[Renderer] Move MM Hash parsing into Renderer (#34711)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-02-17 19:18:55 -08:00
committed by GitHub
parent df3f537a66
commit a0d8d944e2
16 changed files with 254 additions and 217 deletions
+9 -6
View File
@@ -36,9 +36,13 @@ from vllm.multimodal.inputs import (
MultiModalFieldConfig,
MultiModalInputs,
MultiModalKwargsItems,
MultiModalUUIDDict,
)
from vllm.multimodal.parse import ImageProcessorItems, ImageSize, MultiModalDataItems
from vllm.multimodal.parse import (
ImageProcessorItems,
ImageSize,
MultiModalDataItems,
MultiModalUUIDItems,
)
from vllm.multimodal.processing import (
BaseDummyInputsBuilder,
BaseMultiModalProcessor,
@@ -203,10 +207,9 @@ class CLIPMultiModalProcessor(BaseMultiModalProcessor[CLIPProcessingInfo]):
self,
prompt: str | list[int],
mm_items: MultiModalDataItems,
hf_processor_mm_kwargs: Mapping[str, object],
mm_uuid_items: MultiModalUUIDItems | None = None,
hf_processor_mm_kwargs: Mapping[str, object] | None = None,
tokenization_kwargs: Mapping[str, object] | None = None,
*,
mm_uuids: MultiModalUUIDDict | None = None,
) -> MultiModalInputs:
if mm_items:
if isinstance(prompt, str):
@@ -235,9 +238,9 @@ class CLIPMultiModalProcessor(BaseMultiModalProcessor[CLIPProcessingInfo]):
return super().apply(
prompt=prompt,
mm_items=mm_items,
mm_uuid_items=mm_uuid_items,
hf_processor_mm_kwargs=hf_processor_mm_kwargs,
tokenization_kwargs=tokenization_kwargs,
mm_uuids=mm_uuids,
)
def _hf_processor_applies_updates(