此网站需要 JavaScript。
751b4c269d
[Bugfix] Replace global cudaStream in Filter with runtime calls (fix #5153 ) (#5157 )
2023-01-12 00:27:29 -08:00
84e4d0215f
change regex (#5158 )
2023-01-12 15:04:22 +08:00
bff32a0986
[Sparse] Use efficient implementation for Diag @ Sparse and Sparse @ Diag. (#5147 )
2023-01-12 11:53:46 +08:00
21c4c29a36
[Sparse] Reduce peak memory of SpSpAdd. (#5143 )
2023-01-12 11:53:04 +08:00
b743f767b6
fix (#5151 )
2023-01-12 10:13:18 +08:00
f94fa9d975
typo (#5133 )
2023-01-11 22:21:11 +08:00
f1ed5d6de7
blabla (#5152 )
2023-01-11 20:21:55 +08:00
2a78e48f4e
polish (#5150 )
2023-01-11 19:55:38 +08:00
41b4180950
Polish (#5149 )
2023-01-11 19:31:08 +08:00
9c647d8095
[Sparse] Add elementwise mul and div method, and polish the python doc. (#5142 )
2023-01-11 19:07:32 +08:00
491c19fe4a
[Bugfix] Fix the call of tar.extractall() method (#5139 )
2023-01-10 23:11:56 -08:00
46455328e4
[CI] fix bugs for multigpu benchmarks (#5140 )
2023-01-11 14:50:37 +08:00
d837029925
try again. (#5141 )
2023-01-11 12:59:50 +08:00
e032de5848
[Bugfix] Avoid initializing CUDA context at importing (#5134 )
2023-01-11 12:30:20 +08:00
1a33ee99d3
[Sparse] Update doc string of element-wise ops for DiagMatrix and SparseMatrix. (#5136 )
2023-01-11 12:08:24 +08:00
c5119480f2
[Sparse] Remove unnecessary API exposure. (#5135 )
2023-01-11 11:47:14 +08:00
c6228c0118
update suffix (#5128 )
2023-01-10 09:56:09 +08:00
b7042a141c
[BugFix] fix unexpected exception when agg_type is GCN and bias disabled (#5127 )
2023-01-10 09:05:44 +08:00
5c6af80444
CVE-2007-4559 Patch (#5122 )
2023-01-08 21:49:10 -06:00
f1fb859f99
bump version to 1.0 (#5123 )
2023-01-09 11:28:26 +08:00
580c702417
[DataLoader] Allow batch_size=None for GraphDataLoader (#4483 )
2023-01-09 00:44:46 +08:00
e296c468b2
[Optimization] Optimize bias term in SageConv layer (#4747 )
2023-01-08 06:06:46 +01:00
56ffb650fe
[API Deprecation]Deprecate contrib module (#5114 )
2023-01-06 20:16:01 +08:00
436de3d120
[API Deprecation] Remove _dataloading and tgcn example (#5118 )
2023-01-06 19:51:55 +08:00
c8bc558880
[Sparse] Remove SparseMatrix.indices and add device/dtype conversions (#5108 )
2023-01-06 17:37:13 +08:00
c55ab2d147
deprecate candidates in dataloader (#5117 )
2023-01-06 16:18:32 +08:00
3a2a5031e9
[API Deprecation]Deprecate candidates in dgl.distributed (#5116 )
2023-01-06 16:17:44 +08:00
ab0c0ec68f
[API Deprecation] Deprecate candidates in convert module (#4988 ) (#5115 )
2023-01-06 14:45:52 +08:00
46a3fc2b5f
[CI] updgrade pytorch version for benchmark CI (#5102 )
2023-01-06 14:35:36 +08:00
dde5cf5d02
[Bug] Fix NN modules crashing with non-FP32 inputs (reopen #4262 ) (#4829 )
2023-01-06 14:18:19 +08:00
9a40d2080e
[Sparse] Change CMakeFiles to build DGL Sparse for multiple PyTorch versions (#5106 )
2023-01-06 14:14:20 +08:00
6069f34c4f
[Performance] Fix for number of threads in COOToCSR (#5017 )
2023-01-06 02:14:27 +01:00
a506ebe82b
[Example][Refactor] Multi-gpu graphsage link prediction example refactor (#5091 )
2023-01-05 04:59:39 -08:00
9890201d58
[Dist] Allow reading and writing single-column vector Parquet files. (#5098 )
2023-01-05 04:37:28 -08:00
7ee550f004
update cmake for cuda12 (#5048 )
2023-01-05 10:47:10 +08:00
ec3934d0d1
[Example] Sparse Graph Transformer (#5069 )
2023-01-05 08:50:38 +08:00
9169fc3541
[Sparse] Polish sparse matrix creation functions (#5093 )
2023-01-03 22:59:57 +08:00
0698e91a0e
[Sparse] Use Pytorch dense computation in SpMM tests (#5096 )
2023-01-03 22:26:06 +08:00
774709d399
[Dist] Add support for Parquet-formatted edges files, remove some assumptions on edge file number. (#5051 )
2023-01-03 00:01:50 -08:00
cd817a1a00
[NN] Add SpatialEncoder and SpatialEncoder3d (#4991 )
2023-01-03 14:02:14 +08:00
ce378327c7
fix bf16 tests (#5089 )
2022-12-29 21:36:39 +08:00
37bd092587
[Sparse] Namespace migration and doc update (#5088 )
2022-12-29 20:34:29 +08:00
e65fc9ff78
[Sparse] Avoid using macros in DGL headers (#5087 )
2022-12-29 17:35:29 +08:00
255ad1b35b
[Sparse] New print for SparseMatrix and DiagMatrix (#5085 )
2022-12-29 15:38:10 +08:00
025e43210f
[Sparse] Add tests for sparse examples; Migrate from mock_sparse to mock_sparse2 (#5073 )
2022-12-29 08:55:25 +08:00
811e35a6ef
[Sparse] Change all CHECK to TORCH_CHECK (#5082 )
2022-12-28 23:26:06 +08:00
14429df661
[Sparse] Support BSpMM and BSDDMM (#5079 )
2022-12-28 17:14:12 +08:00
bda6a816be
rename (#5058 )
2022-12-28 13:27:52 +08:00
fa5ff2fceb
[Sparse] Add coalesce and has_duplicate to SparseMatrix (#5071 )
2022-12-28 13:10:10 +08:00
8c3e7830dc
[Sparse] Elementwise multiplication of a SparseMatrix object by a scalar (#5076 )
2022-12-28 09:37:44 +08:00
0f1bcd9927
[Sparse] Softmax based on Reduction and BroadcastOp (#5067 )
2022-12-27 14:50:15 +08:00
311bd88a04
[Doc] update doc page for distributed partition pipeline (#5064 )
2022-12-26 23:11:32 +08:00
3eac464a3f
[Sparse] Fix the sddmm backward problem in mock_sparse. (#5070 )
2022-12-26 23:10:34 +08:00
4aff59f775
[Sparse] Rename existing DGL sparse module. (#5066 )
2022-12-26 13:55:48 +08:00
0159c3c11d
[Sparse] Add SpSpMM for sparse-sparse and sparse-diag matrix multiplication. (#5050 )
2022-12-24 15:31:09 +08:00
f0ce2bea22
[Sparse] Sparse matrix reduction Python part (#5013 )
2022-12-22 16:49:29 +08:00
b3aec7aeb1
[Sparse] Add mock_sddmm in mock_sparse (#5059 )
2022-12-22 00:07:56 +08:00
56ce60b061
[Sparse] Fix SpMM and SDDMM test precision problem (#5060 )
2022-12-21 18:02:29 +08:00
1f2fcae3e2
[Sparse] Support SpMM and SDDMM (#5032 )
2022-12-21 10:29:23 +08:00
f40db9b743
[Dist][Test] Add exit_code asserts in some distributed tests (#5053 )
2022-12-20 17:03:13 -08:00
11e6190579
[Sparse] Add Two Sparse Matrices with Different Sparsity, DiagMatrix.dense, Add SparseMatrix and DiagMatrix (#5044 )
2022-12-20 20:15:37 +08:00
f1ee3e311d
[Sparse] Sparse matrix reduction C++ part (#5012 )
2022-12-20 12:37:12 +08:00
00f2099934
[CI] upgrade CI pytorch version (#5047 )
2022-12-19 17:29:03 +08:00
f4eef72628
[Fix core lib warning] Remove LooseVersion (#5026 )
2022-12-19 09:02:14 +08:00
6bd8175890
[Sparse] GCNII example (#5008 )
2022-12-18 14:44:22 +08:00
3db6604e67
[Fix core lib warning] Fix using torch.tensor for tensor conversion (#5028 )
2022-12-15 13:50:33 +08:00
9731e02325
[Dist] enable to chunk node/edge data into arbitrary number of chunks (#4930 )
2022-12-15 10:01:39 +08:00
08b60eb162
[Sparse] Add SpMM and SDDMM on CSR and COO in dgl include headers (#5016 )
2022-12-15 09:09:47 +08:00
0038a29ba1
[Fix core lib warning] Fix numpy dtype (#5027 )
2022-12-15 09:04:16 +08:00
354a211038
[Sparse] Elementwise ops for DiagMatrix and Elementwise Power for SparseMatrix (#5024 )
2022-12-15 08:33:51 +08:00
32dc1af67e
[Dist] generate partition meta for ParMETIS pipeline (#5020 )
2022-12-14 21:15:54 +08:00
f4f9abc871
[API Deprecation] Remove deprecated_kwargs in edge_subgraph (#4990 )
2022-12-13 09:05:31 +08:00
d02e560e07
Revert "[Sparse] Add SpMM and SDDMM." (#5014 )
2022-12-12 19:37:08 +08:00
15365d7855
[Sparse] Add SpMM and SDDMM. (#4999 )
2022-12-12 15:37:09 +08:00
996c533149
[Model] Fix bug of gatv2 when input is block (#5000 )
2022-12-12 15:32:48 +08:00
236fac4fb9
[Misc] Small fix in sparse GCN example (#5006 )
2022-12-12 15:30:49 +08:00
e01580d3b9
[Sparse] Misc fix for existing elementwise ops (#5003 )
2022-12-09 17:16:59 +08:00
aad3bd0484
[Bugfix] Fix empty tensors may being treated as pinned (#5005 )
2022-12-09 16:42:59 +08:00
e28f07812b
[Sparse] GCN Example (#4996 )
2022-12-09 09:19:38 +08:00
20fb4d4c31
[Lint] Add a formatter GitHub Action for ufmt and clang-format (#4977 )
2022-12-08 13:32:08 +08:00
774d57539c
[CMAKE] Disable --exclude-libs option in MAX OS (#4992 )
2022-12-08 10:40:26 +08:00
394794b19d
Fix bug when feature_tid is empty (#4985 )
2022-12-07 00:35:37 -08:00
279e2e8fba
Add Graph Transformer Layer (Dense Computation) (#4959 )
2022-12-07 16:23:14 +08:00
a80bd9e039
Update (#4997 )
2022-12-07 15:07:50 +08:00
f85da5f533
[Bugfix] Turn off use_alternate_stream when TensorAdaptor is not enabled (#4987 )
2022-12-07 14:41:28 +08:00
a2defae2bf
[Bug] Fix typo in _gsddmm_hetero (#4944 )
2022-12-07 11:16:51 +08:00
84a12cf6a1
[Doc] Add Labor Sampler documentation (#4986 )
2022-12-06 19:42:26 -05:00
ba21295cd5
[Model] Update CuGraphRelGraphConv to use new bindings from pylibcugraphops (#4965 )
2022-12-06 01:00:57 -05:00
fb223d4735
Add support for next cusparse release (#4974 )
2022-12-05 19:55:56 -08:00
97fbd94dfc
[Sparse] neg and inv (#4980 )
2022-12-05 21:19:27 +08:00
edb14f9358
[Dist] remove dependency on deprecated _dataloading (#4979 )
2022-12-05 18:23:09 +08:00
c604366d4c
[Sparse][Example] Add TWIRLS example in sparse API (#4922 )
2022-12-05 16:56:21 +08:00
93ecfa313a
[NN] Add PathEncoder (#4956 )
2022-12-05 13:47:51 +08:00
b84de903a2
GCN example correction (#4969 ) (#4976 )
2022-12-05 03:00:57 +01:00
26612d0cb0
[Fix] Fix record_stream for PyTorch 1.14 (#4975 )
2022-12-02 13:31:47 +08:00
943abba3fb
[Example] add entity_sample example of using CuGraphRelGraphConv (#4827 )
2022-12-01 08:09:14 -05:00
a5a0d9ed9d
[Sparse] C&S Example (#4963 )
2022-12-01 18:35:53 +08:00
611393021a
[API Deprecation] Remove candidates in DGLGraph (#4946 )
2022-12-01 16:41:53 +08:00
e088acac00
[Sparse] Add val_like and Disable Setting Nonzero Values (#4972 )
2022-12-01 14:09:36 +08:00
b1e2695f3e
[Feature] replace dgl PRNG with pcg32 (#4807 )
2022-11-30 20:19:28 -05:00
nv-dlasalle