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

[Doc] Show that use_audio_in_video is supported in docs (#30837)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-01-06 15:27:19 +08:00
committed by GitHub
parent 1fb0209bbc
commit da71d44410
4 changed files with 0 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/qwen2_5_omni_thinker.py
View File

@@ -1128,8 +1128,6 @@ class Qwen2_5OmniThinkerForConditionalGeneration(
multimodal_embeddings += tuple(audio_embeddings)
return multimodal_embeddings
# TODO (ywang96): support overlapping modality embeddings so that
# `use_audio_in_video` will work on V1.
def embed_input_ids(
self,
input_ids: torch.Tensor,

2
vllm/model_executor/models/qwen3_omni_moe_thinker.py
View File

@@ -1371,8 +1371,6 @@ class Qwen3OmniMoeThinkerForConditionalGeneration(
return inputs_embeds
deepstack_input_embeds = None
# TODO (ywang96): support overlapping modalitiy embeddings so that
# `use_audio_in_video` will work on V1.
# split the feat dim to obtain multi-scale visual feature
has_vision_embeddings = [
embeddings.shape[-1] != self.config.text_config.hidden_size