vllm部署--Qwen2.5VL-7B

model

Qwen/Qwen2.5-VL-7B-Instruct

pytorch：

2.4.0+cu118

flash-attn

选择合适的版本，直接pip安装总是出错：
https://github.com/Dao-AILab/flash-attention/releases?page=2

flash-attn 版本 2.7.0.post1

requirements

accelerate==1.1.0
av==14.3.0
huggingface-hub==0.30.2
modelscope==1.25.0
scikit-image==0.24.0
requests==2.32.3
tokenizers==0.21.1
transformers==4.49.0
xformers==0.0.27.post2

测试代码

import torch
from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
model = Qwen2_5_VLForConditionalGeneration.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct",torch_dtype=torch.bfloat16,attn_implementation="flash_attention_2",device_map="auto",
)# The default range for the number of visual tokens per image in the model is 4-16384.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
min_pixels = 128*28*28
max_pixels = 512*28*28
processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)messages = [{"role": "user","content": [{"type": "image","image": "./1745224698785.jpg",},{"type": "text", "text": "请描述一下这幅图像。"},],}
]# Preparation for inference
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(text=[text],images=image_inputs,videos=video_inputs,padding=True,return_tensors="pt",
)
inputs = inputs.to("cuda")# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)