# d3 runtime. Validated with transformers 5.17.0 on ROCm (torch 2.13).
torch>=2.8
transformers==5.17.0
accelerate>=1.10
safetensors>=0.6
huggingface_hub>=1.0
# GPU kernels for the Gated DeltaNet layers; without them transformers runs its slower PyTorch reference.
flash-linear-attention==0.5.2
einops
# Image inputs: PIL decodes the images; the processor's torchvision backend resizes them as in evaluation
# (install the torchvision build that matches torch; without it transformers falls back to a PIL resize).
pillow>=10
torchvision
# Video files: OpenCV decodes them with FFmpeg (frame arrays need no decoder).
opencv-python-headless
# d3_server.py needs nothing beyond the above (Python standard library HTTP server).