Qwen3-VL-235B-A22B-Instruct-FP8

# -*- coding: utf-8 -*-
import torch
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from vllm import LLM, SamplingParams

import os
os.environ['VLLM_WORKER_MULTIPROC_METHOD'] = 'spawn'

def prepare_inputs_for_vllm(messages, processor):
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    # qwen_vl_utils 0.0.14+ reqired
    image_inputs, video_inputs, video_kwargs = process_vision_info(
        messages,
        image_patch_size=processor.image_processor.patch_size,
        return_video_kwargs=True,
        return_video_metadata=True
    )
    print(f"video_kwargs: {video_kwargs}")

    mm_data = {}
    if image_inputs is not None:
        mm_data['image'] = image_inputs
    if video_inputs is not None:
        mm_data['video'] = video_inputs

    return {
        'prompt': text,
        'multi_modal_data': mm_data,
        'mm_processor_kwargs': video_kwargs
    }


if __name__ == '__main__':
    # messages = [
    #     {
    #         "role": "user",
    #         "content": [
    #             {
    #                 "type": "video",
    #                 "video": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-VL/space_woaudio.mp4",
    #             },
    #             {"type": "text", "text": "这段视频有多长"},
    #         ],
    #     }
    # ]

    messages = [
        {
            "role": "user",
            "content": [
              {
                  "type": "image",
                  "image": "https://ofasys-multimodal-wlcb-3-toshanghai.oss-accelerate.aliyuncs.com/wpf272043/keepme/image/receipt.png",
              },
              {"type": "text", "text": "Read all the text in the image."},
            ],
        }
    ]

    # TODO: change to your own checkpoint path
    checkpoint_path = "Qwen/Qwen3-VL-235B-A22B-Instruct-FP8"
    processor = AutoProcessor.from_pretrained(checkpoint_path)
    inputs = [prepare_inputs_for_vllm(message, processor) for message in [messages]]

    llm = LLM(
        model=checkpoint_path,
        trust_remote_code=True,
        gpu_memory_utilization=0.70,
        enforce_eager=False,
        tensor_parallel_size=torch.cuda.device_count(),
        seed=0
    )

    sampling_params = SamplingParams(
        temperature=0,
        max_tokens=1024,
        top_k=-1,
        stop_token_ids=[],
    )

    for i, input_ in enumerate(inputs):
        print()
        print('=' * 40)
        print(f"Inputs[{i}]: {input_['prompt']=!r}")
    print('\n' + '>' * 40)

    outputs = llm.generate(inputs, sampling_params=sampling_params)
    for i, output in enumerate(outputs):
        generated_text = output.outputs[0].text
        print()
        print('=' * 40)
        print(f"Generated text: {generated_text!r}")

import time
from PIL import Image
from sglang import Engine
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor, AutoConfig

if __name__ == "__main__":
    # TODO: change to your own checkpoint path
    checkpoint_path = "Qwen/Qwen3-VL-235B-A22B-Instruct-FP8"
    processor = AutoProcessor.from_pretrained(checkpoint_path)

    messages = [
        {
            "role": "user",
            "content": [
              {
                  "type": "image",
                  "image": "https://ofasys-multimodal-wlcb-3-toshanghai.oss-accelerate.aliyuncs.com/wpf272043/keepme/image/receipt.png",
              },
              {"type": "text", "text": "Read all the text in the image."},
            ],
        }
    ]

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

    image_inputs, _ = process_vision_info(messages, image_patch_size=processor.image_processor.patch_size)

    llm = Engine(
        model_path=checkpoint_path,
        enable_multimodal=True,
        mem_fraction_static=0.8,
        tp_size=torch.cuda.device_count(),
        attention_backend="fa3"
    )

    start = time.time()
    sampling_params = {"max_new_tokens": 1024}
    response = llm.generate(prompt=text, image_data=image_inputs, sampling_params=sampling_params)
    print(f"Response costs: {time.time() - start:.2f}s")
    print(f"Generated text: {response['text']}")

@misc{qwen3technicalreport,
      title={Qwen3 Technical Report}, 
      author={Qwen Team},
      year={2025},
      eprint={2505.09388},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.09388}, 
}

@article{Qwen2.5-VL,
  title={Qwen2.5-VL Technical Report},
  author={Bai, Shuai and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Song, Sibo and Dang, Kai and Wang, Peng and Wang, Shijie and Tang, Jun and Zhong, Humen and Zhu, Yuanzhi and Yang, Mingkun and Li, Zhaohai and Wan, Jianqiang and Wang, Pengfei and Ding, Wei and Fu, Zheren and Xu, Yiheng and Ye, Jiabo and Zhang, Xi and Xie, Tianbao and Cheng, Zesen and Zhang, Hang and Yang, Zhibo and Xu, Haiyang and Lin, Junyang},
  journal={arXiv preprint arXiv:2502.13923},
  year={2025}
}
@article{Qwen2VL,
  title={Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution},
  author={Wang, Peng and Bai, Shuai and Tan, Sinan and Wang, Shijie and Fan, Zhihao and Bai, Jinze and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Fan, Yang and Dang, Kai and Du, Mengfei and Ren, Xuancheng and Men, Rui and Liu, Dayiheng and Zhou, Chang and Zhou, Jingren and Lin, Junyang},
  journal={arXiv preprint arXiv:2409.12191},
  year={2024}
}

@article{Qwen-VL,
  title={Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond},
  author={Bai, Jinze and Bai, Shuai and Yang, Shusheng and Wang, Shijie and Tan, Sinan and Wang, Peng and Lin, Junyang and Zhou, Chang and Zhou, Jingren},
  journal={arXiv preprint arXiv:2308.12966},
  year={2023}
}