vllm-project/vllm-omni

[RFC]: Support Wan-AI/Wan2.2-S2V-14B in vllm-omni

Open

#2,612 opened on Apr 8, 2026

View on GitHub
 (3 comments) (0 reactions) (2 assignees)Python (1,067 forks)github user discovery
good first issuehelp wantednew model

Repository metrics

Stars
 (4,990 stars)
PR merge metrics
 (PR metrics pending)

Description

Motivation.

SOTA audio-driven model which enables lip-synced video generation based on input image and audio. This RFC is to propose Wan2.2-S2V model support in vllm-omni

Example model weight: Wan-AI/Wan2.2-S2V-14B

Input:

db4810e2-a379-41e9-815f-bbb1a9cafbae.mp3

output:

https://github.com/user-attachments/assets/25e108b8-93cf-4575-b6cd-ff4a00ddd845

Proposed Change.

Please provide the detailed design document of the RFC using the template.

Feedback Period.

No response

CC List.

@hsliuustc0106 @Gaohan123 @gcanlin

Any Other Things.

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

Contributor guide

Research direction
Study the Wan2.2 model architecture and understand how to integrate it into vllm omni's model registry. Look at existing similar model support for reference.
Tech stack
python
Domain
aiaudio video rtc
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
Python
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30