pyg-nightly 2.7.0.dev20250811__py3-none-any.whl → 2.7.0.dev20250813__py3-none-any.whl

{pyg_nightly-2.7.0.dev20250811.dist-info → pyg_nightly-2.7.0.dev20250813.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyg-nightly
-Version: 2.7.0.dev20250811
+Version: 2.7.0.dev20250813
 Summary: Graph Neural Network Library for PyTorch
 Keywords: deep-learning,pytorch,geometric-deep-learning,graph-neural-networks,graph-convolutional-networks
 Author-email: Matthias Fey <matthias@pyg.org>
@@ -445,6 +445,22 @@ We recommend to start with a minimal installation, and install additional depend
 
 For ease of installation of these extensions, we provide `pip` wheels for all major OS/PyTorch/CUDA combinations, see [here](https://data.pyg.org/whl).
 
+#### PyTorch 2.8
+
+To install the binaries for PyTorch 2.8.0, simply run
+
+```
+pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.8.0+${CUDA}.html
+```
+
+where `${CUDA}` should be replaced by either `cpu`, `cu126`, `cu128`, or `cu129` depending on your PyTorch installation.
+
+|             | `cpu` | `cu126` | `cu128` | `cu129` |
+| ----------- | ----- | ------- | ------- | ------- |
+| **Linux**   | ✅    | ✅      | ✅      | ✅      |
+| **Windows** | ✅    | ✅      | ✅      | ✅      |
+| **macOS**   | ✅    |         |         |         |
+
 #### PyTorch 2.7
 
 To install the binaries for PyTorch 2.7.0, simply run

{pyg_nightly-2.7.0.dev20250811.dist-info → pyg_nightly-2.7.0.dev20250813.dist-info}/RECORD

@@ -1,4 +1,4 @@
-torch_geometric/__init__.py,sha256=eOn-xi_uILg90CqcIXdvAj2EE0r9bSAPQ1Md4f9o4iw,2250
+torch_geometric/__init__.py,sha256=5OUi4MV3nk3AM7b-HpvH2PojxIosOGNudgCDwtO136s,2250
 torch_geometric/_compile.py,sha256=9yqMTBKatZPr40WavJz9FjNi7pQj8YZAZOyZmmRGXgc,1351
 torch_geometric/_onnx.py,sha256=V9ffrIKSqhDw6xUZ12lkuSfNs48cQp2EeJ6Z19GfnVw,349
 torch_geometric/backend.py,sha256=lVaf7aLoVaB3M-UcByUJ1G4T4FOK6LXAg0CF4W3E8jo,1575
@@ -7,11 +7,11 @@ torch_geometric/config_store.py,sha256=zdMzlgBpUmBkPovpYQh5fMNwTZLDq2OneqX47QEx7
 torch_geometric/debug.py,sha256=cLyH9OaL2v7POyW-80b19w-ctA7a_5EZsS4aUF1wc2U,1295
 torch_geometric/deprecation.py,sha256=gN65uX23c3miRPOpQzxcRS_QDUpD3B-qVKD6y6GX8Yw,872
 torch_geometric/device.py,sha256=tU5-_lBNVbVHl_kUmWPwiG5mQ1pyapwMF4JkmtNN3MM,1224
-torch_geometric/edge_index.py,sha256=RbIwLhtoLXmkQ_DqThBCwi1JH7zNRTsuVj0X-sTYlWE,70094
+torch_geometric/edge_index.py,sha256=pnOv8yGJYaaaKPQbQ3VQ-DTukX84UfQeNnw0Gw9NhCA,70078
 torch_geometric/experimental.py,sha256=JbtNNEXjFGI8hZ9raM6-qrZURP6Z5nlDK8QicZUIbz0,4756
-torch_geometric/hash_tensor.py,sha256=ItpMOBtD62zirrNeigZxql0EXofrEcThHX6ZJ50yDYc,24919
+torch_geometric/hash_tensor.py,sha256=uB32qj_zp4XfKXIsd5qCnrIaT4Hjd1i6wUglGCvQizg,24903
 torch_geometric/home.py,sha256=EV54B4Dmiv61GDbkCwtCfWGWJ4eFGwZ8s3KOgGjwYgY,790
-torch_geometric/index.py,sha256=FSP-Tkfw6d7P5U8ua8BO2IoEPJSnJT0L2IKyAfIqJR0,24360
+torch_geometric/index.py,sha256=I0MXlwUeYM8ttf_IiteLxq_cFHvAcDJh639uh5qPWao,24344
 torch_geometric/inspector.py,sha256=nKi5o4Mn6xsG0Ex1GudTEQt_EqnF9mcMqGtp7Shh9sQ,19336
 torch_geometric/isinstance.py,sha256=truZjdU9PxSvjJ6k0d_CLJ2iOpen2o8U-54pbUbNRyE,935
 torch_geometric/lazy_loader.py,sha256=SM0UcXtIdiFge75MKBAWXedoiSOdFDOV0rm1PfoF9cE,908
@@ -294,7 +294,7 @@ torch_geometric/loader/temporal_dataloader.py,sha256=Z7L_rYdl6SYBQXAgtr18FVcmfMH
 torch_geometric/loader/utils.py,sha256=3hzKzIgB52QIZu7Jdn4JeXZaegIJinIQfIUP9DrUWUQ,14903
 torch_geometric/loader/zip_loader.py,sha256=3lt10fD15Rxm1WhWzypswGzCEwUz4h8OLCD1nE15yNg,3843
 torch_geometric/metrics/__init__.py,sha256=3krvDobW6vV5yHTjq2S2pmOXxNfysNG26muq7z48e94,699
-torch_geometric/metrics/link_pred.py,sha256=dtaI39JB-WqE1B-raiElns6xySRwmkbb9izbcyt6xHI,30886
+torch_geometric/metrics/link_pred.py,sha256=mRQTSYYJgLKXFCelZHMKVOSbPED11JVhbryp7ajjxDU,31137
 torch_geometric/nn/__init__.py,sha256=kQHHHUxFDht2ztD-XFQuv98TvC8MdodaFsIjAvltJBw,874
 torch_geometric/nn/data_parallel.py,sha256=YiybTWoSFyfSzlXAamZ_-y1f7B6tvDEFHOuy_AyJz9Q,4761
 torch_geometric/nn/encoding.py,sha256=3DCOCO-XFt-lMb97sHWGN-4KeGUFY5lVo9P00SzrCNk,3559
@@ -645,7 +645,7 @@ torch_geometric/utils/undirected.py,sha256=H_nfpI0_WluOG6VfjPyldvcjL4w5USAKWu2x5
 torch_geometric/visualization/__init__.py,sha256=b-HnVesXjyJ_L1N-DnjiRiRVf7lhwKaBQF_2i5YMVSU,208
 torch_geometric/visualization/graph.py,sha256=mfZHXYfiU-CWMtfawYc80IxVwVmtK9hbIkSKhM_j7oI,14311
 torch_geometric/visualization/influence.py,sha256=CWMvuNA_Nf1sfbJmQgn58yS4OFpeKXeZPe7kEuvkUBw,477
-pyg_nightly-2.7.0.dev20250811.dist-info/licenses/LICENSE,sha256=ic-27cMJc1kWoMEYncz3Ya3Ur2Bi3bNLWib2DT763-o,1067
-pyg_nightly-2.7.0.dev20250811.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
-pyg_nightly-2.7.0.dev20250811.dist-info/METADATA,sha256=IdOb3DTp4CwTA83ekfMt97r_JHMA8YohNYvl5YyJ9ko,63484
-pyg_nightly-2.7.0.dev20250811.dist-info/RECORD,,
+pyg_nightly-2.7.0.dev20250813.dist-info/licenses/LICENSE,sha256=ic-27cMJc1kWoMEYncz3Ya3Ur2Bi3bNLWib2DT763-o,1067
+pyg_nightly-2.7.0.dev20250813.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
+pyg_nightly-2.7.0.dev20250813.dist-info/METADATA,sha256=WhUqzOZIg7BJlAQo6JphSxLn8cOuAxpAiUtBYWNd6_c,64100
+pyg_nightly-2.7.0.dev20250813.dist-info/RECORD,,

torch_geometric/__init__.py

@@ -31,7 +31,7 @@ from .lazy_loader import LazyLoader
 contrib = LazyLoader('contrib', globals(), 'torch_geometric.contrib')
 graphgym = LazyLoader('graphgym', globals(), 'torch_geometric.graphgym')
 
-__version__ = '2.7.0.dev20250811'
+__version__ = '2.7.0.dev20250813'
 
 __all__ = [
     'Index',

torch_geometric/edge_index.py

@@ -325,7 +325,7 @@ class EdgeIndex(Tensor):
             elif sparse_size[0] is None and sparse_size[1] is not None:
                 sparse_size = (sparse_size[1], sparse_size[1])
 
-        out = Tensor._make_wrapper_subclass(  # type: ignore
+        out = Tensor._make_wrapper_subclass(
             cls,
             size=data.size(),
             strides=data.stride(),

torch_geometric/hash_tensor.py

@@ -241,7 +241,7 @@ class HashTensor(Tensor):
             layout = torch.strided
             requires_grad = False
 
-        out = Tensor._make_wrapper_subclass(  # type: ignore
+        out = Tensor._make_wrapper_subclass(
             cls,
             size=size,
             strides=stride,

torch_geometric/index.py

@@ -182,7 +182,7 @@ class Index(Tensor):
         assert_one_dimensional(data)
         assert_contiguous(data)
 
-        out = Tensor._make_wrapper_subclass(  # type: ignore
+        out = Tensor._make_wrapper_subclass(
             cls,
             size=data.size(),
             strides=data.stride(),

torch_geometric/metrics/link_pred.py

@@ -332,7 +332,10 @@ class LinkPredMetricCollection(torch.nn.ModuleDict):
         r"""The maximum number of top-:math:`k` predictions to evaluate
         against.
         """
-        return max([metric.k for metric in self.values()])
+        return max([
+            metric.k  # type: ignore[return-value]
+            for metric in self.values()
+        ])  # type: ignore[type-var]
 
     @property
     def weighted(self) -> bool:
@@ -402,17 +405,23 @@ class LinkPredMetricCollection(torch.nn.ModuleDict):
 
         for metric in self.values():
             if not isinstance(metric, LinkPredMetric):
-                metric.update(pred_index_mat, edge_label_index,
-                              edge_label_weight)
+                metric.update(  # type: ignore[operator]
+                    pred_index_mat,
+                    edge_label_index,
+                    edge_label_weight,
+                )
 
     def compute(self) -> Dict[str, Tensor]:
         r"""Computes the final metric values."""
-        return {name: metric.compute() for name, metric in self.items()}
+        return {
+            name: metric.compute()  # type: ignore[operator]
+            for name, metric in self.items()
+        }
 
     def reset(self) -> None:
         r"""Reset metric state variables to their default value."""
         for metric in self.values():
-            metric.reset()
+            metric.reset()  # type: ignore[operator]
 
     def __repr__(self) -> str:
         names = [f'  {name}: {metric},\n' for name, metric in self.items()]