vllm-project/vllm

[Feature]: Qwen3 Omni Transcriptions

Open

#29,405 创建于 2025年11月25日

在 GitHub 查看
 (9 评论) (0 反应) (1 负责人)Python (80,034 star) (16,816 fork)batch import
feature requestgood first issue

描述

🚀 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.

贡献者指南

技术栈
python
领域
machine learningai
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
4
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
3-5 days
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
blocked
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
Basic understanding of vllm architectureFamiliarity with Qwen model family
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
30
研究方向
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.