Add CUDA build

Author: mthrok

.github/workflows/_build_windows.yml

@@ -10,6 +10,13 @@ on:
         description: 'Whether FT Python or not. Valid value is "ft" or not.'
         default: ''
         type: string
+      cuda-version:
+        required: true
+        type: string
+      use-nvdec:
+        default: "nvdec"
+        type: string
+        description: 'Whether build NVDEC extension. Valid value is "nvdec" or not.'
       run-test:
         required: false
         default: 'false'
@@ -20,6 +27,9 @@ on:
 
 env:
   ARTIFACT: wheel-win-py${{ inputs.python-version }}${{ inputs.free-threaded }}
+  SPDL_USE_TRACING: 0
+  SPDL_USE_CUDA: 1
+  SPDL_USE_NVDEC: "${{ inputs.use-nvdec == 'nvdec' }}"
 
 jobs:
   build:
@@ -29,10 +39,39 @@ jobs:
         with:
           persist-credentials: false
 
+    - name: Install Cuda Toolkit 12.4 on Windows
+      run: |
+        mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4"
+        choco install unzip -y
+        curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-12.4.127-archive.zip"
+        curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-12.4.131-archive.zip"
+        curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-12.4.127-archive.zip"
+        # curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-12.4.5.8-archive.zip"
+        # curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-12.4.127-archive.zip"
+        # curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-12.4.127-archive.zip"
+        curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-12.4.127-archive.zip"
+        # curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvprof/windows-x86_64/cuda_nvprof-windows-x86_64-12.4.127-archive.zip"
+        # curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cccl/windows-x86_64/cuda_cccl-windows-x86_64-12.4.127-archive.zip"
+        unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4"
+        xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cudart-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
+        xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvcc-windows-x86_64-12.4.131-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
+        xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvrtc-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
+        # xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libcublas-windows-x86_64-12.4.5.8-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
+        # xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvtx-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
+        # xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_profiler_api-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
+        xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\visual_studio_integration-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
+        # xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_nvprof-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
+        # xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\cuda_cccl-windows-x86_64-12.4.127-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" /E /I /H /Y
+
+    # Default installation path for CUDA Toolkit is C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4
+    - name: Add Path
+      run: |
+        echo "C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.4\\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
+        echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\libnvvp" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
+        echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
+        echo "CUDA_PATH_V12_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
+
       - name: Build
-        env:
-          SPDL_USE_TRACING: 0
-          SPDL_BUILD_STUB: 0
         shell: cmd
         run: |
           packaging/vc_env_helper.bat            ^
@@ -57,9 +96,9 @@ jobs:
             bash                                 ^
               .github/scripts/check_package.sh
 
-  unit-test:
+  test-cpu:
     if: "${{ inputs.run-test == 'true' }}"
-    name: "test ffmpeg"
+    name: "test-cpu ffmpeg ${{ matrix.ffmpeg-version }}"
     needs: ["build"]
     strategy:
       fail-fast: false

.github/workflows/packaging.yml

@@ -43,6 +43,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.10", "3.11", "3.12", "3.13"]
+        cuda-version: ["12.4"]
         free-threaded: [""]
         include:
           - python-version: "3.13"
@@ -51,6 +52,7 @@ jobs:
     with:
       python-version: "${{ matrix.python-version }}"
       free-threaded: "${{ matrix.free-threaded }}"
+      cuda-version: "${{ matrix.cuda-version }}"
       run-test: "${{ matrix.python-version == '3.11'}}"
 
   #############################################################################