biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-08-18 17:52:00 +08:00
committed by GitHub
parent 5c79b0d648
commit 27e8d1ea3e
77 changed files with 431 additions and 383 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/models/llava_next_video.py
View File

@@ -16,7 +16,7 @@ from vllm.model_executor.models.clip import CLIPVisionModel
from vllm.model_executor.sampling_metadata import SamplingMetadata
from vllm.multimodal import MULTIMODAL_REGISTRY
from vllm.multimodal.inputs import (MultiModalDataDict, MultiModalFieldConfig,
MultiModalKwargs)
MultiModalKwargsItems)
from vllm.multimodal.parse import (ImageSize, MultiModalDataItems,
VideoEmbeddingItems, VideoProcessorItems)
from vllm.multimodal.processing import (BaseMultiModalProcessor,
@@ -185,7 +185,7 @@ class LlavaNextVideoMultiModalProcessor(
self,
mm_items: MultiModalDataItems,
hf_processor_mm_kwargs: Mapping[str, object],
out_mm_kwargs: MultiModalKwargs,
out_mm_kwargs: MultiModalKwargsItems,
) -> Sequence[PromptUpdate]:
hf_config = self.info.get_hf_config()
video_token_id = hf_config.video_token_index