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

[sparse] Update cuSPARSELt to v0.6.2 (#134022)

Browse Source 
Summary:

This PR updated cuSPARSELt to v0.6.2. I think we should land
https://github.com/pytorch/pytorch/pull/128534 first though.

Most of this PR is just enabling tests to run when cuSPARSELt v0.6.2 is
available.

Unfortunately was running into a bug with fp32 support on Hopper, so I
removed fp32 support from the cuSPARSELt backend. I think this should be
fine since almost everybody uses the bfloat/float16/int8 kernels.

Test Plan:

Reviewers:

Subscribers:

Tasks:

Tags:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/134022
Approved by: https://github.com/jerryzh168, https://github.com/malfet
ghstack dependencies: #128534
This commit is contained in:
Jesse Cai
2024-08-22 15:22:39 -07:00
committed by PyTorch MergeBot
parent 74a9001ada
commit 157de30f53
4 changed files with 55 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
torch/sparse/semi_structured.py
View File

@ -537,7 +537,6 @@ class SparseSemiStructuredTensorCUSPARSELT(SparseSemiStructuredTensor):
torch.int8: _SEMI_STRUCTURED_SPARSE_CONFIG(32, 32, 16, 16),
torch.float16: _SEMI_STRUCTURED_SPARSE_CONFIG(16, 16, 8, 8),
torch.bfloat16: _SEMI_STRUCTURED_SPARSE_CONFIG(16, 16, 8, 8),
torch.float32: _SEMI_STRUCTURED_SPARSE_CONFIG(8, 8, 4, 4),
}
@classmethod