{"library":"fastsafetensors","type":"library","category":null,"description":"fastsafetensors is a Python library designed for high-performance loading of safetensors models, particularly optimized for GPU environments (CUDA, ROCm). It aims to offer faster loading times compared to the standard `safetensors` library for large models. The current version is `0.2.2`, and it maintains an active release cadence with frequent bug fixes and performance improvements.","language":"python","status":"active","version":"0.2.2","tags":["safetensors","pytorch","tensorflow","paddlepaddle","gpu","ml","high-performance","model-loading","rocm"],"last_verified":"Tue May 26","install":[{"cmd":"pip install fastsafetensors","imports":["from fastsafetensors import FastSafetensorsFile","from fastsafetensors.lazy_tensor_factory import LazyTensorFactory"]}],"homepage":null,"github":"https://github.com/foundation-model-stack/fastsafetensors","docs":null,"changelog":null,"pypi":"https://pypi.org/project/fastsafetensors/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":50,"avg_install_s":2.9,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/fastsafetensors/compatibility"}}