Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 7 additions & 29 deletions .github/workflows/building.yml
Original file line number Diff line number Diff line change
Expand Up @@ -11,38 +11,24 @@ jobs:
fail-fast: false
matrix:
os: [ubuntu-22.04, macos-14, windows-2022, ubuntu-22.04-arm]
python-version: ['3.9', '3.10', '3.11', '3.12', '3.13']
torch-version: [2.8.0]
cuda-version: ['cpu', 'cu118', 'cu124', 'cu126', 'cu128', 'cu129']
python-version: ['3.10', '3.11', '3.12', '3.13', '3.14']
torch-version: [2.9.0, 2.10.0]
cuda-version: ['cpu', 'cu126', 'cu128', 'cu130']
exclude:
- torch-version: 2.6.0
cuda-version: 'cu128'
- torch-version: 2.7.0
cuda-version: 'cu124'
- torch-version: 2.8.0
cuda-version: 'cu124'
- torch-version: 2.8.0
cuda-version: 'cu118'
- os: macos-14
cuda-version: 'cu118'
- os: macos-14
cuda-version: 'cu124'
- os: windows-2022
cuda-version: 'cu130'
- os: macos-14
cuda-version: 'cu126'
- os: macos-14
cuda-version: 'cu128'
- os: macos-14
cuda-version: 'cu129'
- os: ubuntu-22.04-arm
cuda-version: 'cu118'
- os: ubuntu-22.04-arm
cuda-version: 'cu124'
cuda-version: 'cu130'
- os: ubuntu-22.04-arm
cuda-version: 'cu126'
- os: ubuntu-22.04-arm
cuda-version: 'cu128'
- os: ubuntu-22.04-arm
cuda-version: 'cu129'
cuda-version: 'cu130'

steps:
- uses: actions/checkout@v2
Expand Down Expand Up @@ -71,14 +57,6 @@ jobs:
python -c "import torch; print('PyTorch:', torch.__version__)"
python -c "import torch; print('CUDA:', torch.version.cuda)"

- name: Patch PyTorch static constexpr on Windows
if: ${{ runner.os == 'Windows' }}
run: |
Torch_DIR=`python -c 'import os; import torch; print(os.path.dirname(torch.__file__))'`
sed -i '31,38c\
TORCH_API void lazy_init_num_threads();' ${Torch_DIR}/include/ATen/Parallel.h
shell: bash

- name: Set version
if: ${{ runner.os != 'macOS' }}
run: |
Expand Down
8 changes: 8 additions & 0 deletions .github/workflows/cuda/cu130-Linux-env.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
#!/bin/bash

CUDA_HOME=/usr/local/cuda-13.0
LD_LIBRARY_PATH=${CUDA_HOME}/lib64:${LD_LIBRARY_PATH}
PATH=${CUDA_HOME}/bin:${PATH}

export FORCE_CUDA=1
export TORCH_CUDA_ARCH_LIST="7.5;8.0;8.6;9.0;10.0;12.0+PTX"
17 changes: 17 additions & 0 deletions .github/workflows/cuda/cu130-Linux.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
#!/bin/bash

OS=ubuntu2204

wget -nv https://developer.download.nvidia.com/compute/cuda/repos/${OS}/x86_64/cuda-${OS}.pin
sudo mv cuda-${OS}.pin /etc/apt/preferences.d/cuda-repository-pin-600

wget -nv https://developer.download.nvidia.com/compute/cuda/13.0.2/local_installers/cuda-repo-${OS}-13-0-local_13.0.2-580.95.05-1_amd64.deb

sudo dpkg -i cuda-repo-${OS}-13-0-local_13.0.2-580.95.05-1_amd64.deb
sudo cp /var/cuda-repo-${OS}-13-0-local/cuda-*-keyring.gpg /usr/share/keyrings/

sudo apt-get -qq update
sudo apt install cuda-nvcc-13-0 cuda-libraries-dev-13-0
sudo apt clean

rm -f *.deb
12 changes: 2 additions & 10 deletions .github/workflows/testing.yml
Original file line number Diff line number Diff line change
Expand Up @@ -15,8 +15,8 @@ jobs:
fail-fast: false
matrix:
os: [ubuntu-latest, windows-latest]
python-version: [3.9]
torch-version: [2.6.0, 2.7.0]
python-version: ['3.10']
torch-version: [2.9.0, 2.10.0]

steps:
- uses: actions/checkout@v2
Expand All @@ -29,14 +29,6 @@ jobs:
run: |
pip install torch==${{ matrix.torch-version }} --extra-index-url https://download.pytorch.org/whl/cpu

- name: Patch PyTorch static constexpr on Windows
if: ${{ runner.os == 'Windows' }}
run: |
Torch_DIR=`python -c 'import os; import torch; print(os.path.dirname(torch.__file__))'`
sed -i '31,38c\
TORCH_API void lazy_init_num_threads();' ${Torch_DIR}/include/ATen/Parallel.h
shell: bash

- name: Install main package
run: |
python setup.py develop
Expand Down
32 changes: 16 additions & 16 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -45,55 +45,55 @@ All included operations are broadcastable, work on varying data types, are imple

We provide pip wheels for all major OS/PyTorch/CUDA combinations, see [here](https://data.pyg.org/whl).

#### PyTorch 2.8
#### PyTorch 2.10

To install the binaries for PyTorch 2.8.0, simply run
To install the binaries for PyTorch 2.10, simply run

```
pip install torch-scatter -f https://data.pyg.org/whl/torch-2.8.0+${CUDA}.html
pip install torch-scatter -f https://data.pyg.org/whl/torch-2.10.0+${CUDA}.html
```

where `${CUDA}` should be replaced by either `cpu`, `cu126`, `cu128`, or `cu129` depending on your PyTorch installation.
where `${CUDA}` should be replaced by either `cpu`, `cu126`, `cu128`, or `cu130` depending on your PyTorch installation.

| | `cpu` | `cu126` | `cu128` | `cu129` |
| | `cpu` | `cu126` | `cu128` | `cu130` |
|-------------|-------|---------|---------|---------|
| **Linux** | ✅ | ✅ | ✅ | ✅ |
| **Windows** | ✅ | ✅ | ✅ | ✅ |
| **macOS** | ✅ | | | |

#### PyTorch 2.7
#### PyTorch 2.9

To install the binaries for PyTorch 2.7.0, simply run
To install the binaries for PyTorch 2.9, simply run

```
pip install torch-scatter -f https://data.pyg.org/whl/torch-2.7.0+${CUDA}.html
pip install torch-scatter -f https://data.pyg.org/whl/torch-2.9.0+${CUDA}.html
```

where `${CUDA}` should be replaced by either `cpu`, `cu118`, `cu126`, or `cu128` depending on your PyTorch installation.
where `${CUDA}` should be replaced by either `cpu`, `cu126`, `cu128`, or `cu130` depending on your PyTorch installation.

| | `cpu` | `cu118` | `cu126` | `cu128` |
| | `cpu` | `cu126` | `cu128` | `cu130` |
|-------------|-------|---------|---------|---------|
| **Linux** | ✅ | ✅ | ✅ | ✅ |
| **Windows** | ✅ | ✅ | ✅ | ✅ |
| **macOS** | ✅ | | | |

#### PyTorch 2.6
#### PyTorch 2.8

To install the binaries for PyTorch 2.6.0, simply run
To install the binaries for PyTorch 2.8, simply run

```
pip install torch-scatter -f https://data.pyg.org/whl/torch-2.6.0+${CUDA}.html
pip install torch-scatter -f https://data.pyg.org/whl/torch-2.8.0+${CUDA}.html
```

where `${CUDA}` should be replaced by either `cpu`, `cu118`, `cu124`, or `cu126` depending on your PyTorch installation.
where `${CUDA}` should be replaced by either `cpu`, `cu126`, `cu128`, or `cu129` depending on your PyTorch installation.

| | `cpu` | `cu118` | `cu124` | `cu126` |
| | `cpu` | `cu126` | `cu128` | `cu129` |
|-------------|-------|---------|---------|---------|
| **Linux** | ✅ | ✅ | ✅ | ✅ |
| **Windows** | ✅ | ✅ | ✅ | ✅ |
| **macOS** | ✅ | | | |

**Note:** Binaries of older versions are also provided for PyTorch 1.4.0, PyTorch 1.5.0, PyTorch 1.6.0, PyTorch 1.7.0/1.7.1, PyTorch 1.8.0/1.8.1, PyTorch 1.9.0, PyTorch 1.10.0/1.10.1/1.10.2, PyTorch 1.11.0, PyTorch 1.12.0/1.12.1, PyTorch 1.13.0/1.13.1, PyTorch 2.0.0/2.0.1, PyTorch 2.1.0/2.1.1/2.1.2, PyTorch 2.2.0/2.2.1/2.2.2, PyTorch 2.3.0/2.3.1, PyTorch 2.4.0/2.4.1, and PyTorch 2.5.0/2.5.1 (following the same procedure).
**Note:** Binaries of older versions are also provided for PyTorch 1.4.0, PyTorch 1.5.0, PyTorch 1.6.0, PyTorch 1.7.0/1.7.1, PyTorch 1.8.0/1.8.1, PyTorch 1.9.0, PyTorch 1.10.0/1.10.1/1.10.2, PyTorch 1.11.0, PyTorch 1.12.0/1.12.1, PyTorch 1.13.0/1.13.1, PyTorch 2.0.0/2.0.1, PyTorch 2.1.0/2.1.1/2.1.2, PyTorch 2.2.0/2.2.1/2.2.2, PyTorch 2.3.0/2.3.1, PyTorch 2.4.0/2.4.1, PyTorch 2.5.0/2.5.1, PyTorch 2.6.0, and PyTorch 2.7.0/2.7.1 (following the same procedure).
For older versions, you need to explicitly specify the latest supported version number or install via `pip install --no-index` in order to prevent a manual installation from source.
You can look up the latest supported version number [here](https://data.pyg.org/whl).

Expand Down
3 changes: 3 additions & 0 deletions setup.py
Original file line number Diff line number Diff line change
Expand Up @@ -72,6 +72,9 @@ def get_extensions():
nvcc_flags = os.getenv('NVCC_FLAGS', '')
nvcc_flags = [] if nvcc_flags == '' else nvcc_flags.split(' ')
nvcc_flags += ['-O3']
nvcc_flags += ['-DTORCH_INDUCTOR_CPP_WRAPPER']
if sys.platform == 'win32':
nvcc_flags += ['-Xcompiler', '/permissive-']
if torch.version.hip:
# USE_ROCM was added to later versions of PyTorch.
# Define here to support older PyTorch versions as well:
Expand Down