[Models] Kimi-K2.5 (#33131)

Signed-off-by: wanglinian <wanglinian@stu.pku.edu.cn>
Signed-off-by: wangln19 <96399074+wangln19@users.noreply.github.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: wanglinian <wanglinian@stu.pku.edu.cn>
Co-authored-by: wangln19 <96399074+wangln19@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Roger Wang
2026-01-27 14:50:31 +08:00
committed by GitHub
co-authored by wanglinian wangln19 Zaida Zhou Isotr0py Nick Hill youkaichao gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent 6c00645712
commit b539f988e1
16 changed files with 1799 additions and 8 deletions
+19
View File
@@ -384,6 +384,13 @@ class VideoEmbeddingItems(EmbeddingItems):
super().__init__(data, "video", expected_hidden_size)
class VisionChunkProcessorItems(ProcessorBatchItems[Any]):
"""Processor items for vision chunks (unified image and video chunks)."""
def __init__(self, data: Sequence[Any]) -> None:
super().__init__(data, "vision_chunk")
_D = TypeVar("_D", bound=ModalityDataItems[Any, Any])
@@ -652,11 +659,23 @@ class MultiModalDataParser:
return VideoProcessorItems(new_videos, metadata=metadata_lst)
def _parse_vision_chunk_data(
self,
data: ModalityData[Any],
) -> ModalityDataItems[Any, Any] | None:
"""Parse vision chunk data (unified image and video chunks)."""
if data is None or self._is_empty(data):
return None
if self.is_embeddings(data):
raise ValueError("Do not support embedding data for vision_chunk right now")
return VisionChunkProcessorItems(data)
def _get_subparsers(self) -> Mapping[str, ModalityDataParser]:
return {
"audio": self._parse_audio_data,
"image": self._parse_image_data,
"video": self._parse_video_data,
"vision_chunk": self._parse_vision_chunk_data,
}
def parse_mm_data(self, mm_data: MultiModalDataDict) -> MultiModalDataItems: