{"library":"nixl-cu12","type":"library","category":null,"description":"NIXL (NVIDIA Inference Xfer Library) is an open-source Python API designed to accelerate point-to-point communications in AI inference frameworks. It provides a unified abstraction layer over various memory types (CPU, GPU) and storage (file, block, object store) through a modular plugin architecture. The `nixl-cu12` package specifically targets CUDA 12 environments. NIXL is actively maintained with frequent releases, with version 1.0.0 being the current stable release.","language":"python","status":"active","version":"1.0.0","tags":["AI inference","data transfer","GPU","CUDA","high-performance","NVIDIA"],"install":[{"cmd":"pip install nixl-cu12","imports":["from nixl_cu12 import nixl_agent"]},{"cmd":"pip install \"nixl[cu12]\" # for CUDA 12\n# For backwards compatibility, 'pip install nixl' automatically installs nixl[cu12]","imports":[]}],"homepage":null,"github":null,"docs":null,"changelog":null,"pypi":"https://pypi.org/project/nixl-cu12/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":50,"avg_install_s":78.1,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/nixl-cu12/compatibility"},"provenance":{"verified_status":"passing","verified_at":"Fri Jul 03","last_verified":"Fri Jul 03","next_check":"Sun Aug 02","install_tag":null}}