Skip to content

[Bugfix] Ensure tensors are contiguous during serialisation #18860

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
May 29, 2025
Merged

[Bugfix] Ensure tensors are contiguous during serialisation #18860

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3f333ad
[Bugfix] Ensure tensors are contiguous during serialisation
lgeiger May 28, 2025
1bc3bf3
Force contiguous data after flatten
lgeiger May 28, 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
4 changes: 2 additions & 2 deletions vllm/v1/serial_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,8 +158,8 @@ def _encode_tensor(
self, obj: torch.Tensor
) -> tuple[str, tuple[int, ...], Union[int, memoryview]]:
assert self.aux_buffers is not None
# view the tensor as a 1D array of bytes
arr = obj.flatten().view(torch.uint8).numpy()
# view the tensor as a contiguous 1D array of bytes
arr = obj.flatten().contiguous().view(torch.uint8).numpy()
if obj.nbytes < self.size_threshold:
# Smaller tensors are encoded inline, just like ndarrays.
data = msgpack.Ext(CUSTOM_TYPE_RAW_VIEW, arr.data)
Expand Down