What this issue is

when I used the code for batch inference, it gives incomplete generation whenever batch size > 1.

To reproduce

I just used the code shared on the model card page

import os
from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# default: Load the model on the available device(s)
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2.5-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
)

# 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",
# )

# default processer
processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")

# 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 = 256*28*28
# max_pixels = 1280*28*28
# processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)


# Sample messages for batch inference
messages1 = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "img1.png"},
            {"type": "image", "image": "img2.png"},
            {"type": "text", "text": "What are the common elements in these pictures?"},
        ],
    }
]
messages2 = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who are you?"},
]
# Combine messages for batch processing
messages = [messages1, messages2]

# Preparation for batch inference
texts = [processor.apply_chat_template(msg, tokenize=False, add_generation_prompt=True) for msg in messages]
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=texts,
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

# Batch 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_texts = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_texts)

I got

['Both images appear to be X-rays of the knee joint, likely taken from the same patient at different times or under different conditions. ..', 
' addCriterion']

Notice, that the second generation contains 'addCriterion'.

To fix bug

add

processor.tokenizer.padding_side = "left"

then the second generation will be normal:

I am Qwen, a large language model created by Alibaba Cloud. I am designed to assist with a wide range of tasks, from answering questions and providing information to generating text based on prompts. How can I help you today?