Skip to content
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

Avoid using torch.compile for roll and fill_ #609

Merged
merged 2 commits into from
Jan 19, 2024
Merged

Avoid using torch.compile for roll and fill_ #609

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d307849
Avoid using torch.compile for roll and fill_
ksivaman Jan 17, 2024
321144d
Merge branch 'main' into avoid_torch_compile_for_roll_kernel
ksivaman Jan 17, 2024
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
4 changes: 2 additions & 2 deletions transformer_engine/pytorch/fp8.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -583,7 +583,7 @@ def _update_amax_history(amax_history: torch.Tensor) -> torch.Tensor:
return amax_history


@jit_fuser
@torch.jit.script
def _default_get_amax(
amax_history: torch.Tensor,
amax_compute_algo: str,
Expand Down Expand Up @@ -625,7 +625,7 @@ def _compute_scaling_factor_inverse(
return torch.where(non_weight_mask, 1.0 / scale, scale_inv)


@jit_fuser
@torch.jit.script
def _fused_amax_and_scale_update(
amax_history: torch.Tensor,
scale: torch.Tensor,
Expand Down