部署通义千问Qwen模型时，遇到Flash-Attention2装不上的问题

参考 Qwen2-VL 最佳实践 — swift 2.5.0.dev0 文档

我不去装什么Flash-Attention2，说是要编译好几个小时，然后我这边一直报错。

直接从头开始说我的部署方式，最后可以实现图片描述：
        1. 从“通义千问2-VL-7B-Instruct · 模型库”下载模型到本地

         2. 按照参考的文档里，完成如下操作：

git clone https://github.com/modelscope/ms-swift.git
cd ms-swift
pip install -e .[llm]

pip install git+https://github.com/huggingface/transformers.git
pip install pyav qwen_vl_utils

        3. 完成这些之后，应该就不需要安装Flash-Attention2了。跑我的这段代码就可以读取图片了：

import os
os.environ["CUDA_VISIBLE_DEVICES"] = '0'

from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model_path = "/data/ljx/txy/project/Qwen/Qwen2-VL-7B-Instruct"

# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
model = Qwen2VLForConditionalGeneration.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processer
processor = AutoProcessor.from_pretrained(model_path)

# 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 count range of 256-1280, to balance speed and memory usage.
# min_pixels = 256*28*28
# max_pixels = 1280*28*28
# processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)

# Messages containing multiple images and a text query
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "/data/ljx/txy/project/Qwen/other/test_img.png"},
            {"type": "text", "text": "Describe the image."},
        ],
    }
]

# Preparation for inference
# '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|><|vision_start|><|image_pad|><|vision_end|>Describe the two images separately.<|im_end|>\n<|im_start|>assistant\n'
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
generated_ids = model.generate(**inputs, max_new_tokens=128)
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[0])

自己改一下路径就行