[MM] Remove text components from ProcessorInputs (#53093)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-08-20 20:42:53 -07:00
committed by GitHub
parent 2adf4b9e2a
commit b00f475f09
92 changed files with 220 additions and 806 deletions
-7
View File
@@ -456,13 +456,11 @@ return a schema of the tensors outputted by the HF processor that are related to
prompt: str,
mm_data: Mapping[str, object],
mm_kwargs: Mapping[str, object],
tok_kwargs: Mapping[str, object],
) -> BatchFeature:
processed_outputs = super()._call_hf_processor(
prompt=prompt,
mm_data=mm_data,
mm_kwargs=mm_kwargs,
tok_kwargs=tok_kwargs,
)
pixel_values = processed_outputs.get("pixel_values")
@@ -479,11 +477,6 @@ return a schema of the tensors outputted by the HF processor that are related to
return processed_outputs
```
!!! note
The `_call_hf_processor` method specifies both `mm_kwargs` and `tok_kwargs` for
processing. `mm_kwargs` is used to both initialize and call the huggingface
processor, whereas `tok_kwargs` is only used to call the huggingface processor.
Since `pixel_values` is now a list with one tensor per image, we can override
[_get_mm_fields_config][vllm.multimodal.processing.BaseMultiModalProcessor._get_mm_fields_config] as follows: