{"library":"sageattention","type":"library","category":null,"description":"SageAttention is a Python library providing accurate and efficient 8-bit plug-and-play attention mechanisms, including Mixture-of-Experts (MoE) implementations. It aims to accelerate large language models with minimal performance drop. The current bleeding-edge version is 2.0.1, though the PyPI package might lag behind GitHub releases. Releases typically occur when major architectural changes or significant features are implemented.","language":"python","status":"active","version":"2.0.1","tags":["attention","transformer","moe","mixture-of-experts","8-bit","deep-learning","pytorch"],"install":[{"cmd":"pip install sageattention","imports":["from sageattention import SageMoE"]},{"cmd":"pip install git+https://github.com/thu-ml/SageAttention.git","imports":[]}],"homepage":null,"github":"https://github.com/thu-ml/SageAttention","docs":null,"changelog":null,"pypi":"https://pypi.org/project/sageattention/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":50,"avg_install_s":1.5,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/sageattention/compatibility"},"provenance":{"verified_status":"import_fail","verified_at":"Fri Jul 03","last_verified":"Fri Jul 03","next_check":"Fri Jul 10","install_tag":null}}