Skip to content

Add torch.float64 as a viable dtype for scales #379

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
Jul 9, 2025
Merged

Add torch.float64 as a viable dtype for scales #379

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
2 changes: 1 addition & 1 deletion src/compressed_tensors/quantization/lifecycle/initialize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -189,7 +189,7 @@ def _initialize_scale_zero_point(
else:
# TODO: consider erroring out in the future as if the dtype if not one of these,
# there is likely bug
if scale_dtype not in [torch.float16, torch.bfloat16, torch.float32]:
if scale_dtype not in [torch.float16, torch.bfloat16, torch.float32, torch.float64]:
scale_dtype = torch.float16
zp_dtype = quantization_args.pytorch_dtype()

Expand Down