transformers
Fix Qwen3-Omni inference when mixing video and image inputs in one batch
#41741
Merged
Merged
Fix Qwen3-Omni inference when mixing video and image inputs in one batch #41741
zucchini-nlp
merged
2 commits into
huggingface:main
from
BakerBunker:fix-qwen3omni-vi-batch
Fix qwen3omni inference when mixing video and image inputs in one batch
16972110
zucchini-nlp
commented
on 2025-10-20
Fix `router_aux_loss_coef`
afa43305
zucchini-nlp
approved these changes
on 2025-10-20
Login to write a write a comment.
Login via GitHub