Skip to content

Add an assertion to enhance the robustness of the operator #5736

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
Apr 27, 2025
Merged

Add an assertion to enhance the robustness of the operator #5736

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
18d3c73
In the VisionSdpaAttention class, an assertion has been added for the…
Apr 25, 2025
8c51650
Merge branch 'main' into add-check-of--vision-attention
merrymercy Apr 25, 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
2 changes: 2 additions & 0 deletions python/sglang/srt/layers/attention/vision.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -271,6 +271,8 @@ def forward(
Returns:
[b * s, h, head_size]
"""
if self.flatten_batch:
assert bsz == 1, "flatten_batch is True, bsz must be 1"
Copy link
Collaborator

Choose a reason for hiding this comment

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

LGTM. It is beneficial for the addition of a new model.


s = q.shape[0] // bsz

Expand Down
Loading