Setup Guide
System Requirements
- NVIDIA GPUs with Ampere architecture (RTX 30 Series, A100) or newer
- NVIDIA driver >=570.124.06 compatible with CUDA 12.8.1
- Linux x86-64
- glibc>=2.35 (e.g Ubuntu >=22.04)
- Python 3.10
Installation
Clone the repository:
Install system dependencies:
Install the package into a new environment:
Or, install the package into the active environment (e.g. conda):
CUDA variants:
--extra=cu128: CUDA 12.8--extra=cu129: CUDA 12.9
Downloading Checkpoints
- Get a Hugging Face Access Token with
Readpermission - Install Hugging Face CLI:
uv tool install -U "huggingface_hub[cli]" - Login:
hf auth login - Accept the NVIDIA Open Model License Agreement.
Checkpoints are automatically downloaded during inference and post-training. To modify the checkpoint cache location, set the HF_HOME environment variable.
Next Steps
Once the setup is complete, proceed to the post-training tutorial to learn how to use Cosmos Predict 2 for sports video generation with LoRA adaptation.