Cyrus Leung afffd3cc8a

[Model] Pass mm_features directly into get_mrope_input_positions (#28399) ...

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

2025-11-11 21:14:48 +08:00

..

__init__.py

…

audio.py

…

base.py

…

cache.py

[Chore] Separate out vllm.utils.mem_utils (#27143)

2025-10-18 10:06:59 +00:00

evs.py

…

hasher.py

…

image.py

…

inputs.py

[Model] Pass mm_features directly into get_mrope_input_positions (#28399)

2025-11-11 21:14:48 +08:00

parse.py

[Misc] Raise error for missing video metadata in MultiModalDataParser (#27664)

2025-10-29 10:06:42 +00:00

processing.py

[Frontend] Require flag for loading text and image embeds (#27204)

2025-10-22 15:52:02 +00:00

profiling.py

[V0 deprecation] Remove VLLM_USE_V1 usage in most modules (#27955)

2025-11-04 20:51:16 -08:00

registry.py

[Misc] Simplify max tokens in multimodal registry (#27500)

2025-10-24 23:56:01 -07:00

utils.py

[Core][MM] Add mechanism to configure multimodal fields which should stay on CPU (#28168)

2025-11-07 12:14:29 +00:00

video.py

[Multimodal] Make MediaConnector extensible. (#27759)

2025-11-04 18:28:01 +00:00