Skip to content

[float8] fuse abs/max with torch.linalg.vector_norm #905

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

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

[float8] fuse abs/max with torch.linalg.vector_norm #905

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 torchao/float8/float8_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,7 @@ def amax_history_to_scale_stack(

@torch.no_grad()
def tensor_to_amax(x: torch.Tensor, reduce_amax: bool = False) -> torch.Tensor:
amax = torch.max(torch.abs(x))
amax = torch.linalg.vector_norm(x, ord=float("inf"))

# If the user asked for distributed reduction, do it.
# If the user did not ask for it, assume that it will
Expand Down
Loading