We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 292084e commit c55bc1dCopy full SHA for c55bc1d
vllm/model_executor/models/qwen2_vl.py
@@ -1225,7 +1225,6 @@ def get_multimodal_embeddings(self,
1225
modalities = self._parse_and_validate_multimodal_inputs(**kwargs)
1226
if not modalities:
1227
return []
1228
- return None
1229
1230
# The result multimodal_embeddings is tuple of tensors, with each
1231
# tensor correspoending to a multimodal data item (image or video).
0 commit comments