pyg-nightly 2.7.0.dev20250410__py3-none-any.whl → 2.7.0.dev20250411__py3-none-any.whl

{pyg_nightly-2.7.0.dev20250410.dist-info → pyg_nightly-2.7.0.dev20250411.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyg-nightly
-Version: 2.7.0.dev20250410
+Version: 2.7.0.dev20250411
 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>
@@ -13,6 +13,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3 :: Only
 License-File: LICENSE
 Requires-Dist: aiohttp
@@ -411,7 +412,7 @@ These approaches have been implemented in PyG, and can benefit from the above GN
 
 ## Installation
 
-PyG is available for Python 3.9 to Python 3.12.
+PyG is available for Python 3.9 to Python 3.13.
 
 From **PyG 2.3** onwards, you can install and use PyG **without any external library** required except for PyTorch.
 For this, simply run

{pyg_nightly-2.7.0.dev20250410.dist-info → pyg_nightly-2.7.0.dev20250411.dist-info}/RECORD

@@ -1,4 +1,4 @@
-torch_geometric/__init__.py,sha256=8STFnZ5D5SJ_NXByr6Uts6yFesA2ot2-To0NNYU8MqE,1978
+torch_geometric/__init__.py,sha256=5jyXuTotTDAXoFpYa157TW_x88VLzZsbeo_2LDBcf70,1978
 torch_geometric/_compile.py,sha256=f-WQeH4VLi5Hn9lrgztFUCSrN_FImjhQa6BxFzcYC38,1338
 torch_geometric/_onnx.py,sha256=V9ffrIKSqhDw6xUZ12lkuSfNs48cQp2EeJ6Z19GfnVw,349
 torch_geometric/backend.py,sha256=lVaf7aLoVaB3M-UcByUJ1G4T4FOK6LXAg0CF4W3E8jo,1575
@@ -395,7 +395,7 @@ torch_geometric/nn/conv/spline_conv.py,sha256=RzxHKlBAitCRIBbj2Co7MH6HCFwhlzVD2t
 torch_geometric/nn/conv/ssg_conv.py,sha256=qHjvBwppfazl5qCVsmZz0X1gl9M1fFsVHke9nOArT9w,5131
 torch_geometric/nn/conv/supergat_conv.py,sha256=ul0qyLBlMFYFDlwvF_vszqcxiX9hA9eeK9p8AUIAs8M,12420
 torch_geometric/nn/conv/tag_conv.py,sha256=nYcRVQzKqJhe9qmW0QQWHlQielm9AH4gM9AcsiF2ELo,4164
-torch_geometric/nn/conv/transformer_conv.py,sha256=kEHP-qy2Fo1sKY1AoobknTBzBpT8wnI0SehsFgQwT0s,10407
+torch_geometric/nn/conv/transformer_conv.py,sha256=SqtzV9lQwP_Uvmoc428P2ZNdisSWmgu9qq5t8wUV3iQ,10504
 torch_geometric/nn/conv/wl_conv.py,sha256=je4EM8rVrxG0h9-CWmgXZJnMVhns_VjAVbeqb_tOwos,3140
 torch_geometric/nn/conv/wl_conv_continuous.py,sha256=nnfd5JVAR2UYz6AQxwCN2a8C6RXDMZVL-WE_wPXKFsU,2777
 torch_geometric/nn/conv/x_conv.py,sha256=c_qnD-o9-qMa-vaOgEDGb5ZT1NdhS2vrhTQdp-8cYIo,6013
@@ -518,7 +518,7 @@ torch_geometric/sampler/utils.py,sha256=RJtasO6Q7Pp3oYEOWrbf2DEYuSfuKZOsF2I7-eJD
 torch_geometric/testing/__init__.py,sha256=0mAGVWRrTBNsGV2YUkCu_FkyQ8JIcrYVw2LsdKgY9ak,1291
 torch_geometric/testing/asserts.py,sha256=DLC9HnBgFWuTIiQs2OalsQcXGhOVG-e6R99IWhkO32c,4606
 torch_geometric/testing/data.py,sha256=O1qo8FyNxt6RGf63Ys3eXBfa5RvYydeZLk74szrez3c,2604
-torch_geometric/testing/decorators.py,sha256=j45wlxMB1-Pn3wPKBgDziqg6KkWJUb_fcwfUXzkL2mM,8677
+torch_geometric/testing/decorators.py,sha256=BaaQRGgU1r1_p3OTpSLzgUaROq6EB2vojq4VKSzXE6w,8657
 torch_geometric/testing/distributed.py,sha256=ZZCCXqiQC4-m1ExSjDZhS_a1qPXnHEwhJGTmACxNnVI,2227
 torch_geometric/testing/feature_store.py,sha256=J6JBIt2XK-t8yG8B4JzXp-aJcVl5jaCS1m2H7d6OUxs,2158
 torch_geometric/testing/graph_store.py,sha256=00B7QToCIspYmgN7svQKp1iU-qAzEtrt3VQRFxkHfuk,1044
@@ -636,7 +636,7 @@ torch_geometric/utils/undirected.py,sha256=H_nfpI0_WluOG6VfjPyldvcjL4w5USAKWu2x5
 torch_geometric/visualization/__init__.py,sha256=PyR_4K5SafsJrBr6qWrkjKr6GBL1b7FtZybyXCDEVwY,154
 torch_geometric/visualization/graph.py,sha256=ZuLPL92yGRi7lxlqsUPwL_EVVXF7P2kMcveTtW79vpA,4784
 torch_geometric/visualization/influence.py,sha256=CWMvuNA_Nf1sfbJmQgn58yS4OFpeKXeZPe7kEuvkUBw,477
-pyg_nightly-2.7.0.dev20250410.dist-info/licenses/LICENSE,sha256=ic-27cMJc1kWoMEYncz3Ya3Ur2Bi3bNLWib2DT763-o,1067
-pyg_nightly-2.7.0.dev20250410.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
-pyg_nightly-2.7.0.dev20250410.dist-info/METADATA,sha256=VCJmk0zw0oTq7-7e5BugaUHh2XfOxL-KeSNLRqqhtHA,62652
-pyg_nightly-2.7.0.dev20250410.dist-info/RECORD,,
+pyg_nightly-2.7.0.dev20250411.dist-info/licenses/LICENSE,sha256=ic-27cMJc1kWoMEYncz3Ya3Ur2Bi3bNLWib2DT763-o,1067
+pyg_nightly-2.7.0.dev20250411.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
+pyg_nightly-2.7.0.dev20250411.dist-info/METADATA,sha256=bF_PoHTK8G7dyiEt49wMpwWWukdKa_xa0XOz7flRH_M,62703
+pyg_nightly-2.7.0.dev20250411.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.dev20250410'
+__version__ = '2.7.0.dev20250411'
 
 __all__ = [
     'Index',

torch_geometric/nn/conv/transformer_conv.py

@@ -126,9 +126,11 @@ class TransformerConv(MessagePassing):
         if isinstance(in_channels, int):
             in_channels = (in_channels, in_channels)
 
-        self.lin_key = Linear(in_channels[0], heads * out_channels)
-        self.lin_query = Linear(in_channels[1], heads * out_channels)
-        self.lin_value = Linear(in_channels[0], heads * out_channels)
+        self.lin_key = Linear(in_channels[0], heads * out_channels, bias=bias)
+        self.lin_query = Linear(in_channels[1], heads * out_channels,
+                                bias=bias)
+        self.lin_value = Linear(in_channels[0], heads * out_channels,
+                                bias=bias)
         if edge_dim is not None:
             self.lin_edge = Linear(edge_dim, heads * out_channels, bias=False)
         else:

torch_geometric/testing/decorators.py

@@ -33,8 +33,8 @@ def onlyFullTest(func: Callable) -> Callable:
 
 def is_distributed_test() -> bool:
     r"""Whether to run the distributed test suite."""
-    return ((is_full_test() or os.getenv('DIST_TEST', '0') == '1')
-            and sys.platform == 'linux' and has_package('pyg_lib'))
+    return (os.getenv('DIST_TEST', '0') == '1' and sys.platform == 'linux'
+            and has_package('pyg_lib'))
 
 
 def onlyDistributedTest(func: Callable) -> Callable: