{"library":"tensorizer","type":"library","category":null,"description":"Tensorizer is a Python library developed by CoreWeave for fast serialization and deserialization of PyTorch modules, models, and tensors. It aims to reduce model load times and CPU memory usage by efficiently streaming tensor data, supporting local filesystems, HTTP/HTTPS, and S3 endpoints. The current version is 2.12.0, with ongoing development and updates primarily driven by CoreWeave's needs for serving large AI models.","language":"python","status":"active","version":"2.12.0","tags":["pytorch","serialization","deserialization","deep-learning","mlops","performance"],"last_verified":"Mon May 25","install":[{"cmd":"pip install tensorizer","imports":["from tensorizer import TensorSerializer","from tensorizer import TensorDeserializer","from tensorizer.torch_compat import tensorizer_saving","from tensorizer.torch_compat import tensorizer_loading"]},{"cmd":"pip install git+https://github.com/coreweave/tensorizer","imports":[]}],"homepage":null,"github":"https://github.com/coreweave/tensorizer","docs":null,"changelog":"https://github.com/coreweave/tensorizer/blob/main/CHANGELOG.md","pypi":"https://pypi.org/project/tensorizer/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":20,"avg_install_s":72.6,"avg_import_s":6.76,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/tensorizer/compatibility"}}