Merge remote-tracking branch 'upstream/main' into feature/directml

kazssym · kazssym · commit 1fdce26d0476 · 2025-03-08T17:40:46.000+09:00
diff --git a/.github/workflows/build_main_documentation.yml b/.github/workflows/build_main_documentation.yml
@@ -186,7 +186,7 @@ jobs:
       - name: Combine subpackage documentation
         run: |
           cd optimum
-          sudo python docs/combine_docs.py --subpackages nvidia amd intel neuron tpu habana furiosa --version ${{ env.VERSION }}
+          sudo python docs/combine_docs.py --subpackages nvidia amd intel neuron tpu habana furiosa executorch --version ${{ env.VERSION }}
           cd ..
 
       - name: Push to repositories
diff --git a/.github/workflows/build_pr_documentation.yml b/.github/workflows/build_pr_documentation.yml
@@ -120,7 +120,7 @@ jobs:
       - name: Combine subpackage documentation
         run: |
           cd optimum
-          sudo python docs/combine_docs.py --subpackages nvidia amd intel neuron tpu habana furiosa --version pr_$PR_NUMBER
+          sudo python docs/combine_docs.py --subpackages nvidia amd intel neuron tpu habana furiosa executorch --version pr_$PR_NUMBER
           sudo mv optimum-doc-build ../
           cd ..
 
diff --git a/.github/workflows/check_code_quality.yml b/.github/workflows/check_code_quality.yml
@@ -17,7 +17,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: [3.9]
-        os: [ubuntu-20.04]
+        os: [ubuntu-22.04]
 
     runs-on: ${{ matrix.os }}
     steps:
diff --git a/.github/workflows/dev_test_benckmark.yml b/.github/workflows/dev_test_benckmark.yml
@@ -13,7 +13,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ['3.9', '3.11']
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
     - uses: actions/checkout@v2
     - name: Setup Python ${{ matrix.python-version }}
diff --git a/.github/workflows/dev_test_bettertransformer.yml b/.github/workflows/dev_test_bettertransformer.yml
@@ -13,7 +13,7 @@ jobs:
       fail-fast: false
       matrix:
         os:
-        - ubuntu-20.04
+        - ubuntu-22.04
         - macos-13
     runs-on: ${{ matrix.os }}
     steps:
diff --git a/.github/workflows/dev_test_dummy_inputs.yml b/.github/workflows/dev_test_dummy_inputs.yml
@@ -14,7 +14,7 @@ jobs:
       matrix:
         python-version: ['3.9', '3.11']
         os:
-        - ubuntu-20.04
+        - ubuntu-22.04
         - macos-13
     runs-on: ${{ matrix.os }}
     steps:
diff --git a/.github/workflows/dev_test_exporters.yml b/.github/workflows/dev_test_exporters.yml
@@ -13,7 +13,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ['3.9', '3.11']
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
     - uses: actions/checkout@v2
     - name: Setup Python ${{ matrix.python-version }}
diff --git a/.github/workflows/dev_test_fx.yml b/.github/workflows/dev_test_fx.yml
@@ -14,7 +14,7 @@ jobs:
       matrix:
         python-version: ['3.9', '3.11']
         os:
-        - ubuntu-20.04
+        - ubuntu-22.04
         - macos-13
     runs-on: ${{ matrix.os }}
     steps:
diff --git a/.github/workflows/dev_test_onnx.yml b/.github/workflows/dev_test_onnx.yml
@@ -14,7 +14,7 @@ jobs:
       matrix:
         python-version: ['3.9', '3.11']
         os:
-        - ubuntu-20.04
+        - ubuntu-22.04
         - macos-13
     runs-on: ${{ matrix.os }}
     steps:
diff --git a/.github/workflows/dev_test_onnxruntime.yml b/.github/workflows/dev_test_onnxruntime.yml
@@ -14,7 +14,7 @@ jobs:
       matrix:
         python-version: ['3.9', '3.11']
         os:
-        - ubuntu-20.04
+        - ubuntu-22.04
         - windows-2019
         - macos-13
     runs-on: ${{ matrix.os }}
diff --git a/.github/workflows/dev_test_optimum_common.yml b/.github/workflows/dev_test_optimum_common.yml
@@ -14,7 +14,7 @@ jobs:
       matrix:
         python-version: ['3.9', '3.11']
         os:
-        - ubuntu-20.04
+        - ubuntu-22.04
         - windows-2019
         - macos-13
     runs-on: ${{ matrix.os }}
@@ -38,5 +38,5 @@ jobs:
         # Setting HUGGINGFACE_CO_STAGING to true for only one job of the matrix
         as the staging tests cannot run in parallel.
         export HUGGINGFACE_CO_STAGING=${{ matrix.python-version == 3.8 && matrix.os
-        == ubuntu-20.04 }}
+        == ubuntu-22.04 }}
         python -m unittest discover -s tests -p test_*.py
diff --git a/.github/workflows/test_benckmark.yml b/.github/workflows/test_benckmark.yml
@@ -18,7 +18,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: [3.9]
-        os: [ubuntu-20.04]
+        os: [ubuntu-22.04]
 
     runs-on: ${{ matrix.os }}
     steps:
diff --git a/.github/workflows/test_bettertransformer.yml b/.github/workflows/test_bettertransformer.yml
@@ -16,7 +16,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: [3.9]
-        os: [ubuntu-20.04]
+        os: [ubuntu-22.04]
 
     runs-on: ${{ matrix.os }}
     steps:
@@ -32,7 +32,7 @@ jobs:
         run: |
           pip install .[tests]
           pip install --no-cache-dir --upgrade torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
-          pip install accelerate
+          pip install accelerate transformers==4.48.*
 
       - name: Test with stable pytorch
         working-directory: tests
diff --git a/.github/workflows/test_cli.yml b/.github/workflows/test_cli.yml
@@ -18,7 +18,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: [3.9]
-        os: [ubuntu-20.04, macos-13]
+        os: [ubuntu-22.04, macos-13]
 
     runs-on: ${{ matrix.os }}
     steps:
diff --git a/.github/workflows/test_export_onnx.yml b/.github/workflows/test_export_onnx.yml
@@ -16,7 +16,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.9"]
-        os: [ubuntu-20.04]
+        os: [ubuntu-22.04]
 
     runs-on: ${{ matrix.os }}
     steps:
diff --git a/.github/workflows/test_export_onnx_cli.yml b/.github/workflows/test_export_onnx_cli.yml
@@ -18,7 +18,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.9"]
-        os: [ubuntu-20.04]
+        os: [ubuntu-22.04]
 
     runs-on: ${{ matrix.os }}
 
diff --git a/.github/workflows/test_export_onnx_cli_timm.yml b/.github/workflows/test_export_onnx_cli_timm.yml
@@ -15,7 +15,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: [3.9]
-        os: [ubuntu-20.04]
+        os: [ubuntu-22.04]
 
     runs-on: ${{ matrix.os }}
     steps:
diff --git a/.github/workflows/test_export_onnx_timm.yml b/.github/workflows/test_export_onnx_timm.yml
@@ -15,7 +15,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: [3.9]
-        os: [ubuntu-20.04]
+        os: [ubuntu-22.04]
 
     runs-on: ${{ matrix.os }}
     steps:
diff --git a/.github/workflows/test_export_tflite.yml b/.github/workflows/test_export_tflite.yml
@@ -22,7 +22,7 @@ jobs:
       matrix:
         python-version: ['3.9', '3.11']
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
     - uses: actions/checkout@v2
     - name: Setup Python ${{ matrix.python-version }}
diff --git a/.github/workflows/test_export_tflite_cli.yml b/.github/workflows/test_export_tflite_cli.yml
@@ -22,7 +22,7 @@ jobs:
       matrix:
         python-version: ['3.9', '3.11']
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
     - uses: actions/checkout@v2
     - name: Setup Python ${{ matrix.python-version }}
diff --git a/.github/workflows/test_export_tflite_cli_dynamic_quantization_int8.yml b/.github/workflows/test_export_tflite_cli_dynamic_quantization_int8.yml
@@ -22,7 +22,7 @@ jobs:
       matrix:
         python-version: ['3.9']
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
     - uses: actions/checkout@v2
     - name: Setup Python ${{ matrix.python-version }}
diff --git a/.github/workflows/test_export_tflite_cli_quantization_fp16.yml b/.github/workflows/test_export_tflite_cli_quantization_fp16.yml
@@ -22,7 +22,7 @@ jobs:
       matrix:
         python-version: ['3.9']
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
     - uses: actions/checkout@v2
     - name: Setup Python ${{ matrix.python-version }}
diff --git a/.github/workflows/test_export_tflite_cli_quantization_full_int8.yml b/.github/workflows/test_export_tflite_cli_quantization_full_int8.yml
@@ -22,7 +22,7 @@ jobs:
       matrix:
         python-version: ['3.9']
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
     - uses: actions/checkout@v2
     - name: Setup Python ${{ matrix.python-version }}
diff --git a/.github/workflows/test_export_tflite_cli_quantization_int8_custom_dataset.yml b/.github/workflows/test_export_tflite_cli_quantization_int8_custom_dataset.yml
@@ -22,7 +22,7 @@ jobs:
       matrix:
         python-version: ['3.9']
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
     - uses: actions/checkout@v2
     - name: Setup Python ${{ matrix.python-version }}
diff --git a/.github/workflows/test_export_tflite_cli_quantization_int8_default_dataset.yml b/.github/workflows/test_export_tflite_cli_quantization_int8_default_dataset.yml
@@ -22,7 +22,7 @@ jobs:
       matrix:
         python-version: ['3.9']
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
     - uses: actions/checkout@v2
     - name: Setup Python ${{ matrix.python-version }}
diff --git a/.github/workflows/test_export_tflite_cli_quantization_int8x16.yml b/.github/workflows/test_export_tflite_cli_quantization_int8x16.yml
@@ -22,7 +22,7 @@ jobs:
       matrix:
         python-version: ['3.9']
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
     - uses: actions/checkout@v2
     - name: Setup Python ${{ matrix.python-version }}
diff --git a/.github/workflows/test_exporters_common.yml b/.github/workflows/test_exporters_common.yml
@@ -17,7 +17,7 @@ jobs:
       matrix:
         python-version: ['3.9', '3.11']
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
     - uses: actions/checkout@v2
     - name: Setup Python ${{ matrix.python-version }}
diff --git a/.github/workflows/test_exporters_slow.yml b/.github/workflows/test_exporters_slow.yml
@@ -16,7 +16,7 @@ jobs:
       matrix:
         python-version: ["3.9"]
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
       - uses: actions/checkout@v2
       - name: Setup Python ${{ matrix.python-version }}
diff --git a/.github/workflows/test_fx.yml b/.github/workflows/test_fx.yml
@@ -16,7 +16,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ['3.9']
-        os: [ubuntu-20.04, macos-13]
+        os: [ubuntu-22.04, macos-13]
 
     runs-on: ${{ matrix.os }}
     steps:
diff --git a/.github/workflows/test_offline.yml b/.github/workflows/test_offline.yml
@@ -17,7 +17,7 @@ jobs:
       matrix:
         python-version: ['3.9']
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
diff --git a/.github/workflows/test_onnx.yml b/.github/workflows/test_onnx.yml
@@ -16,7 +16,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ['3.9']
-        os: [ubuntu-20.04, macos-14]
+        os: [ubuntu-22.04, macos-14]
 
     runs-on: ${{ matrix.os }}
     steps:
diff --git a/.github/workflows/test_onnxruntime.yml b/.github/workflows/test_onnxruntime.yml
@@ -18,18 +18,18 @@ jobs:
       fail-fast: false
       matrix:
         transformers-version: ["latest"]
-        os: [ubuntu-20.04, windows-2019] # TODO : add macos-15 after mps fix
+        os: [ubuntu-22.04, windows-2019] # TODO : add macos-15 after mps fix
         include:
           - transformers-version: "4.36.*"
-            os: ubuntu-20.04
+            os: ubuntu-22.04
           - transformers-version: "4.45.*"
-            os: ubuntu-20.04
+            os: ubuntu-22.04
 
     runs-on: ${{ matrix.os }}
 
     steps:
       - name: Free Disk Space (Ubuntu)
-        if: matrix.os == 'ubuntu-20.04'
+        if: matrix.os == 'ubuntu-22.04'
         uses: jlumbroso/free-disk-space@main
 
       - name: Checkout code
diff --git a/.github/workflows/test_optimum_common.yml b/.github/workflows/test_optimum_common.yml
@@ -18,7 +18,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ['3.9']
-        os: [ubuntu-20.04, windows-2019, macos-13]
+        os: [ubuntu-22.04, windows-2019, macos-13]
 
     runs-on: ${{ matrix.os }}
     steps:
@@ -36,5 +36,5 @@ jobs:
         shell: bash
         run: |
           # Setting HUGGINGFACE_CO_STAGING to true for only one job of the matrix as the staging tests cannot run in parallel.
-          export HUGGINGFACE_CO_STAGING=${{ matrix.python-version == '3.9' && matrix.os == 'ubuntu-20.04' }}
+          export HUGGINGFACE_CO_STAGING=${{ matrix.python-version == '3.9' && matrix.os == 'ubuntu-22.04' }}
           pytest tests/test_*.py
diff --git a/.github/workflows/test_utils.yml b/.github/workflows/test_utils.yml
@@ -15,7 +15,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-20.04, macos-13]
+        os: [ubuntu-22.04, macos-13]
         python-version: ['3.9']
 
     runs-on: ${{ matrix.os }}
diff --git a/docs/combine_docs.py b/docs/combine_docs.py
@@ -133,6 +133,31 @@ def add_tpu_doc(base_toc: List):
     )
 
 
+def add_executorch_doc(base_toc: List):
+    """
+    Extends the table of content with a section about Optimum ExecuTorch.
+
+    Args:
+        base_toc (List): table of content for the doc of Optimum.
+    """
+    # Update optimum table of contents
+    base_toc.insert(
+        SUBPACKAGE_TOC_INSERT_INDEX,
+        {
+            "sections": [
+                {
+                    # Ideally this should directly point at https://huggingface.co/docs/optimum-executorch/index
+                    # Current hacky solution is to have a redirection in _redirects.yml
+                    "local": "docs/optimum-executorch/index",
+                    "title": "🤗 Optimum ExecuTorch",
+                }
+            ],
+            "title": "ExecuTorch",
+            "isExpanded": False,
+        },
+    )
+
+
 def main():
     args = parser.parse_args()
     optimum_path = Path("optimum-doc-build")
@@ -153,6 +178,9 @@ def main():
             # At the moment, Optimum Nvidia's doc is the README of the GitHub repo
             # It is linked to in optimum/docs/source/nvidia_overview.mdx
             continue
+        elif subpackage == "executorch":
+            # Optimum ExecuTorch has its own doc so it is managed differently
+            add_executorch_doc(base_toc)
         else:
             subpackage_path = Path(f"{subpackage}-doc-build")
 
diff --git a/docs/source/_redirects.yml b/docs/source/_redirects.yml
@@ -38,3 +38,6 @@ docs/optimum-neuron/index: /docs/optimum-neuron/index
 # Optimum TPU
 docs/optimum-tpu/index: /docs/optimum-tpu/index
 tpu/index: /docs/optimum-tpu/index
+
+# Optimum ExecuTorch
+docs/optimum-executorch/index: /docs/optimum-executorch/index
diff --git a/docs/source/exporters/onnx/usage_guides/export_a_model.mdx b/docs/source/exporters/onnx/usage_guides/export_a_model.mdx
diff --git a/notebooks/README.md b/notebooks/README.md
diff --git a/optimum/bettertransformer/__init__.py b/optimum/bettertransformer/__init__.py
diff --git a/optimum/bettertransformer/transformation.py b/optimum/bettertransformer/transformation.py
diff --git a/optimum/exporters/onnx/model_configs.py b/optimum/exporters/onnx/model_configs.py
diff --git a/optimum/exporters/tasks.py b/optimum/exporters/tasks.py
diff --git a/optimum/pipelines/pipelines_base.py b/optimum/pipelines/pipelines_base.py
diff --git a/tests/bettertransformer/Dockerfile_bettertransformer_gpu b/tests/bettertransformer/Dockerfile_bettertransformer_gpu
diff --git a/tests/exporters/exporters_utils.py b/tests/exporters/exporters_utils.py
