Skip to content

Unbreak build after #621 #826

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

Merged
merged 1 commit into from
Sep 6, 2024
Merged

Unbreak build after #621 #826

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
5 changes: 3 additions & 2 deletions torchao/dtypes/affine_quantized_tensor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,5 @@
import torch
from typing import Tuple, Optional, Union
import torchao.ops
from collections import defaultdict
import functools
import math
Expand Down Expand Up @@ -1425,6 +1424,8 @@ def _linear_fp_act_int4_weight_sparse_marlin_check(input_tensor, weight_tensor,

def _linear_fp_act_int4_weight_sparse_marlin_impl(input_tensor, weight_tensor, bias):
from torchao.sparsity.marlin import marlin_24_workspace, const
from torchao.ops import marlin_24_gemm

assert isinstance(weight_tensor, AffineQuantizedTensor)

sparse_w_int4 = weight_tensor.layout_tensor.int_data
Expand All @@ -1441,7 +1442,7 @@ def _linear_fp_act_int4_weight_sparse_marlin_impl(input_tensor, weight_tensor, b
size_k = input_2d.shape[1]
workspace_24 = marlin_24_workspace(original_shape[1])

out = torchao.ops.marlin_24_gemm(
out = marlin_24_gemm(
input_2d, sparse_w_int4, meta, scale,
workspace_24, num_bits, size_m, size_n, size_k
)
Expand Down
Loading