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

Adds FunAudioChat multimodal audio model support (#2) (#33058)

Browse Source 
Signed-off-by: ramos <49182011+nemoramo@users.noreply.github.com>
Signed-off-by: mayufeng <mayufeng@example.com>
Co-authored-by: mayufeng <mayufeng@example.com>
This commit is contained in:
ramos
2026-01-28 13:18:09 +08:00
committed by GitHub
parent a2b877df6c
commit 36d450e3b8
8 changed files with 1264 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1083
vllm/model_executor/models/funaudiochat.py Normal file
View File

File diff suppressed because it is too large Load Diff

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

@@ -312,6 +312,10 @@ _MULTIMODAL_MODELS = {
"ernie45_vl",
"Ernie4_5_VLMoeForConditionalGeneration",
),
"FunAudioChatForConditionalGeneration": (
"funaudiochat",
"FunAudioChatForConditionalGeneration",
),
"FuyuForCausalLM": ("fuyu", "FuyuForCausalLM"),
"Gemma3ForConditionalGeneration": ("gemma3_mm", "Gemma3ForConditionalGeneration"), # noqa: E501
"Gemma3nForConditionalGeneration": (