"
 
 jobs:
   build_and_run:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
 
     steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
+      - name: Checkout code
+        uses: actions/checkout@v4
 
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
 
-    - name: Build and Run Docker Image
-      run: |
-        IMAGE_NAME="intel_image:latest"
-        docker build -f docker/Dockerfile.intel -t $IMAGE_NAME .
-        if [ $? -ne 0 ]; then
-          echo "Docker image build failed."
-          exit 1
-        fi
-        CONTAINER_ID=$(docker run -d $IMAGE_NAME tail -f /dev/null)
-        if docker inspect -f '{{.State.Running}}' $CONTAINER_ID 2>/dev/null | grep -q 'true'; then
-          echo "Container is running."
-        else
-          echo "Container failed to start."
-          docker logs $CONTAINER_ID 2>/dev/null || echo "No container ID found."
-          exit 1
-        fi
-        docker stop $CONTAINER_ID
-        docker rm $CONTAINER_ID
+      - name: Build and Run Docker Image
+        run: |
+          IMAGE_NAME="intel_image:latest"
+          docker build -f docker/Dockerfile.intel -t $IMAGE_NAME .
+          if [ $? -ne 0 ]; then
+            echo "Docker image build failed."
+            exit 1
+          fi
+          CONTAINER_ID=$(docker run -d $IMAGE_NAME tail -f /dev/null)
+          if docker inspect -f '{{.State.Running}}' $CONTAINER_ID 2>/dev/null | grep -q 'true'; then
+            echo "Container is running."
+          else
+            echo "Container failed to start."
+            docker logs $CONTAINER_ID 2>/dev/null || echo "No container ID found."
+            exit 1
+          fi
+          docker stop $CONTAINER_ID
+          docker rm $CONTAINER_ID

.github/workflows/quality.yml

@@ -0,0 +1,41 @@
+name: Quality Checks
+on:
+  push:
+    branches:
+      - main
+      - v*-release
+  pull_request:
+    branches:
+      - main
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  quality:
+    runs-on: ubuntu-22.04
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.9
+
+      - name: Install dependencies
+        run: |
+          pip install --upgrade pip
+          # .[quality] installs too many dependencies
+          # TODO: we should remove the the version pinning at some point
+          pip install "black~=23.1" "ruff==0.4.4"
+
+      - name: Check style with black
+        run: |
+          black --check .
+
+      - name: Check style with ruff
+        run: |
+          ruff check .

.github/workflows/security.yml

@@ -9,6 +9,7 @@ permissions:
 jobs:
   secrets:
     runs-on: ubuntu-latest
+
     steps:
       - shell: bash
         run: |

.github/workflows/test_generation.yml

@@ -1,38 +1,36 @@
-# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
-# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
-name: Intel Generation Utils - Test
+name: Generation Utils - Test (deprecated)
 
 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:
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: [3.8, 3.9]
-        os: [ubuntu-latest]
+    runs-on: ubuntu-22.04
 
-    runs-on: ${{ matrix.os }}
     steps:
-    - uses: actions/checkout@v2
-    - name: Setup Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
-      with:
-        python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install transformers==4.43.*
-        pip install optimum[exporters]
-        pip install .[tests]
-    - name: Test with Pytest
-      run: |
-        pytest tests/generation/
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.9
+
+      - name: Install dependencies
+        run: |
+          pip install --upgrade pip
+          pip install .[tests] transformers[testing]==4.43.*
+
+      - name: Test with Pytest
+        run: |
+          pytest tests/generation/

.github/workflows/test_inc.yml

@@ -1,6 +1,4 @@
-# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
-# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
-name: Intel Neural Compressor - Test
+name: INC - Test
 
 on:
   push:
@@ -20,31 +18,34 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: [3.8, 3.9]
-        os: [ubuntu-latest]
+        torch-version: ["2.2.0", "2.3.*", "2.4.*"]
+
+    runs-on: ubuntu-22.04
 
-    runs-on: ${{ matrix.os }}
     steps:
-    - uses: actions/checkout@v2
-    - name: Setup Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
-      with:
-        python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install cmake
-        pip install py-cpuinfo
-        pip install torch==2.3.0 torchaudio==2.3.0 torchvision==0.18 --index-url https://download.pytorch.org/whl/cpu
-        pip install intel-extension-for-pytorch==2.3.0
-        pip install datasets==2.19.0
-        pip install .[neural-compressor,diffusers,tests]
-        pip install peft
-
-    - name: Test with Pytest
-      run: |
-        pytest tests/neural_compressor/ --ignore tests/neural_compressor/test_ipex.py --durations=0
-    - name: Test IPEX
-      run: |
-        pytest tests/neural_compressor/test_ipex.py
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.9
+
+      - name: Install dependencies
+        run: |
+          pip install --upgrade pip
+          pip install torch==${{ matrix.torch-version }} torchaudio torchvision --index-url https://download.pytorch.org/whl/cpu
+          pip install .[neural-compressor,ipex,diffusers,peft,tests] transformers[testing] intel-extension-for-pytorch==${{ matrix.torch-version }}
+
+      - if: ${{ matrix.torch-version == '2.2.0' }}
+        name: Downgrade Numpy
+        run: pip install numpy==1.*
+
+      - name: Assert versions
+        run: |
+          python -c "import torch; print(torch.__version__); assert torch.__version__.startswith('${{ matrix.torch-version }}'.replace('.*', ''))"
+          python -c "import intel_extension_for_pytorch; print(intel_extension_for_pytorch.__version__); assert intel_extension_for_pytorch.__version__.startswith('${{ matrix.torch-version }}'.replace('.*', ''))"
 
+      - name: Test with Pytest
+        run: |
+          pytest tests/neural_compressor