frozenleaves/pytorch
1
0
Fork 0
mirror of https://github.com/pytorch/pytorch.git synced 2025-10-20 21:14:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix SEMI_STRUCTURED_SUPPORTED_BACKENDS selection on CUDA and ROCm (#163223)

Browse Source 
It should work with the current CUDA/ROCm device_capability enumeration anyway. But it will help to avoid unexpected triggering in the future

Pull Request resolved: https://github.com/pytorch/pytorch/pull/163223
Approved by: https://github.com/jeffdaily
This commit is contained in:
Dmitry Nikolaev
2025-09-18 06:29:25 +00:00
committed by PyTorch MergeBot
parent 708dc6e3cd
commit 6f9b4ccf8f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
test/test_sparse_semi_structured.py
View File

@ -50,8 +50,8 @@ _IS_SM9X = False
_IS_HIPSPARSELT_AVAILABLE = False
if torch.cuda.is_available():
_IS_SM8X = torch.cuda.get_device_capability(0)[0] == 8
_IS_SM9X = torch.cuda.get_device_capability(0)[0] == 9
_IS_SM8X = torch.version.cuda is not None and (torch.cuda.get_device_capability(0)[0] == 8)
_IS_SM9X = torch.version.cuda is not None and (torch.cuda.get_device_capability(0)[0] == 9)
_IS_HIPSPARSELT_AVAILABLE = torch.version.hip is not None and tuple(int(v) for v in torch.version.hip.split('.')[:2]) > (6, 4)
# CUTLASS kernels only work for Ampere
if _IS_SM8X: