transformers
Fix continuous batching for multimodal models
#44436
Merged

Fix continuous batching for multimodal models #44436

jw9603
Fix continuous batching for multimodal models
ffa676af
zucchini-nlp
zucchini-nlp commented on 2026-03-04
Add continuous batching test for VLM
68ed6a43
remi-or
remi-or commented on 2026-03-05
remi-or
remi-or commented on 2026-03-05
jw9603 jw9603 requested a review from remi-or remi-or 31 days ago
jw9603 jw9603 requested a review from zucchini-nlp zucchini-nlp 31 days ago
jw9603
Fall back to regular generate for non-text-only models
007e4e18
remi-or
Add warning when falling back from continuous batching
6decf8f1
jw9603
remi-or
remi-or approved these changes on 2026-03-09
remi-or Merge branch 'main' into fix-continuous-batching-tokenize
9f0a70e9
HuggingFaceDocBuilderDev
remi-or remi-or merged 70ca366f into main 27 days ago
jw9603 jw9603 deleted the fix-continuous-batching-tokenize branch 27 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone