Video-XL-2

pip install transformers==4.43.0
pip install torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 --index-url https://download.pytorch.org/whl/cu121
pip install decord
pip install einops
pip install opencv-python
pip install accelerate==0.30.0
pip install numpy==1.26.4
# optional
pip install flash-attn --no-build-isolation

from transformers import AutoTokenizer, AutoModel, AutoConfig, BitsAndBytesConfig, AutoModelForCausalLM
import torch

# load model 
model_path = '/root/Models/Video-XL-2'
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
device = 'cuda' if torch.cuda.is_available() else 'cpu'
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, device_map=device,quantization_config=None, attn_implementation="sdpa", torch_dtype=torch.float16, low_cpu_mem_usage=True)

gen_kwargs = {
    "do_sample": False,
    "temperature": 0.01,
    "top_p": 0.001,
    "num_beams": 1,
    "use_cache": True,
    "max_new_tokens": 256
}

model.config.enable_sparse = False

# input data
video_path = "/asset/demo.mp4"
question1 = "How many people in the video? (A)3 people (B)6 people. Please only respone the letter"

# params
max_num_frames = 150
sample_fps = 1  # extract frame at 1fps
max_sample_fps = 4

with torch.inference_mode():
    response = model.chat(video_path, tokenizer, question1, chat_history=None, return_history=False,max_num_frames=max_num_frames, sample_fps=sample_fps, max_sample_fps=max_sample_fps, generation_config=gen_kwargs)
    
print(response)

from transformers import AutoTokenizer, AutoModel, AutoConfig, BitsAndBytesConfig, AutoModelForCausalLM
import torch
import pdb
import argparse

torch.cuda.reset_peak_memory_stats()
# load model 
model_path = '/root/Models/Video-XL-2'
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
device = 'cuda:0' if torch.cuda.is_available() else 'cpu'
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, device_map=device,quantization_config=None, attn_implementation="sdpa", torch_dtype=torch.float16, low_cpu_mem_usage=True) # sdpa

gen_kwargs = {"do_sample": False, "temperature": 0.01, "top_p": 0.001, "num_beams": 1, "use_cache": True, "max_new_tokens": 128}

model.config.enable_chunk_prefill = True
prefill_config = {
    'chunk_prefill_mode': 'streaming',
    'chunk_size': 4,
    'step_size': 1,
    'offload': True,
    'chunk_size_for_vision_tower': 24,
}
model.config.prefill_config = prefill_config

# input data
video_path = "/asset/demo.mp4"
question1 = "How many people in the video? (A)3 people (B)6 people. Please only respone the letter"

# params
max_num_frames = 1300
sample_fps = None  # uniform sampling
max_sample_fps = None

with torch.inference_mode():
    response = model.chat(video_path, tokenizer, question1, chat_history=None, return_history=False,max_num_frames=max_num_frames, sample_fps=sample_fps, max_sample_fps=max_sample_fps, generation_config=gen_kwargs)
    

peak_memory_allocated = torch.cuda.max_memory_allocated()
print(f"Memory Peak: {peak_memory_allocated / (1024**3):.2f} GB")
print(response)

@article{shu2024video,
  title={Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding},
  author={Shu, Yan and Zhang, Peitian and Liu, Zheng and Qin, Minghao and Zhou, Junjie and Huang, Tiejun and Zhao, Bo},
  journal={arXiv preprint arXiv:2409.14485},
  year={2024}
}

@article{liu2025video,
  title={Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding},
  author={Liu, Xiangrui and Shu, Yan and Liu, Zheng and Li, Ao and Tian, Yang and Zhao, Bo},
  journal={arXiv preprint arXiv:2503.18478},
  year={2025}
}