xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-24 01:55:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Update get_processor_data to use get_all method (#30583)

Browse Source 
Signed-off-by: Drew Botwinick <6953152+dbotwinick@users.noreply.github.com>
This commit is contained in:
Drew Botwinick 2025-12-14 07:19:20 -06:00 committed by GitHub
parent a8ec486592
commit 5b64ac21f9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/multimodal/parse.py
View File

@ -120,7 +120,7 @@ class ProcessorBatchItems(ModalityDataItems[Sequence[_T], _T]):
return self.data[index] return self.data[index]
def get_processor_data(self) -> Mapping[str, object]: def get_processor_data(self) -> Mapping[str, object]:
return {f"{self.modality}s": self.data} return {f"{self.modality}s": self.get_all()}
def get_passthrough_data(self) -> Mapping[str, object]: def get_passthrough_data(self) -> Mapping[str, object]:
return {} return {}