vllm-project/vllm-omni

[New Model]: deepseek-janus

Open

#3,205 opened on Apr 28, 2026

View on GitHub
 (3 comments) (1 reaction) (1 assignee)Python (1,067 forks)github user discovery
help wantedhigh prioritynew model

Repository metrics

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

Description

The model to consider.

https://github.com/deepseek-ai/Janus

The closest model vllm-omni already supports.

bagel&hy-image

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
Examine the Janus model architecture (https://github.com/deepseek ai/Janus) and study how similar multimodal models are implemented in vllm omni, particularly the bagel&hy image model. Identify the necessary changes to register and run the Janus model within the existing omni modality inference pipeline. Start by reading the model registration guide and existing model implementations.
Tech stack
python
Domain
backendai
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.
3-5 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.
Needs investigation
Prerequisites
PythonGitPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30