NVIDIA GPU#
Instructions to install FastVideo for NVIDIA CUDA GPUs.
Requirements#
OS: Linux or Windows WSL
Python: 3.10-3.12
CUDA 12.8
At least 1 NVIDIA GPU
Set up using Python#
Create a new Python environment#
Conda#
You can create a new python environment using Conda
1. Install Miniconda (if not already installed)#
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
bash Miniconda3-latest-Linux-x86_64.sh
source ~/.bashrc
2. Create and activate a Conda environment for FastVideo#
# (Recommended) Create a new conda environment.
conda create -n fastvideo python=3.12 -y
conda activate fastvideo
Note
PyTorch has deprecated the conda release channel. If you use conda
, please only use it to create Python environment rather than installing packages.
uv#
Tip
We highly recommend using uv
to install FastVideo. In our experience, uv
speeds up installation by at least 3x.
Note that you can also use uv
to install FastVideo in a Conda environment.
Or you can create a new Python environment using uv, a very fast Python environment manager. Please follow the documentation to install uv
. After installing uv
, you can create a new Python environment using the following command:
# (Recommended) Create a new uv environment. Use `--seed` to install `pip` and `setuptools` in the environment.
uv venv --python 3.12 --seed
source .venv/bin/activate
Installation#
pip install fastvideo
# or if you are using uv
uv pip install fastvideo
Also optionally install flash-attn:
pip install flash-attn --no-build-isolation
Installation from Source#
1. Clone the FastVideo repository#
git clone https://github.com/hao-ai-lab/FastVideo.git && cd FastVideo
2. Install FastVideo#
Basic installation:
pip install -e .
# or if you are using uv
uv pip install -e .
Optional Dependencies#
Flash Attention#
pip install flash-attn --no-build-isolation
Set up using Docker#
We also have prebuilt docker images with FastVideo dependencies pre-installed: Docker Images
Development Environment Setup#
If youβre planning to contribute to FastVideo please see the following page: Contributor Guide
Hardware Requirements#
For Basic Inference#
NVIDIA GPU with CUDA 12.8 support
For Lora Finetuning#
40GB GPU memory each for 2 GPUs with lora
30GB GPU memory each for 2 GPUs with CPU offload and lora
For Full Finetuning/Distillation#
Multiple high-memory GPUs recommended (e.g., H100)
Troubleshooting#
If you encounter any issues during installation, please open an issue on our GitHub repository.
You can also join our Slack community for additional support.