Skip to content

[Bugfix] Fix MRoPE Errors in the Qwen-VL Model When Processing Pure Text #18407

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 20, 2025
Merged

[Bugfix] Fix MRoPE Errors in the Qwen-VL Model When Processing Pure Text #18407

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
18804d9
fix mrop for pure text input in vl models in graph mode.
May 20, 2025
bc2e246
Merge branch 'main' of https://github.com/vllm-project/vllm into fix_…
May 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
8 changes: 0 additions & 8 deletions vllm/worker/model_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -729,8 +729,6 @@ def _compute_multi_modal_input(self, inter_data: InterDataForSeqGroup,
mm_kwargs, placeholder_maps = MultiModalPlaceholderMap.from_seq_group(
seq_group_metadata,
range(positions[0], positions[0] + len(positions)))
if not mm_kwargs:
return

inter_data.multi_modal_kwargs = mm_kwargs
inter_data.multi_modal_placeholder_maps = placeholder_maps
Expand All @@ -741,12 +739,6 @@ def _compute_multi_modal_input(self, inter_data: InterDataForSeqGroup,
video_grid_thw = mm_kwargs.get("video_grid_thw", None)
audio_feature_lengths = mm_kwargs.get("audio_feature_lengths",
None)
assert (
image_grid_thw is not None or video_grid_thw is not None
or audio_feature_lengths is not None), (
"mrope embedding type requires multi-modal input mapper "
"returns 'image_grid_thw' or 'video_grid_thw' or "
"'audio_feature_lengths'.")

second_per_grid_ts = mm_kwargs.get("second_per_grid_ts", None)
use_audio_in_video = mm_kwargs.get("use_audio_in_video", False)
Expand Down