{"library":"nvidia-cutlass-dsl-libs-base","type":"library","category":null,"description":"NVIDIA CUTLASS Python DSL (`nvidia-cutlass-dsl-libs-base`) provides a Pythonic interface for writing high-performance CUDA kernels using CUTLASS's CuTe library and tensor abstractions. It enables kernel development with automatic compilation to optimized PTX/SASS, offering performance comparable to hand-written CUDA C++ while enhancing developer productivity. Currently at version 4.4.2, the library is actively developed with frequent releases, often tied to new CUDA Toolkit versions and NVIDIA GPU architectures.","language":"python","status":"active","version":"4.4.2","tags":["cuda","gpu","high-performance","deep-learning","linear-algebra","nvidia","kernel","dsl","jit-compilation"],"install":[{"cmd":"pip install nvidia-cutlass-dsl","imports":["import cutlass.cute as cute","from cutlass.cute.runtime import from_dlpack","import cutlass_cppgen as cutlass"]},{"cmd":"pip install nvidia-cutlass-dsl-libs-base","imports":[]},{"cmd":"pip install nvidia-cutlass-dsl[cu13]","imports":[]}],"homepage":"https://developer.nvidia.com/cutlass","github":"https://github.com/NVIDIA/cutlass","docs":"https://github.com/NVIDIA/cutlass","changelog":null,"pypi":"https://pypi.org/project/nvidia-cutlass-dsl-libs-base/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":40,"avg_install_s":7.1,"avg_import_s":1.8,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/nvidia-cutlass-dsl-libs-base/compatibility"},"provenance":{"verified_status":"passing","verified_at":"Sun Jun 28","last_verified":"Sun Jun 28","next_check":"Tue Jul 28","install_tag":null}}