Zitong Zhan 90c821814e SparseCsrCUDA: cuDSS backend for linalg.solve (#129856) ... This PR switches to cuDSS library and has the same purpose of #127692, which is to add Sparse CSR tensor support to linalg.solve. Fixes #69538 Minimum example of usage: ``` import torch if __name__ == '__main__': spd = torch.rand(4, 3) A = spd.T @ spd b = torch.rand(3).to(torch.float64).cuda() A = A.to_sparse_csr().to(torch.float64).cuda() x = torch.linalg.solve(A, b) print((A @ x - b).norm()) ``` Pull Request resolved: https://github.com/pytorch/pytorch/pull/129856 Approved by: https://github.com/amjames, https://github.com/lezcano, https://github.com/huydhn Co-authored-by: Zihang Fang <zhfang1108@gmail.com> Co-authored-by: Huy Do <huydhn@gmail.com>		2024-08-22 07:57:30 +00:00
..
__init__.py	SparseCsrCUDA: cuDSS backend for linalg.solve (#129856)	2024-08-22 07:57:30 +00:00
_semi_structured_conversions.py	Enable UFMT on all of torch/sparse (#130545)	2024-07-15 22:35:52 +00:00
_semi_structured_ops.py	[BE][Easy][19/19] enforce style for empty lines in import segments in torch/[o-z]*/ (#129771)	2024-08-01 17:07:14 +00:00
_triton_ops_meta.py	Tune _int_bsr_dense_addmm for int8 inputs on A100 (#134035)	2024-08-22 06:43:11 +00:00
_triton_ops.py	Add int8 support to bsr_dense_addmm and bsr_dense_mm Triton kernels (#133855)	2024-08-21 20:44:40 +00:00
semi_structured.py	[BE][Easy][19/19] enforce style for empty lines in import segments in torch/[o-z]*/ (#129771)	2024-08-01 17:07:14 +00:00