ggml-org/llama.cpp

Feature Request: support Qwen3-omni, Qwen3-TTS and MiniCPM-o

Closed

#17,634 opened on Dec 1, 2025

View on GitHubContributor guide
 (14 comments) (29 reactions) (0 assignees)C++ (21,323 forks)batch import
Review Complexity : Highenhancementgood first issuehelp wantedmtmdtts

Repository metrics

Stars
 (122,715 stars)
PR merge metrics
 (Avg merge 6d 8h) (389 merged PRs in 30d)

Description

Prerequisites

  • I am running the latest code. Mention the version if possible as well.
  • I carefully followed the README.md.
  • I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
  • I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

support qwen omni audio generator

Motivation

currently omni can work but it does not provide a whisper-like api for tts and it does not support asr.

Possible Implementation

https://github.com/ggml-org/llama.cpp/issues/16885 https://github.com/ggml-org/llama.cpp/issues/16186 https://github.com/ggml-org/llama.cpp/issues/11347

Contributor guide

Research direction
Review the linked issues and existing code for TTS/ASR support in llama.cpp. Understand the model architectures for Qwen3 omni, Qwen3 TTS, and MiniCPM o. Identify the necessary changes to the inference pipeline and audio processing.
Tech stack
cpp
Domain
backendapiai
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
C++Git
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
25