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

[BE][6/16] fix typos in torch/ (#156316)

Browse Source 
Pull Request resolved: https://github.com/pytorch/pytorch/pull/156316
Approved by: https://github.com/albanD
ghstack dependencies: #156313, #156314, #156315
This commit is contained in:
Xuehai Pan
2025-06-22 13:21:04 +08:00
committed by PyTorch MergeBot
parent c2f0292bd5
commit b210cf1ea5
32 changed files with 58 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
torch/sparse/semi_structured.py
View File

@ -37,7 +37,7 @@ _SEMI_STRUCTURED_SPARSE_CONFIG = namedtuple(
class SparseSemiStructuredTensor(torch.Tensor):
"""
This class implementes semi-structured sparsity as a Tensor subclass.
This class implements semi-structured sparsity as a Tensor subclass.
Semi-structured sparsity describes a sparsity pattern where n in every 2n elements are sparse,
depending on the datatype. It is also referred to as 2:4 sparsity or fine-grained
@ -46,11 +46,11 @@ class SparseSemiStructuredTensor(torch.Tensor):
There are two backends available for semi_structred sparsity, either cuSPARSELt or CUTLASS.
This class is meant to serve as a base class for both implementations. SparseSemiStructuredCUTLASS
and SparseSemiStructuredCUSPARSELT both inherit from this class and define three backend-specific items.
Note that as such, this class cannot be insantiated directly.
Note that as such, this class cannot be instantiated directly.
-`_DTYPE_SHAPE_CONSTRAINTS` - A dictionary holding backend specific dense/sparse min shape constraints
- `def from_dense()` - backend specific compression routines
- `def _mm()` - backend specifc mm op (either torch._cslt_sparse_mm or torch._sparse_semi_structured_(mm|addmm))
- `def _mm()` - backend specific mm op (either torch._cslt_sparse_mm or torch._sparse_semi_structured_(mm|addmm))
"""
_DEFAULT_ALG_ID: int = 0
@ -123,7 +123,7 @@ class SparseSemiStructuredTensor(torch.Tensor):
)
cls._PROTOTYPE_WARNING_SHOWN = True
# Because this only runs onces, we also load the dispatch table here as well.
# Because this only runs once, we also load the dispatch table here as well.
# We can't define the dispatch table explicitly because of torch.ops import errors, so we do this instead
# But this is useful since it allows users to overload the dispatch table for debugging / testing.
cls._load_dispatch_table()
@ -325,7 +325,7 @@ def to_sparse_semi_structured(
This function will check to ensure the dense tensor has the right dtype, size, dims, and device.
We currently only support semi-structured sparse tensors for 2d CUDA tensors.
Additionally, your tensor must be a positive multiple of the mininum sparse block size, given in
Additionally, your tensor must be a positive multiple of the minimum sparse block size, given in
`_DTYPE_TO_SHAPE_CONSTRAINTS` for each dtype (float32, float16, bfloat16, int8).
Args:
@ -388,7 +388,7 @@ class SparseSemiStructuredTensorCUTLASS(SparseSemiStructuredTensor):
This class implements semi-structured sparsity for the CUTLASS backend.
In this implementation, the specified elements and metadata are stored seprately,
In this implementation, the specified elements and metadata are stored separately,
in packed and meta respectively.
When _FORCE_CUTLASS is set, or when cuSPARSELt is not available, this subclass calls into _sparse_semi_structured_(mm|addmm) and