[CI] Drop python 3.8, torch 2.0, add python 3.13, torch 2.5 & 2.6dev

Author: tridao

.github/workflows/publish.yaml

@@ -43,37 +43,43 @@ jobs:
           # Using ubuntu-20.04 instead of 22.04 for more compatibility (glibc). Ideally we'd use the
           # manylinux docker image, but I haven't figured out how to install CUDA on manylinux.
           os: [ubuntu-20.04]
-          python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
-          torch-version: ['2.0.1', '2.1.2', '2.2.2', '2.3.1', '2.4.0']
-          cuda-version: ['11.8.0', '12.2.2']
+          python-version: ['3.9', '3.10', '3.11', '3.12', '3.13']
+          torch-version: ['2.1.2', '2.2.2', '2.3.1', '2.4.0', '2.5.1', '2.6.0.dev20241010']
+          cuda-version: ['11.8.0', '12.3.2']
           # We need separate wheels that either uses C++11 ABI (-D_GLIBCXX_USE_CXX11_ABI) or not.
           # Pytorch wheels currently don't use it, but nvcr images have Pytorch compiled with C++11 ABI.
           # Without this we get import error (undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationESs)
           # when building without C++11 ABI and using it on nvcr images.
           cxx11_abi: ['FALSE', 'TRUE']
           exclude:
+            # see https://github.com/pytorch/pytorch/blob/main/RELEASE.md#release-compatibility-matrix
             # Pytorch < 2.2 does not support Python 3.12
-            - torch-version: '2.0.1'
-              python-version: '3.12'
             - torch-version: '2.1.2'
               python-version: '3.12'
-            # Pytorch <= 2.0 only supports CUDA <= 11.8
-            - torch-version: '2.0.1'
-              cuda-version: '12.2.2'
+            # Pytorch < 2.5 does not support Python 3.13
+            - torch-version: '2.1.2'
+              python-version: '3.13'
+            - torch-version: '2.2.2'
+              python-version: '3.13'
+            - torch-version: '2.3.1'
+              python-version: '3.13'
+            - torch-version: '2.4.0'
+              python-version: '3.13'
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 
       - name: Set CUDA and PyTorch versions
         run: |
           echo "MATRIX_CUDA_VERSION=$(echo ${{ matrix.cuda-version }} | awk -F \. {'print $1 $2'})" >> $GITHUB_ENV
           echo "MATRIX_TORCH_VERSION=$(echo ${{ matrix.torch-version }} | awk -F \. {'print $1 "." $2'})" >> $GITHUB_ENV
+          echo "WHEEL_CUDA_VERSION=$(echo ${{ matrix.cuda-version }} | awk -F \. {'print $1'})" >> $GITHUB_ENV
 
       - name: Free up disk space
         if: ${{ runner.os == 'Linux' }}
@@ -92,33 +98,31 @@ jobs:
 
       - name: Install CUDA ${{ matrix.cuda-version }}
         if: ${{ matrix.cuda-version != 'cpu' }}
-        uses: Jimver/cuda-toolkit@v0.2.14
+        uses: Jimver/cuda-toolkit@v0.2.19
         id: cuda-toolkit
         with:
           cuda: ${{ matrix.cuda-version }}
           linux-local-args: '["--toolkit"]'
           # default method is "local", and we're hitting some error with caching for CUDA 11.8 and 12.1
           # method: ${{ (matrix.cuda-version == '11.8.0' || matrix.cuda-version == '12.1.0') && 'network' || 'local' }}
           method: 'network'
-          # We need the cuda libraries (e.g. cuSparse, cuSolver) for compiling PyTorch extensions,
-          # not just nvcc
-          # sub-packages: '["nvcc"]'
+          sub-packages: '["nvcc"]'
 
       - name: Install PyTorch ${{ matrix.torch-version }}+cu${{ matrix.cuda-version }}
         run: |
           pip install --upgrade pip
-          # If we don't install before installing Pytorch, we get error for torch 2.0.1
-          # ERROR: Could not find a version that satisfies the requirement setuptools>=40.8.0 (from versions: none)
-          pip install lit
           # For some reason torch 2.2.0 on python 3.12 errors saying no setuptools
-          pip install setuptools
+          pip install setuptools==68.0.0
+          # With python 3.13 and torch 2.5.1, unless we update typing-extensions, we get error
+          # AttributeError: attribute '__default__' of 'typing.ParamSpec' objects is not writable
+          pip install typing-extensions==4.12.2
           # We want to figure out the CUDA version to download pytorch
           # e.g. we can have system CUDA version being 11.7 but if torch==1.12 then we need to download the wheel from cu116
           # This code is ugly, maybe there's a better way to do this.
           export TORCH_CUDA_VERSION=$(python -c "from os import environ as env; \
-            minv = {'2.0': 117, '2.1': 118, '2.2': 118, '2.3': 118, '2.4': 118}[env['MATRIX_TORCH_VERSION']]; \
-            maxv = {'2.0': 118, '2.1': 121, '2.2': 121, '2.3': 121, '2.4': 124}[env['MATRIX_TORCH_VERSION']]; \
-            print(max(min(int(env['MATRIX_CUDA_VERSION']), maxv), minv))" \
+            minv = {'2.1': 118, '2.2': 118, '2.3': 118, '2.4': 118, '2.5': 118, '2.6': 118}[env['MATRIX_TORCH_VERSION']]; \
+            maxv = {'2.1': 121, '2.2': 121, '2.3': 121, '2.4': 124, '2.5': 124, '2.6': 124}[env['MATRIX_TORCH_VERSION']]; \
+            print(minv if int(env['MATRIX_CUDA_VERSION']) < 120 else maxv)" \
           )
           if [[ ${{ matrix.torch-version }} == *"dev"* ]]; then
             pip install --no-cache-dir --pre torch==${{ matrix.torch-version }} --index-url https://download.pytorch.org/whl/nightly/cu${TORCH_CUDA_VERSION}
@@ -144,7 +148,7 @@ jobs:
           export LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:$LD_LIBRARY_PATH
           # Limit MAX_JOBS otherwise the github runner goes OOM
           MAX_JOBS=2 MAMBA_FORCE_BUILD="TRUE" MAMBA_FORCE_CXX11_ABI=${{ matrix.cxx11_abi}} python setup.py bdist_wheel --dist-dir=dist
-          tmpname=cu${MATRIX_CUDA_VERSION}torch${MATRIX_TORCH_VERSION}cxx11abi${{ matrix.cxx11_abi }}
+          tmpname=cu${WHEEL_CUDA_VERSION}torch${MATRIX_TORCH_VERSION}cxx11abi${{ matrix.cxx11_abi }}
           wheel_name=$(ls dist/*whl | xargs -n 1 basename | sed "s/-/+$tmpname-/2")
           ls dist/*whl |xargs -I {} mv {} dist/${wheel_name}
           echo "wheel_name=${wheel_name}" >> $GITHUB_ENV
@@ -183,9 +187,9 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: '3.10'
 

setup.py

@@ -277,10 +277,10 @@ def get_wheel_url():
         # We're using the CUDA version used to build torch, not the one currently installed
         # _, cuda_version_raw = get_cuda_bare_metal_version(CUDA_HOME)
         torch_cuda_version = parse(torch.version.cuda)
-        # For CUDA 11, we only compile for CUDA 11.8, and for CUDA 12 we only compile for CUDA 12.2
+        # For CUDA 11, we only compile for CUDA 11.8, and for CUDA 12 we only compile for CUDA 12.3
         # to save CI time. Minor versions should be compatible.
-        torch_cuda_version = parse("11.8") if torch_cuda_version.major == 11 else parse("12.2")
-        cuda_version = f"{torch_cuda_version.major}{torch_cuda_version.minor}"
+        torch_cuda_version = parse("11.8") if torch_cuda_version.major == 11 else parse("12.3")
+        cuda_version = f"{torch_cuda_version.major}"
 
     gpu_compute_version = hip_ver if HIP_BUILD else cuda_version
     cuda_or_hip = "hip" if HIP_BUILD else "cu"