Skip to content

[torch.compile] fix sym_tensor_indices #12191

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 2 commits into from
Jan 20, 2025
Merged

[torch.compile] fix sym_tensor_indices #12191

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ddddf33
fix sym_tensor_indices
youkaichao Jan 19, 2025
d5c42f2
use torch check
youkaichao Jan 20, 2025
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
3 changes: 3 additions & 0 deletions vllm/compilation/backends.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -624,9 +624,12 @@ def __call__(self, graph: fx.GraphModule, example_inputs) -> Callable:
]

# index of tensors that have symbolic shapes (batch size)
# for weights and static buffers, they will have concrete shapes,
# and therefore x.numel() will be an integer.
self.sym_tensor_indices = [
i for i, x in enumerate(fake_args)
if isinstance(x, torch._subclasses.fake_tensor.FakeTensor)
and not isinstance(x.numel(), int)
]

# compiler managed cudagraph input buffers
Expand Down
Loading