{"library":"vsa","type":"library","category":null,"description":"VSA (Video Sparse Attention) is a CUDA kernel for efficient sparse attention in video diffusion models, part of the FastVideo library. Current version 0.0.5 (PyPI) and 0.1.7 (GitHub release). Development is active with frequent releases. Requires Python >=3.10 and CUDA toolkit.","language":"python","status":"active","version":"0.1.7","tags":["video","attention","sparse","cuda","fastvideo"],"last_verified":"Sat May 09","install":[{"cmd":"pip install vsa","imports":["import vsa"]}],"homepage":null,"github":"https://github.com/hao-ai-lab/FastVideo","docs":null,"changelog":null,"pypi":"https://pypi.org/project/vsa/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":null}