Batch Inference

from transformers import AutoModelForImageTextToText, AutoProcessor

model = AutoModelForImageTextToText.from_pretrained(
    "Qwen/Qwen3-VL-235B-A22B-Instruct", 
    dtype="auto", 
    device_map="auto"
)
processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-235B-A22B-Instruct")

# For batch generation, padding_side should be set to left!
processor.tokenizer.padding_side = 'left'

# Sample messages for batch inference
messages1 = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "file:///path/to/image1.jpg"},
            {"type": "image", "image": "file:///path/to/image2.jpg"},
            {"type": "text", "text": "What are the common elements in these pictures?"},
        ],
    }
]

messages2 = [
    {"role": "system", "content": [{"type": "text", "text": "You are a helpful assistant."}]},
    {"role": "user", "content": [{"type": "text", "text": "Who are you?"}]},
]

# Combine messages for batch processing
messages = [messages1, messages2]

# Preparation for inference
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
    padding=True  # padding should be set for batch generation!
)
inputs = inputs.to(model.device)

# Inference: Generation of the output
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)

# Required: Set padding to left side
processor.tokenizer.padding_side = 'left'

# Required: Enable padding in template
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
    padding=True  # Must be True for batching
)

# Batch 1: Multiple images
messages1 = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "file:///path/to/image1.jpg"},
            {"type": "image", "image": "file:///path/to/image2.jpg"},
            {"type": "text", "text": "Compare these images."},
        ],
    }
]

# Batch 2: Single image
messages2 = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "file:///path/to/image3.jpg"},
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

# Batch 3: Text only
messages3 = [
    {
        "role": "user",
        "content": [{"type": "text", "text": "What is the capital of France?"}],
    }
]

# Process all together
messages = [messages1, messages2, messages3]

# Batch with video and image
messages1 = [
    {
        "role": "user",
        "content": [
            {
                "type": "video",
                "video": "file:///path/to/video.mp4",
            },
            {"type": "text", "text": "Summarize this video."},
        ],
    }
]

messages2 = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "file:///path/to/image.jpg"},
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

processor.tokenizer.padding_side = 'left'
messages = [messages1, messages2]

inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
    padding=True
)

import torch

model = AutoModelForImageTextToText.from_pretrained(
    "Qwen/Qwen3-VL-235B-A22B-Instruct",
    dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    device_map="auto",
)

try:
    generated_ids = model.generate(**inputs, max_new_tokens=128)
except RuntimeError as e:
    if "out of memory" in str(e):
        print("Reduce batch size or use smaller images/videos")
    raise