Skip to content

Commit 103ebce

Browse files
committed
fix: dropping redundant task visual-question-answering, it's overruled
by `image-text-to-text` Signed-off-by: DWarez <dario.salvati@huggingface.co>
1 parent 9883435 commit 103ebce

1 file changed

Lines changed: 1 addition & 1 deletion

File tree

‎sagemaker-serve/src/sagemaker/serve/constants.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -71,10 +71,10 @@
7171
}
7272

7373
# HuggingFace pipeline tags that should route to the vLLM-omni (multimodal) server.
74+
# Note: visual-question-answering is folded into image-text-to-text as of transformers v5.
7475
OMNI_TASKS: Set[str] = {
7576
"image-text-to-text",
7677
"any-to-any",
77-
"visual-question-answering",
7878
"audio-text-to-text",
7979
}
8080

0 commit comments

Comments
 (0)