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

Jump to bottom

int4_weight_only dequant does not restore original shape #848

Open

jerryzh168 opened this issue Sep 9, 2024 · 0 comments

Contributor

jerryzh168 commented Sep 9, 2024

att, I think it's because we did padding before:

ao/torchao/dtypes/affine_quantized_tensor.py

Line 480 in e1039ab

def pre_process(self, input: torch.Tensor) -> torch.Tensor:

and we should restore the shape after unpacking from TensorCoreTiledLayout

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment