Skip to content

Refactor NF4Tensor to use dispatch utils #543

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

Refactor NF4Tensor to use dispatch utils #543

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions torchao/dtypes/affine_quantized_tensor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -487,7 +487,7 @@ def __torch_dispatch__(cls, func, types, args, kwargs):
)

def get_plain(self):
# Currently we don't have cuSPARSELt expansion routines, so we matmul by
# Currently we don't have cuSPARSELt expansion routines, so we matmul by
# the identity matrix to get the original dense matrix. This is slow though.
cols = self.int_data.numel() * 16 // (10 * self.scale.shape[0])
int_data_expanded = torch._cslt_sparse_mm(self.int_data,
Expand All @@ -507,7 +507,7 @@ def from_plain(
assert isinstance(layout_type, SemiSparseLayoutType)
int_data_compressed = torch._cslt_compress(int_data)
return cls(int_data_compressed, scale, zero_point, layout_type)


@register_layout_cls(TensorCoreTiledLayoutType)
class TensorCoreTiledAQTLayout(AQTLayout):
Expand Down
Loading
Loading