requirements.txt

flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.3/flash_attn-2.7.3+cu12torch2.6cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
transformers-stream-generator
qwen-vl-utils
docling-core
torch==2.6.0
transformers
torchvision
accelerate
matplotlib
easydict
requests
hf_xet
spaces
pillow
gradio
addict
einops
numpy
timm