vllm-project/vllm

[Feature]: Qwen3 Omni Transcriptions

Open

#29405 opened on Nov 25, 2025

View on GitHub
 (9 comments) (0 reactions) (1 assignee)Python (80,034 stars) (16,816 forks)batch import
feature requestgood first issue

Description

🚀 The feature, motivation and pitch

Would love to see this model included in the supported as a Transcription model. According to the docs it looks like only 4 different models are supported as of now.

https://docs.vllm.ai/en/latest/models/supported_models/#transcription

Alternatives

No response

Additional context

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

Tech stack
python
Domain
machine learningai
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.
3-5 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
blocked
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Basic understanding of vllm architectureFamiliarity with Qwen model family
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30
Research direction
Examine the existing transcription model implementations in vllm (e.g., Whisper) to understand the required interfaces. Then study the Qwen3 Omni model to determine how to integrate it as a transcription model. Focus on model loading, inference, and configuration files. The issue has an assignee, so coordinate with them to avoid duplication.