anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Model] Support NVIDIA-NemotronLabs-VoiceChat-11B offline speech-to-speech (#5842)

Browse Source 
Signed-off-by: Yuekai Zhang <zhangyuekai@foxmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Yuekai ZhangandClaude Fable 5 authored and GitHub committed 2026-08-12 16:25:48 +08:00
1 parent 9b0df3909a
commit 5be7541d01
46 files changed
+13034
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

mkdocs.yml
+1
View File
@@ -111,6 +111,7 @@ plugins:
- "vllm_omni.entrypoints.openai" # avoid importing vllm in mkdocs building
- "vllm_omni.entrypoints.openai.protocol" # avoid importing vllm in mkdocs building
- "vllm_omni.experimental" # avoid importing optional serving deps (openai, fastapi, uvicorn, httpx) in mkdocs building
- "vllm_omni.model_executor.models.nemotron_voicechat.nemo_vendored" # vendored NeMo code; upstream docstrings trip griffe strict warnings
- mkdocstrings:
handlers:
python: