Skip to content

GitLab

Unverified Commit 0a3960f2 authored by Yineng Zhang's avatar Yineng Zhang Committed by GitHub
Browse files

fix awq_dequantize (#4333)

parent 07f94463
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
sgl-kernel/python/sgl_kernel/gemm.py
View file @ 0a3960f2
......@@ -7,7 +7,7 @@ from sgl_kernel.utils import _get_cache_buf, get_cuda_stream
def awq_dequantize(
qweight: torch.Tensor, scales: torch.Tensor, qzeros: torch.Tensor
) -> torch.ByteTensor:
return torch.ops.sgl_kernels.awq_dequantize(qweight, scales, qzeros)
return torch.ops.sgl_kernel.awq_dequantize(qweight, scales, qzeros)
def int8_scaled_mm(mat_a, mat_b, scales_a, scales_b, out_dtype, bias=None):
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment