warp.get_cuda_supported_archs

warp.get_cuda_supported_archs()

Return a sorted list of CUDA compute architectures that can be used as compilation targets.

The returned architectures represent the compute capabilities that Warp’s NVRTC compiler can generate code for. These values correspond to CUDA compute capability versions (e.g., 75 for sm_75, 80 for sm_80, 90 for sm_90).

Returns:

A sorted list of architecture values from lowest to highest, or an empty list if CUDA is not available or no architectures are supported.

Return type:

list[int]