Skip to content

Fix flaky CI: test_vlm_models #8006

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
zhyncs merged 4 commits into from
Jul 14, 2025
Merged

Fix flaky CI: test_vlm_models #8006

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
fe656be
Fix flakey CI: test_vlm_models
lifuhuang Jul 14, 2025
8591dfb
Delete prints
lifuhuang Jul 14, 2025
8d2eebe
Minor
lifuhuang Jul 14, 2025
589f049
Fix
lifuhuang Jul 14, 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
1 change: 0 additions & 1 deletion python/sglang/srt/managers/mm_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,6 @@ def pad_input_tokens(
This function will replace the data-tokens in between with pad_values accordingly
"""
pad_values = [item.pad_value for item in mm_inputs.mm_items]
print(f"{mm_inputs.mm_items=}")
data_token_pairs = self.data_token_id_pairs
mm_inputs.data_offsets = []
if data_token_pairs is None:
Expand Down
3 changes: 0 additions & 3 deletions python/sglang/srt/multimodal/processors/gemma3.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,6 @@ async def process_mm_data_async(
*args,
**kwargs,
):
print(f"{image_data=}")
base_output = self.load_mm_data(
prompt=input_text,
image_data=image_data,
Expand All @@ -48,8 +47,6 @@ async def process_mm_data_async(
)

mm_items, input_ids, _ = self.process_and_combine_mm_data(base_output)
print(f"{base_output=}")
print(f"{mm_items=}")
return {
"input_ids": input_ids.tolist(),
"mm_items": mm_items,
Expand Down
Loading