vllm-project/vllm-omni

[New Model]: OmniWeaving

Open

#2,664 opened on Apr 10, 2026

View on GitHub
 (3 comments) (0 reactions) (1 assignee)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

The model to consider.

OmniWeaving: https://github.com/Tencent-Hunyuan/OmniWeaving

The closest model vllm-omni already supports.

OmniWeaving consists of MLLM and MMDiT:

  1. MLLM: base model is Qwen2.5-VL
  2. MMDiT: base model is HunyuanVideo 1.5 (already supported in vLLM-Omni)

What's your difficulty of supporting the model you want?

No response

Use case and motivation

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 existing HunyuanVideo 1.5 support in vLLM Omni and the Qwen2.5 VL MLLM implementation. Then determine how to compose OmniWeaving by reusing those components and adding any missing parts. Look at the repository's model contribution guide.
Tech stack
python
Domain
aibackend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
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.
Clear
Prerequisites
GitPythonModel Integration Experience
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40