Currently there are only binary wheels available at https://pypi.org/project/nvidia-cutlass-dsl

They include various binaries:

• lib/libmlir_c_runner_utils.so
• lib/libmlir_cuda_runtime.so
• lib/libmlir_float16_utils.so
• lib/libmlir_runner_utils.so
• python_packages/cutlass/_mlir/_mlir_libs/_cute.cpython-313-x86_64-linux-gnu.so
• python_packages/cutlass/_mlir/_mlir_libs/_cute_nvgpu.cpython-313-x86_64-linux-gnu.so
• python_packages/cutlass/_mlir/_mlir_libs/_mlir.cpython-313-x86_64-linux-gnu.so
• python_packages/cutlass/_mlir/_mlir_libs/_mlirDialectsGPU.cpython-313-x86_64-linux-gnu.so
• python_packages/cutlass/_mlir/_mlir_libs/_mlirDialectsLLVM.cpython-313-x86_64-linux-gnu.so
• python_packages/cutlass/_mlir/_mlir_libs/_mlirDialectsNVGPU.cpython-313-x86_64-linux-gnu.so
• python_packages/cutlass/_mlir/_mlir_libs/_mlirExecutionEngine.cpython-313-x86_64-linux-gnu.so
• python_packages/cutlass/_mlir/_mlir_libs/_mlirGPUPasses.cpython-313-x86_64-linux-gnu.so
• python_packages/cutlass/_mlir/_mlir_libs/_site_initialize_0.cpython-313-x86_64-linux-gnu.so
• python_packages/cutlass/_mlir/_mlir_libs/libCutlassIRPythonCAPI.so

While they work where available for different Python versions or architectures we may need to build it from source.

Is there any documentation on how to do that? Or are those libraries closed source?