# If you already have transformers installed, please uninstall it first, or create a new Python environment
# pip uninstall transformers
pip install git+https://github.com/huggingface/transformers
pip install accelerate

pip install qwen-omni-utils -U

pip install -U flash-attn --no-build-isolation

import soundfile as sf
from transformers import Qwen3OmniMoeForConditionalGeneration, Qwen3OmniMoeProcessor
from qwen_omni_utils import process_mm_info

MODEL_PATH = "Qwen/Qwen3-Omni-30B-A3B-Instruct"
# MODEL_PATH = "Qwen/Qwen3-Omni-30B-A3B-Thinking"

model = Qwen3OmniMoeForConditionalGeneration.from_pretrained(
    MODEL_PATH,
    dtype="auto",
    device_map="auto",
    attn_implementation="flash_attention_2",
)
processor = Qwen3OmniMoeProcessor.from_pretrained(MODEL_PATH)

conversation = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Omni/demo/cars.jpg"},
            {"type": "audio", "audio": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Omni/demo/cough.wav"},
            {"type": "text", "text": "What can you see and hear? Answer in one short sentence."}
        ],
    },
]

# Set whether to use audio in video
USE_AUDIO_IN_VIDEO = True

# Preparation for inference
text = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False)
audios, images, videos = process_mm_info(conversation, use_audio_in_video=USE_AUDIO_IN_VIDEO)
inputs = processor(text=text, audio=audios, images=images, videos=videos, return_tensors="pt", padding=True, use_audio_in_video=USE_AUDIO_IN_VIDEO)
inputs = inputs.to(model.device).to(model.dtype)

# Inference: Generation of the output text and audio
text_ids, audio = model.generate(**inputs, speaker="Ethan", thinker_return_dict_in_generate=True, use_audio_in_video=USE_AUDIO_IN_VIDEO)
text = processor.batch_decode(text_ids.sequences[:, inputs["input_ids"].shape[1] :], skip_special_tokens=True, clean_up_tokenization_spaces=False)

print(text)

if audio is not None:
    sf.write(
        "output.wav",
        audio.reshape(-1).detach().cpu().numpy(),
        samplerate=24000,
    )

git clone -b qwen3_omni https://github.com/wangxiongts/vllm.git
cd vllm
pip install -r requirements/build.txt
pip install -r requirements/cuda.txt
export VLLM_PRECOMPILED_WHEEL_LOCATION=https://wheels.vllm.ai/a5dd03c1ebc5e4f56f3c9d3dc0436e9c582c978f/vllm-0.9.2-cp38-abi3-manylinux1_x86_64.whl
VLLM_USE_PRECOMPILED=1 pip install -e . -v --no-build-isolation
# If you meet an "Undefined symbol" error, use "pip install -e . -v" to build from source.

# Install other dependencies
pip install git+https://github.com/huggingface/transformers
pip install accelerate
pip install qwen-omni-utils -U
pip install -U flash-attn --no-build-isolation

import os
import torch
from vllm import LLM, SamplingParams
from transformers import Qwen3OmniMoeProcessor
from qwen_omni_utils import process_mm_info

if __name__ == '__main__':
    # vLLM engine v1 not supported yet
    os.environ['VLLM_USE_V1'] = '0'
    
    MODEL_PATH = "Qwen/Qwen3-Omni-30B-A3B-Instruct"
    # MODEL_PATH = "Qwen/Qwen3-Omni-30B-A3B-Thinking"

    llm = LLM(
        model=MODEL_PATH,
        trust_remote_code=True,
        gpu_memory_utilization=0.95,
        tensor_parallel_size=torch.cuda.device_count(),
        limit_mm_per_prompt={'image': 3, 'video': 3, 'audio': 3},
        max_num_seqs=8,
        max_model_len=32768,
        seed=1234,
    )

    sampling_params = SamplingParams(
        temperature=0.6,
        top_p=0.95,
        top_k=20,
        max_tokens=16384,
    )

    processor = Qwen3OmniMoeProcessor.from_pretrained(MODEL_PATH)
    
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "video", "video": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Omni/demo/draw.mp4"}
            ],
        }
    ]

    text = processor.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True,
    )

    audios, images, videos = process_mm_info(messages, use_audio_in_video=True)
    
    inputs = {
        'prompt': text,
        'multi_modal_data': {},
        "mm_processor_kwargs": {
            "use_audio_in_video": True,
        },
    }

    if images is not None:
        inputs['multi_modal_data']['image'] = images
    if videos is not None:
        inputs['multi_modal_data']['video'] = videos
    if audios is not None:
        inputs['multi_modal_data']['audio'] = audios
    
    outputs = llm.generate([inputs], sampling_params=sampling_params)
    print(outputs[0].outputs[0].text)

user_system_prompt = "You are Qwen-Omni, a smart voice assistant created by Alibaba Qwen."

message = {
    "role": "system",
    "content": [
        {"type": "text", "text": f"{user_system_prompt} You are a virtual voice assistant with no gender or age... Keep replies concise and conversational, as if talking face-to-face."}
    ]
}