Skip to content

Fix no grad usage #42573

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

Closed
vasqu wants to merge 1 commit into from
+6 −6
Closed

Fix no grad usage #42573

Show file tree
Hide file tree
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
10 changes: 5 additions & 5 deletions src/transformers/core_model_loading.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,7 +106,7 @@ class Chunk(ConversionOps):
def __init__(self, dim: int = 0):
self.dim = dim

@torch.no_grad
@torch.no_grad()
def convert(
self, input_dict: dict[str, torch.Tensor], source_patterns: list[str], target_patterns: list[str], **kwargs
) -> dict[str, torch.Tensor]:
Expand Down Expand Up @@ -134,7 +134,7 @@ class Concatenate(ConversionOps):
def __init__(self, dim: int = 0):
self.dim = dim

@torch.no_grad
@torch.no_grad()
def convert(
self,
input_dict: dict[str, list[torch.Tensor]],
Expand Down Expand Up @@ -175,7 +175,7 @@ class MergeModulelist(ConversionOps):
def __init__(self, dim: int = 0):
self.dim = dim

@torch.no_grad
@torch.no_grad()
def convert(
self,
input_dict: dict[str, list[torch.Tensor]],
Expand Down Expand Up @@ -211,7 +211,7 @@ class SplitModulelist(ConversionOps):
def __init__(self, dim: int = 0):
self.dim = dim

@torch.no_grad
@torch.no_grad()
def convert(
self, input_dict: dict[str, torch.Tensor], source_patterns: list[str], target_patterns: list[str], **kwargs
) -> dict[str, torch.Tensor]:
Expand Down Expand Up @@ -260,7 +260,7 @@ def _apply(self, tensor: torch.Tensor) -> torch.Tensor:
tensor = tensor.transpose(1, 2).reshape(dim1, dim2)
return tensor

@torch.no_grad
@torch.no_grad()
def convert(
self,
input_dict: dict[str, list[torch.Tensor]],
Expand Down
2 changes: 1 addition & 1 deletion src/transformers/generation/continuous_batching/continuous_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -623,7 +623,7 @@ def fail_all_requests(self, error: Exception) -> None:
self.scheduler.waiting_requests_order.clear()

@traced
@torch.no_grad
@torch.no_grad()
Copy link
Contributor Author

@vasqu vasqu Dec 2, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Unsure about this one but I don't see a reason why we would not close here as well cc @remi-or

def _generation_step(self, model: nn.Module, logit_processor: LogitsProcessor, do_sample: bool) -> None:
"""Perform a single generation step."""

Expand Down